bahayonghang
141 verified skills4,084 total stars
bib-search-citation
Search and cite from local BibTeX/BibLaTeX .bib libraries, including Zotero exports. Use to find, filter, preview, export, or generate LaTeX/Typst citation snippets by topic, author, year, venue, DOI, arXiv ID, keywords, abstract, fields, or compact filters. Do not use for manuscript writing or polishing.
testing288
latex-thesis-zh
中文 LaTeX 学位论文助手，面向已有 .tex 硕博论文项目与高校模板。用于编译诊断、GB/T 7714 参考文献、模板/章节结构、术语一致性、逻辑与文献综述、研究空白、摘要标题、三线表和去 AI 味修改。英文会议期刊论文用 latex-paper-en，审稿式总评用 paper-audit。
testing288
cover-letter
Submission cover-letter assistant for existing LaTeX manuscripts. Use to generate, optimize, align-check, preflight, and journal-fit-check cover letters against paper evidence and target venue framing. Do not use for editing main.tex, full manuscript audit, or bibliography search.
testing288
latex-paper-en
English LaTeX assistant for existing .tex conference or journal papers. Use for compile, venue formatting, bibliography, grammar, logic, abstract/title, figures, tables, pseudocode, related work, research gaps, adaptation, de-AI polish, translation, and submission readiness. Use latex-thesis-zh for Chinese theses and paper-audit for critique.
development288
typst-paper
Typst paper assistant for existing .typ manuscripts in English or Chinese. Use for compile/export diagnosis, venue formatting, BibTeX or Hayagriva checks, grammar, logic, abstract/title, tables, pseudocode, related work, research-gap framing, adaptation, de-AI polish, translation, and submission readiness. Use LaTeX skills for .tex sources.
development288
paper-audit
Reviewer-style audit and submission gate for academic papers in .tex, .typ, or .pdf. Use for peer-review critique, pre-submission readiness, pass/fail gate decisions, blocker triage, revision roadmaps, journal-style reports, or re-audits. Do not use for source editing, sentence polishing, bibliography search, or compile repair.
development288
industrial-ai-research
Industrial AI literature research with mandatory intake questions, venue-aware source prioritization, structured report outputs, and survey draft generation. Use when the user needs up-to-date research on predictive maintenance, intelligent scheduling, industrial anomaly detection, smart manufacturing, cyber-physical systems, edge AI for automation, or crossover robotics-for-industry topics. Also trigger for adjacent terms: "digital twin", "industrial IoT", "Industry 4.0", "manufacturing AI", "factory automation", "process optimization", or "survey draft" in industrial contexts.
tools238
drawio
Create, edit, replicate, import, and export draw.io diagrams with an offline YAML-first workflow. Use for general engineering and product diagrams: architecture, network topologies, flowcharts, UML/ER, org charts, Mermaid/CSV conversion, existing .drawio bundles, style presets, themes, and non-publication formula diagrams. For paper, thesis, journal, conference, IEEE/ACM, manuscript, camera-ready, or publication figures, prefer drawio-academic-skills; this base provides shared CLI, references, themes, schemas, styles, and optional Desktop export.
tools197
drawio-academic-skills
Publication-figure overlay for draw.io. Use instead of the general drawio skill whenever a diagram is for a paper, thesis, dissertation, journal, conference, IEEE/ACM submission, manuscript, camera-ready, Word/LaTeX figure, or other publication. Applies venue, figure-type, color, caption/legend, formula, and paper-readability gates for architecture, workflow, roadmap, network-topology, and replicated paper figures. Runs offline and YAML-first through the sibling ../drawio base for CLI, references, themes, schemas, styles, and Desktop export; never requires MCP or a live backend.
tools197
brainstorming-baha
在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。
data-ai15
codex-companion
Manage Codex background tasks, persistent job threads, adversarial code reviews, and job lifecycle (status, result, cancel) from inside any AI coding session. Use this skill proactively whenever the user wants to delegate work to Codex and check back later, run a security-focused or attack-minded code review, resume a previous Codex task, check on running Codex jobs. Also use when the user mentions "background task", "Codex job", "adversarial review", "diff review", or wants Codex to keep working while they do something else.
development15
antigravity-companion
Coordinate Antigravity companion workflows for staged review, focused task execution, follow-up analysis, and clear continuation boundaries. Use this skill when the user explicitly wants an Antigravity-native companion process, wants help deciding how Antigravity should review versus implement, or needs a structured Antigravity workflow instead of ad-hoc shell usage. Prefer this whenever the task is specifically about operating Antigravity as a companion rather than a single one-off command.
testing15
archify
Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone HTML files with inline SVG, dark/light theme toggle, and one-click export to PNG / JPEG / WebP / SVG. Use this skill for system architecture diagrams, infrastructure/cloud/security/network topology visuals, technical workflows, approval/runbook/CI/CD/process diagrams, API call sequences, request lifecycles, interaction diagrams, data pipelines, ETL/ELT maps, PII/governance/data-lineage diagrams, state machines, status transitions, retry/cancel/timeout paths, or any request that needs a polished browser-openable technical diagram rather than Mermaid or an editable whiteboard.
tools15
html-artifact
Create self-contained HTML artifacts, single-file by default and split into offline per-page bundles when oversized, for complex, visual, comparison-heavy, reviewable, or shareable work outputs. Use this skill when the user asks for an HTML artifact, browser-viewable report, implementation plan, PR/code review report, architecture explainer, design comparison, research briefing, incident report, status dashboard, temporary structured-data editor, mini deck, or design-system specimen. Prefer this skill for long Markdown-like outputs that benefit from navigation, cards, diagrams, filters, copy/export buttons, or annotated diffs. Do not use it for short answers, simple commands, commit messages, tiny patch summaries, or production UI implementation unless the user explicitly asks for a review artifact.
development15
codex-workflow-recommender
Analyze a repository and current Codex environment, then recommend Codex CLI, Codex App, AGENTS.md, skills, native subagents, plugins, MCP servers, config/hooks, and optional OMX workflow improvements without modifying files. Use when the user asks to optimize Codex workflows, improve Codex setup, recommend Codex automation, configure MCP/plugins/subagents, analyze AGENTS.md scope needs, or says "优化 Codex 流程", "Codex 工作流推荐", "给 Codex 配 MCP", "配置 Codex plugins", or "配置 Codex subagents".
tools15
agents-md-improver
Audit and improve Codex AGENTS.md guidance files in repositories. Use when the user asks to check, audit, update, optimize, or fix AGENTS.md files; asks for Codex project guidance maintenance; mentions nested AGENTS.md conflicts, stale commands, scoped instructions, sandbox or approval boundaries; or says "优化 AGENTS.md", "审计 AGENTS.md", "检查 nested AGENTS.md", or "更新 Codex 项目指导".
development15
brainstorming-baha
当用户想要 brainstorm 一个想法、设计 feature 或 spec 时使用。通过对话探索意图与需求，然后将 spec 文档写入 .brainstorm/ 并 STOP。不会自动接 implementation planning 或任何其他技能。
data-ai15
codex-workflow-recommender
Analyze a repository and current Codex environment, then recommend Codex CLI, Codex App, AGENTS.md, skills, native subagents, plugins, MCP servers, config/hooks, and optional OMX workflow improvements without modifying files. Use when the user asks to optimize Codex workflows, improve Codex setup, recommend Codex automation, configure MCP/plugins/subagents, analyze AGENTS.md scope needs, or says "优化 Codex 流程", "Codex 工作流推荐", "给 Codex 配 MCP", "配置 Codex plugins", or "配置 Codex subagents".
tools15
antigravity-companion
Coordinate Antigravity companion workflows for staged review, focused task execution, follow-up analysis, and clear continuation boundaries. Use this skill when the user explicitly wants an Antigravity-native companion process, wants help deciding how Antigravity should review versus implement, or needs a structured Antigravity workflow instead of ad-hoc shell usage. Prefer this whenever the task is specifically about operating Antigravity as a companion rather than a single one-off command.
testing15
claude-code-companion
Coordinate Claude Code companion-style workflows for multi-step implementation, bounded review, follow-up execution, and session-to-session continuation inside Claude Code. Use this skill when the user explicitly wants a Claude Code-native companion workflow, wants help structuring background or follow-up work in Claude Code, or needs clear guidance on when to use direct Claude Code actions versus a persistent companion-style process. Prefer this over generic advice whenever the task is specifically about Claude Code orchestration, review-first execution, or continuing a previous Claude Code task safely.
development15
codex-companion
Manage Codex background tasks, persistent job threads, adversarial code reviews, and job lifecycle (status, result, cancel) from inside any AI coding session. Use this skill proactively whenever the user wants to delegate work to Codex and check back later, run a security-focused or attack-minded code review, resume a previous Codex task, check on running Codex jobs. Also use when the user mentions "background task", "Codex job", "adversarial review", "diff review", or wants Codex to keep working while they do something else.
development15
cold-shower
Challenge ideas, requirements, technical plans, products, pricing, markets, pitch/BP narratives, and major personal decisions with a no-flattery adversarial review. Use when the user asks for 泼冷水, 挑刺, 骂我, 给我泼盆冷水, 假设你是我的对手, 帮我 challenge 一下, 我这个想法有什么问题, 哪里会崩, 魔鬼代言人, devil's advocate, challenge assumptions, 别夸我, hidden assumptions, failure modes, overengineering, missing evidence, or kill criteria before implementation or commitment. Do not trigger for ordinary code review unless the user explicitly asks to challenge assumptions or failure modes.
development15
handoff
Use when the user wants to compact context before auto-compaction kicks in, hand off an unfinished task to a fresh session, switch topics mid-stream and preserve state, or pick up yesterday's work in a new conversation. Produces a single handoff.md that captures completed work, blocked items with what was already tried, next concrete steps, and the minimum context needed to resume cold. Use proactively when context usage is high, a long-running task hits a natural break, or the user signals a session switch. Triggers include 上下文压缩, 交接文档, handoff, 续接会话, 主题切换, 接力, 明早接着干, context handoff, compact before, fresh session, continue tomorrow. Do NOT use for single-file fixes that finish in one commit (put it in the commit body), Q&A or pure investigation sessions, or end-of-session retrospectives meant for human review (those are different artifacts).
tools15
code-auditor
Structured code review across correctness, security, performance, readability, testing, and architecture, with language-specific guidance and human-readable findings. Use whenever the user asks to review a PR, inspect git changes before merge, audit a directory or file set, prepare merge feedback, summarize review findings, or do code review / PR review / CR / review comments / 代码审查. Adapt the output language to the user's context: use Chinese review wording for Chinese or mixed Chinese discussions, and English review wording for English-first discussions.
development15
document-writer
Write or update technical documentation from the real codebase and project files. Use whenever the user asks for README, API docs, architecture guides, user guides, CONTRIBUTING docs, migration notes, or JSDoc/code comments, and also when they want technical documentation rewritten into natural Chinese with correct terminology and formatting.
development15
touying
Author Typst slide decks with Touying. Use when working with .typ presentations, themes, or animations.
content-media15
gh-address-comments
Address GitHub PR review comments and actionable review threads with GitHub CLI. Use when triaging reviewer feedback, summarizing unresolved PR comments, or applying selected fixes on a pull request.
tools15
gh-fix-ci
Debug and fix failing GitHub PR checks with GitHub CLI. Use when GitHub Actions checks fail, when a PR has broken status checks, or when you need local reproduction commands for CI failures.
tools15
gh-bootstrap
Initialize GitHub repository configuration from vetted upstream templates. Use when setting up repository automation, issue and PR templates, CI workflows, or baseline GitHub project files for a new or existing repo.
tools15
deep-research-pro
Multi-source deep research skill for current-topic investigation, comparison, and cited report writing. Use when the user asks to research, compare, or deep-dive a topic with current web sources and citations, including phrases like research, deep dive, latest, 调研, 做个深度研究, or 带来源总结. Do not use for offline-only codebase questions, casual opinion requests, or when the user explicitly forbids web access.
development15
implementation-notes
Use when implementing a multi-step spec, PRD, design doc, GitHub issue, or approved plan where decisions, deviations, and tradeoffs accumulate during coding. Maintain a live implementation-notes.md alongside the work capturing design decisions (choices made where the spec was ambiguous), intentional deviations from the spec, alternatives considered and rejection criteria, and open questions for human review. Use proactively the moment implementation of a written spec begins, before the first edit. Triggers include 实施记录, 实现笔记, 决策日志, 边写边记, 按这个 spec 实现, 按这个计划做, implementation log, decision log, spec divergence, implement this plan. Do NOT use for single-file fixes, pure investigation, one-off scripts, work without a written spec to deviate from, or simple tasks where one commit captures the reasoning.
development15
roundtable
Multi-perspective roundtable discussion skill for exploring a topic through a truth-seeking moderator and a small set of representative real figures. Use when the user asks for 圆桌讨论 / roundtable / 多人物观点碰撞 / 让几位思想家讨论 / 模拟多方思想交锋 / 结构化辩论探索, or wants to examine one topic through disciplined multi-party debate rather than a plain summary. Do not use it for ordinary argumentative writing, generic pros/cons lists, or a single-speaker explanation.
testing15
bidwriter
智能标书编写专家，专精工程咨询、建筑设计、市政工程领域的投标文件编写。 当用户提到：标书、投标、招标、投标文件、技术标、商务标、招标响应、投标方案、 bid document、bid proposal、tender、proposal writing、编写标书、写标书、 招标文件分析、评分标准优化 时使用此技能。
documentation15
beautiful-mermaid-editor
Modify the Beautiful Mermaid live editor itself rather than writing ordinary Mermaid diagrams. Use when the task mentions the Beautiful Mermaid repo, `editor.ts`, generated `editor.html`, config panel/options, themes or dark mode, zoom, PNG/SVG export, clipboard behavior, sample presets, or renderer wiring for the editor. Do not use for generic Mermaid syntax help or normal Markdown Mermaid authoring.
tools15
claude-md-improver
Audit and improve Claude Code CLAUDE.md guidance files, .claude/rules/ path-scoped rules, and companion code_map.md navigation maps. Use when the user asks to check, audit, update, optimize, or fix CLAUDE.md files; mentions nested CLAUDE.md, additive loading, ancestor/descendant loading, path-scoped rules, @import chains, CLAUDE.local.md, claudeMdExcludes, or code_map.md; or says "优化 CLAUDE.md", "审计 CLAUDE.md", "检查嵌套 CLAUDE.md", "Claude Code 项目指导", "生成 code_map (Claude)". Make sure to use this skill whenever the user wants to manage Claude Code memory files at any layer, even if they only mention CLAUDE.md without explicit audit wording.
development15
code-quality-review
Run a code quality review focused on maintainability, structure, abstraction quality, file growth, branching complexity, boundary cleanliness, and refactoring opportunities. Use when the user asks for code quality review, code review, maintainability review, architecture quality review, PR code quality feedback, 代码质量审查, 代码质量 review, 可维护性审查, 架构质量审查, or review comments about code structure. Do not use for pure security review, formatting-only review, performance profiling, or implementation tasks unless the user also asks for a code quality review.
development15
agents-md-improver
Audit and improve Codex AGENTS.md guidance files and companion code_map.md navigation maps in repositories. Use when the user asks to check, audit, update, optimize, or fix AGENTS.md files; asks for Codex project guidance maintenance; mentions nested AGENTS.md conflicts, code maps, stale commands, scoped instructions, sandbox or approval boundaries; or says "优化 AGENTS.md", "审计 AGENTS.md", "检查 nested AGENTS.md", "更新 Codex 项目指导", or "生成 code_map.md".
development15
codex-dynamic-workflows
Use only when the user explicitly asks for swarm, subagents, parallel agents, dynamic workflow, multi-agent orchestration, 多智能体编排, or when the task truly needs coordinated research plus implementation plus review plus verification packets. Do not use for ordinary code review, planning-only work, single-line bugfixes, routine audits, or migrations unless orchestration is requested or at least two independent workflow dimensions are present.
development15
spark
Plan-first brainstorming workflow that turns an idea into an approved Markdown implementation plan by default. Use when the user wants to brainstorm, design, scope, or plan a feature/spec before implementation. Spark explores project context, asks only blocking questions, writes the plan under the project root's .plannings/YYYY-MM-DD-feature-slug.md path, self-reviews it, and waits for user approval. Create an HTML or visual plan/spec only when the user explicitly asks for HTML, browser-viewable, or visual output; save the paired .html beside the Markdown plan.
development15
code-quality-review
Run a code quality review focused on maintainability, structure, abstraction quality, file growth, branching complexity, boundary cleanliness, and refactoring opportunities. Use when the user asks for code quality review, code review, maintainability review, architecture quality review, PR code quality feedback, 代码质量审查, 代码质量 review, 可维护性审查, 架构质量审查, or review comments about code structure. Do not use for pure security review, formatting-only review, performance profiling, or implementation tasks unless the user also asks for a code quality review.
development15
improve-codebase-architecture
Review a codebase for architectural friction, rank deep-module refactoring opportunities, and draft RFCs for safer interfaces and boundary-test strategies. Use when the user wants to improve architecture, identify refactoring seams, consolidate tightly coupled modules, deepen shallow modules, redesign an interface around a core concept, replace brittle unit tests with boundary tests, or turn an architecture review into an RFC or issue draft. Chinese trigger phrases also apply: 架构改进, 抽象太浅, 模块拆得太碎, 接口太多, 测试钉死实现细节, 想写架构 RFC, 这块代码改一改, 模块边界乱.
development15
archive-planning
Archive root-level planning files (`task_plan.md`, `findings.md`, and `progress.md`) into a timestamped `.plannings/` directory for the current feature. Use when Codex should run `$archive-planning [feature-name]`, close out an active plan, preserve completed planning context, or replace the deprecated Codex prompt workflow with a deterministic skill script.
development15
git-commit
Safely orchestrate Conventional Commits for staged Git changes, or for all working-tree changes when the user explicitly asks to include everything. Use when the user asks to write a commit message, split staged changes, split all changes, commit everything regardless of stage state, include untracked files in the commit set, organize a messy index before committing, or generate structured commit text without pushing by default. Default to English. Switch to Chinese only when the user explicitly says `请使用中文拆分提交所有的改动`. Agent commits automatically inject `Agent-Task` / `Agent-Model` / `Generated-By` trailers and an `[AI]` header tag; Why-line is required for feat/fix/refactor/perf; supports a `chore(wip)` checkpoint mode for long-running agent tasks.
development15
paper-workbench
Researcher-profile-driven paper intake and literature workbench for academic workflows. Use this whenever the user wants to skim, deep-read, card, compare, synthesize, map research gaps, or build a literature review from papers, arXiv/AlphaXiv links, DOIs, PDFs, landing pages, or existing paper JSON / workbench artifacts. Normalize sources into `paper-record`, then route into scan, deep-read, card, synthesis, review, or compatibility modes (`json`, `interpret`, `xray`). Trigger even when the user only says things like “精读这篇”, “整合这几篇”, “找研究空白”, or “搭综述框架”.
development15
implementation-notes
Use when implementing a multi-step spec, PRD, design doc, GitHub issue, or approved plan where decisions, deviations, and tradeoffs accumulate during coding. Maintain a live implementation-notes.md alongside the work capturing design decisions (choices made where the spec was ambiguous), intentional deviations from the spec, alternatives considered and rejection criteria, and open questions for human review. Use proactively the moment implementation of a written spec begins, before the first edit. Triggers include 实施记录, 实现笔记, 决策日志, 边写边记, 按这个 spec 实现, 按这个计划做, implementation log, decision log, spec divergence, implement this plan. Do NOT use for single-file fixes, pure investigation, one-off scripts, work without a written spec to deviate from, or simple tasks where one commit captures the reasoning.
development15
claude-code-companion
Coordinate Claude Code companion-style workflows for multi-step implementation, bounded review, follow-up execution, and session-to-session continuation inside Claude Code. Use this skill when the user explicitly wants a Claude Code-native companion workflow, wants help structuring background or follow-up work in Claude Code, or needs clear guidance on when to use direct Claude Code actions versus a persistent companion-style process. Prefer this over generic advice whenever the task is specifically about Claude Code orchestration, review-first execution, or continuing a previous Claude Code task safely.
development15
content/skills/visual-media-design/excalidraw
--- name: excalidraw description: >- Create editable Excalidraw diagrams for architecture views, flowcharts, sequence flows, dependency maps, and other visuals that need a freeform canvas instead of text-only markup. Use when the user wants an Excalidraw file, an editable diagram, a whiteboard or sketch, or a spatial visual for a system with 3+ components or a multi-step flow. Prefer this over Mermaid when layout freedom or post-editing matters. Do not trigger for simple lists, qui
data-ai14
gh-address-comments
Address GitHub PR review comments and actionable review threads with GitHub CLI. Use when triaging reviewer feedback, summarizing unresolved PR comments, or applying selected fixes on a pull request.
tools14
gh-fix-ci
Debug and fix failing GitHub PR checks with GitHub CLI. Use when GitHub Actions checks fail, when a PR has broken status checks, or when you need local reproduction commands for CI failures.
tools14
paper-workbench
Researcher-profile-driven paper intake and literature workbench for academic workflows. Use this whenever the user wants to skim, deep-read, card, compare, synthesize, map research gaps, or build a literature review from papers, arXiv/AlphaXiv links, DOIs, PDFs, landing pages, or existing paper JSON / workbench artifacts. Normalize sources into `paper-record`, then route into scan, deep-read, card, synthesis, review, or compatibility modes (`json`, `interpret`, `xray`). Trigger even when the user only says things like “精读这篇”, “整合这几篇”, “找研究空白”, or “搭综述框架”.
development14
git-commit
Safely orchestrate Conventional Commits for staged Git changes, or for all working-tree changes when the user explicitly asks to include everything. Use when the user asks to write a commit message, split staged changes, split all changes, commit everything regardless of stage state, include untracked files in the commit set, organize a messy index before committing, or generate structured commit text without pushing by default. Default to English. Switch to Chinese only when the user explicitly says `请使用中文拆分提交所有的改动`. Agent commits automatically inject `Agent-Task` / `Agent-Model` / `Generated-By` trailers and an `[AI]` header tag; Why-line is required for feat/fix/refactor/perf; supports a `chore(wip)` checkpoint mode for long-running agent tasks.
development14
architecture-diagram
Create dark-themed standalone HTML architecture diagrams with inline SVG. Use when the user wants a browser-openable HTML architecture artifact for 架构图、系统架构图、云架构图、网络拓扑图、HTML 架构图, cloud infrastructure, or security-boundary work. Do not use for Mermaid, Excalidraw, or generic SVG/PNG-only diagrams.
development14
article-cover
Generate article cover images as SVG. Use when creating cover/banner/header graphics for blogs, documentation, social media cards, or OG images. Trigger this skill whenever the user mentions article covers, blog banners, post thumbnails, social sharing images, or any visual header for written content — even if they don't explicitly say 'SVG'. Do not use it for full-scene illustrations, photo editing, or slide theme work.
testing14
brand-design-md
当用户明确点名真实品牌、产品或媒体站点的视觉语言，并希望先从 getdesign.md 拉取结构化设计规范，再据此生成或改造 UI 代码时使用。适用于“做成 Apple/Stripe/Notion/WIRED 的感觉”“参考某品牌官网风格做页面”“把现有 React 组件改成 Vercel 风格”这类请求，即使用户没提 getdesign.md 也应优先触发。不要用于泛化的“更现代一点”、logo 设计、图片/海报生成、幻灯片换皮、图表/流程图或纯设计分析。
development14
design-artifact
Create HTML-first design artifacts. Use this skill whenever the user wants a browser-openable product prototype, clickable flow demo, landing or storytelling page, HTML slide deck or storyboard, motion concept, or a few design directions in one artifact, even if they never say 'HTML'. Prefer this skill for net-new design exploration and standalone front-end artifacts. Do not use it for brand-style transfer, pure retheming, architecture diagrams, poster or card outputs, or raster image generation.
tools14
roundtable
Multi-perspective roundtable discussion skill for exploring a topic through a truth-seeking moderator and a small set of representative real figures. Use when the user asks for 圆桌讨论 / roundtable / 多人物观点碰撞 / 让几位思想家讨论 / 模拟多方思想交锋 / 结构化辩论探索, or wants to examine one topic through disciplined multi-party debate rather than a plain summary. Do not use it for ordinary argumentative writing, generic pros/cons lists, or a single-speaker explanation.
testing14
fireworks-tech-graph
Generate polished technical diagrams as SVG, and export PNG when local export tooling is available. Use when the user wants an architecture diagram, flowchart, data flow, sequence diagram, agent or memory diagram, comparison matrix, timeline, or concept map rendered as a visual artifact instead of Mermaid or a hand-drawn whiteboard. Trigger on requests like 画图、帮我画、生成图、 做个图、架构图、流程图、时序图、可视化一下, or English requests such as draw diagram, architecture diagram, visualize this system, generate a flowchart, or create a technical SVG. Prefer this skill when the user wants publishable SVG/PNG output, style selection, or AI/agent-system diagram conventions.
tools14
paper2code
Citation-anchored paper-to-code workflow for turning research papers into a minimal, honest Python implementation. Use this whenever the user wants to implement a paper from an arXiv ID, arXiv URL, local PDF, OpenReview forum page, or OpenReview PDF URL. Trigger even when the user says things like “implement this paper”, “复现这篇”, or “把这篇论文写成代码” without naming the source type explicitly. Reject DOI-only requests and unsupported landing pages instead of pretending the paper can be fetched.
development14
content/skills/visual-media-design/mermaid-expert
--- name: mermaid-expert description: >- Expert guidance for Mermaid.js diagramming. Create flowcharts, sequence diagrams, class diagrams, state diagrams, Gantt charts, git graphs, and block diagrams using text-based syntax. Use when working with Mermaid, creating diagrams for Markdown/documentation, or visualizing workflows and architectures. Trigger whenever the user mentions Mermaid, wants a diagram in a README or docs, or needs text-based diagramming. version: 1.0.0 category: vis
development14
plain
Plain-language rewrite skill that turns existing content or questions into natural prose a smart 12-year-old can retell. Use whenever the user says 白话说 / 说人话 / plain / grok, wants jargon stripped away, or needs a concept, document, or explanation rewritten into concrete spoken language. Prefer this over `learn` for simplification and over `rank` for summarization. Do not use it for single-word vocabulary study.
development14
word
Deep single-word English mastery skill. Unpacks one English word's semantic image, modern usage, confusion points, and memory hook. Use when the user wants to deeply understand one English word, asks for deeper meaning or usage rather than translation, or wants a memorable vocabulary breakdown. Prefer this over `plain` or `learn` for a single vocabulary item. Do not use it for phrases, sentence translation, or multiple words at once; route multi-word card workflows to `word-flow`.
data-ai14
memory-system
本地记忆系统，将 Markdown 文件索引到 SQLite 实现跨会话语义搜索。当用户提到：记忆、memory、知识库、索引笔记、搜索记忆、跨会话记忆、记住这个、memory search、memory index、memory status、回忆、查找记忆 时触发。支持增量索引、混合搜索（向量+全文）、记忆添加和清理；不适用于云同步或跨设备共享。
databases14
typst
Generate and edit idiomatic Typst (.typ) code. Use when working with Typst files or when the user mentions Typst markup or document formatting.
development14
knowledge-absorber
深度解析链接、文档、代码或长文本，生成“零基础直达精通”的教学型笔记。适用于“深度解析这个链接”“把这篇讲透”“吃透这段代码”“帮我做学习笔记”等场景；不适用于一句话速览或纯链接转发。
tools14
learn
Multi-angle concept anatomy skill for a single concept or term. Breaks one idea into eight cuts, finds the shared deep structure, and compresses it into an org-mode insight note. Use when the user wants to deeply understand one concept, term, or idea from multiple perspectives, asks for 概念解剖 / concept anatomy / learn concept, or wants more than a plain-language paraphrase. Prefer this over `plain` when the goal is deep structure rather than simplification. Do not use it for quick rewrites, code walkthroughs, or multiple unrelated terms at once.
development14
cold-shower
Challenge ideas, requirements, technical plans, products, pricing, markets, pitch/BP narratives, and major personal decisions with a no-flattery adversarial review. Use when the user asks for 泼冷水, 挑刺, 骂我, 给我泼盆冷水, 假设你是我的对手, 帮我 challenge 一下, 我这个想法有什么问题, 哪里会崩, 魔鬼代言人, devil's advocate, challenge assumptions, 别夸我, hidden assumptions, failure modes, overengineering, missing evidence, or kill criteria before implementation or commitment. Do not trigger for ordinary code review unless the user explicitly asks to challenge assumptions or failure modes.
development14
rank
Domain-reduction skill that finds the smallest set of independent generators behind a messy field and proves them with four tests: generativity, minimality, independence, and predictive power. Use when the user asks for 秩 / irreducible structure / what really holds a domain up, or wants to reduce many phenomena to a small hidden core. Do not use it for ordinary summaries or plain-language rewrites.
testing14
skill-map
Skill map viewer for locally installed skills. Detects the current CLI, resolves that platform's installed-skills root, and renders a stable ASCII overview of installed names, versions, triggerability, and grouping. Use when the user asks what skills are installed on this machine, wants a local skill map, or says '技能地图', '本机 skills', '我装了哪些 skill', 'local skill list', or 'installed skills'. Also use this skill to surface overlap and consolidation suggestions across installed skills — trigger on '哪些 skill 重复', '相似 skill', 'skill 整理', 'skill 去重', '技能瘦身', 'consolidate skills', 'duplicate skills', 'deduplicate skills', or 'similar installed skills'. Do not use it for installable catalogs, registries, or recommendations.
tools14
gh-bootstrap
Initialize GitHub repository configuration from vetted upstream templates. Use when setting up repository automation, issue and PR templates, CI workflows, or baseline GitHub project files for a new or existing repo.
tools14
deep-research-pro
Multi-source deep research skill for current-topic investigation, comparison, and cited report writing. Use when the user asks to research, compare, or deep-dive a topic with current web sources and citations, including phrases like research, deep dive, latest, 调研, 做个深度研究, or 带来源总结. Do not use for offline-only codebase questions, casual opinion requests, or when the user explicitly forbids web access.
development14
card
Turn URLs, pasted text, Markdown, or article files into PNG knowledge cards and visual explainers. Supports five modes: `-l` long reading card, `-i` infographic, `-m` multi-card carousel, `-v` sketchnote, and `-c` black-and-white manga comic. Use whenever the user asks to make content into a card, long image, infographic, visual note, sketchnote, comic, manga page, or says '铸' / 'cast' / '做成图' / '做成卡片' / '视觉化一下', even if they do not specify a mode. Choose the best-fit mode automatically when no flag is given. Do not use it for generic photo illustration, slide decks, or editable diagram authoring.
testing14
word-flow
Word-to-card workflow skill that runs `word` first and then `card -i` for one or more explicit English words. Use when the user wants both deep word analysis and a visual card, says 词卡 / word card / word flow, or provides a clear list of English vocabulary items to turn into cards. Do not use it for raw dictionary lookup, generic English sentences, or ambiguous word targets; if the target list is unclear, ask for the exact words.
testing14
yt-dlp
Download videos via yt-dlp from YouTube, Bilibili, Twitter/X, TikTok, and 1000+ sites. Use when downloading video, extracting audio/music, grabbing subtitles/captions, or saving any online media. Trigger this skill whenever the user wants to download, save, rip, or extract media from a URL — even if they don't mention yt-dlp by name.
content-media14
screenshot
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed. Prefer a more specialized capture tool first for browsers, Figma, or other supported apps.
tools14
tech-design-doc
Generate technical design documents with proper structure, diagrams, and implementation details. Use when designing a new feature, documenting architecture decisions, or planning refactoring work. Default language is English.
development13
tech-blog
Write technical blog posts with source code analysis OR doc-driven research. Use when user wants to explain system internals, architecture, implementation details, or technical concepts with citations.
development13
academic-slides
Academic slide generation with dual engines
research13
qwen-companion
Coordinate Qwen CLI companion workflows for staged review, bounded follow-up execution, and explicit continuation inside repository work. Use this skill when the user explicitly wants a Qwen-native companion process, wants help structuring Qwen review versus implementation, or needs a clear Qwen CLI workflow with scoped next steps instead of generic shell usage. Prefer this when the task is specifically about operating Qwen as a structured companion.
tools13
bidwriter
智能标书编写专家，专精工程咨询、建筑设计、市政工程领域的投标文件编写。 当用户提到：标书、投标、招标、投标文件、技术标、商务标、招标响应、投标方案、 bid document、bid proposal、tender、proposal writing、编写标书、写标书、 招标文件分析、评分标准优化 时使用此技能。
documentation13
gemini-companion
Coordinate Gemini CLI companion workflows for staged review, focused task execution, follow-up analysis, and clear continuation boundaries. Use this skill when the user explicitly wants a Gemini-native companion process, wants help deciding how Gemini should review versus implement, or needs a structured Gemini CLI workflow instead of ad-hoc shell usage. Prefer this whenever the task is specifically about operating Gemini as a companion rather than a single one-off command.
tools13
code-auditor
Structured code review across correctness, security, performance, readability, testing, and architecture, with language-specific guidance and human-readable findings. Use whenever the user asks to review a PR, inspect git changes before merge, audit a directory or file set, prepare merge feedback, summarize review findings, or do code review / PR review / CR / review comments / 代码审查. Adapt the output language to the user's context: use Chinese review wording for Chinese or mixed Chinese discussions, and English review wording for English-first discussions.
development13
commit-daily-summary
Use when the user wants a same-day summary of git commits, a commit-based daily report, asks what they did today, wants to generate a work log from commits, or says 总结我今天做了什么, 总结我的提交, 提交总结, 今天提交总结, 日报. This is the default choice for any "日报" or "daily report" request unless the user explicitly asks for multi-project session aggregation. Use proactively whenever the user mentions commits, daily summary, work log, or end-of-day report.
testing13
document-writer
Write or update technical documentation from the real codebase and project files. Use whenever the user asks for README, API docs, architecture guides, user guides, CONTRIBUTING docs, migration notes, or JSDoc/code comments, and also when they want technical documentation rewritten into natural Chinese with correct terminology and formatting.
development13
latex-document-skill
Create, compile, and convert LaTeX and PDF documents. Use when drafting `.tex`, building PDFs, transforming formats, or extracting structured PDF content.
development13
improve-codebase-architecture
Review a codebase for architectural friction, rank deep-module refactoring opportunities, and draft RFCs for safer interfaces and boundary-test strategies. Use when the user wants to improve architecture, identify refactoring seams, consolidate tightly coupled modules, deepen shallow modules, redesign an interface around a core concept, replace brittle unit tests with boundary tests, or turn an architecture review into an RFC or issue draft.
development13
touying
Author Typst slide decks with Touying. Use when working with .typ presentations, themes, or animations.
content-media13
session-wrap
Use when the user wants to wrap up the current coding session, summarize what happened in this session before ending work, document learnings and decisions, produce a handoff note for the next session, decide what to commit, or says 总结会话, 会话总结, 收尾, 会话收尾, 结束会话, 总结本次会话. Use proactively when the user signals they are done working or switching context, even if they don't explicitly say "wrap up".
testing13
interview-plan
通过苏格拉底式访谈细化需求，优先使用 planning-with-files 文件计划模式生成持久化实施计划，不可用时降级为原生 Plan 模式。适用于需求细化、技术方案设计等场景。
tools13
bib-search-citation
Search, filter, and format entries from BibTeX or BibLaTeX .bib files for research workflows. Use when a user wants to find papers, search a bibliography, filter a library, or look up references by topic, author, year, venue, DOI, arXiv ID, keywords, annotation, abstract, or entry type. Handles Zotero-exported libraries. Supports compact search expressions such as author:, year-gte, type:, and has:, combined filters, research-oriented output fields, raw BibTeX export, and LaTeX/Typst citation snippet generation.
development13
mcp-to-skill
Convert MCP (Model Context Protocol) servers to Claude Code Skills. Use when: (1) User wants to convert an MCP server project to a skill (2) User mentions "MCP to skill", "convert MCP", "MCP 转 skill" (3) User has an MCP server codebase and wants to make it a reusable skill (4) User wants to analyze MCP server structure for skill creation (5) User says "MCP project is too hard to install" or "share MCP tools with others" (6) User wants to package MCP tools for non-technical users (7) User asks "how to distribute MCP tools" or "make MCP portable" Supports TypeScript/JavaScript and Python MCP servers. Handles Tools, Resources, and Prompts.
tools13
lsp-manager
Detect project languages, configure LSP servers, and troubleshoot language-server integration. Use this skill when setting up code intelligence, autocomplete, type checking, IDE integration, or diagnosing LSP failures — prefer it over manual config for any language-server task.
development13
rust-cli-tui-developer
Expert guidance for building Rust CLI and TUI applications using clap, inquire, and ratatui. Use this skill when creating command-line tools, argument parsers, interactive terminal prompts, or rich terminal UIs in Rust — prefer it over generic Rust advice for any CLI/TUI task.
tools13
project-daily-summary
Use when the user wants a same-day work summary grouped by project folder or repository, combining today's coding sessions, extracted plans, completed items, commits, and uncommitted changes, or says 项目日报, 今日工作总结, 按项目总结今天, 总结今天所有会话, 总结今天会话+提交+未提交改动. Use this instead of commit-daily-summary when the user explicitly wants multi-project aggregation or session-level evidence beyond pure git commits.
testing13
uv-expert
Expert guidance for the uv Python package manager. Use this skill when installing packages, managing virtual environments, setting up Python projects, configuring pyproject.toml, migrating from pip or poetry, or pinning Python versions — prefer it over generic pip advice for any uv-related task.
development13
card
Turn URLs, pasted text, Markdown, or article files into PNG knowledge cards and visual explainers. Supports five modes: `-l` long reading card, `-i` infographic, `-m` multi-card carousel, `-v` sketchnote, and `-c` black-and-white manga comic. Use whenever the user asks to make content into a card, long image, infographic, visual note, sketchnote, comic, manga page, or says '铸' / 'cast' / '做成图' / '做成卡片' / '视觉化一下', even if they do not specify a mode. Choose the best-fit mode automatically when no flag is given. Do not use it for generic photo illustration, slide decks, or editable diagram authoring.
testing11
bidwriter
智能标书编写专家，专精工程咨询、建筑设计、市政工程领域的投标文件编写。 当用户提到：标书、投标、招标、投标文件、技术标、商务标、招标响应、投标方案、 bid document、bid proposal、tender、proposal writing、编写标书、写标书、 招标文件分析、评分标准优化 时使用此技能。
documentation11
mermaid-expert
Expert guidance for Mermaid.js diagramming. Create flowcharts, sequence diagrams, class diagrams, state diagrams, Gantt charts, git graphs, and block diagrams using text-based syntax. Use when working with Mermaid, creating diagrams for Markdown/documentation, or visualizing workflows and architectures. Trigger whenever the user mentions Mermaid, wants a diagram in a README or docs, or needs text-based diagramming.
documentation11
gemini-image
Generate images using AI image generation API. Use when user wants to create, draw, paint, illustrate, or edit images. Supports text-to-image and image-to-image workflows. Trigger whenever the user asks to generate an image, create artwork, draw something, or edit an existing image.
development11
latex-document-skill
Create, compile, and convert LaTeX and PDF documents. Use when drafting `.tex`, building PDFs, transforming formats, or extracting structured PDF content.
development11
plain
Plain-language rewrite skill that turns existing content or questions into natural prose a smart 12-year-old can retell. Use whenever the user says 白话说 / 说人话 / plain / grok, wants jargon stripped away, or needs a concept, document, or explanation rewritten into concrete spoken language. Prefer this over `learn` for simplification and over `rank` for summarization. Do not use it for single-word vocabulary study.
development11
uv-expert
Expert guidance for the uv Python package manager. Use this skill when installing packages, managing virtual environments, setting up Python projects, configuring pyproject.toml, migrating from pip or poetry, or pinning Python versions — prefer it over generic pip advice for any uv-related task.
development11
yt-dlp
Download videos via yt-dlp from YouTube, Bilibili, Twitter/X, TikTok, and 1000+ sites. Use when downloading video, extracting audio/music, grabbing subtitles/captions, or saving any online media. Trigger this skill whenever the user wants to download, save, rip, or extract media from a URL — even if they don't mention yt-dlp by name.
content-media11
lib-slint-expert
Build native GUI applications with Slint and Rust. Use this skill when creating desktop UI, cross-platform apps, embedded UI, declarative UI components, or reusable component libraries with Slint — prefer it over generic Rust advice for any Slint UI task.
development11
gemini
Execute Gemini CLI for code generation, review, analysis, and web research. Use when tasks need a second AI perspective, Google Search grounding, codebase architecture analysis, or current web information. Trigger whenever the user mentions gemini, asks for Google Search results, needs real-time web data, wants codebase investigation, or requests a different AI's opinion on code.
tools11
improve-codebase-architecture
Review a codebase for architectural friction, rank deep-module refactoring opportunities, and draft RFCs for safer interfaces and boundary-test strategies. Use when the user wants to improve architecture, identify refactoring seams, consolidate tightly coupled modules, deepen shallow modules, redesign an interface around a core concept, replace brittle unit tests with boundary tests, or turn an architecture review into an RFC or issue draft.
development11
academic-slides
Academic slide generation with dual engines
research11
bib-search-citation
Search, filter, and format entries from BibTeX or BibLaTeX .bib files for research workflows. Use when a user wants to find papers, search a bibliography, filter a library, or look up references by topic, author, year, venue, DOI, arXiv ID, keywords, annotation, abstract, or entry type. Handles Zotero-exported libraries. Supports compact search expressions such as author:, year-gte, type:, and has:, combined filters, research-oriented output fields, raw BibTeX export, and LaTeX/Typst citation snippet generation.
development11
paper-interpretation-flow
Paper workflow: read papers + cast cards in one go. Takes one or more arxiv links, paper URLs, PDFs, or paper names. For each paper, runs ljg-paper (generates org analysis) then ljg-card -l (generates long reading card PNG). Use when user says '论文流', 'paper flow', '读论文并做卡片', '论文卡片', or provides multiple papers wanting both analysis and cards.
development11
paper-interpretation
Paper reader for non-academics. Takes a paper and extracts its ideas for personal use. Focuses on understanding, not academic critique. Use when user shares an arxiv link, paper URL, PDF, or asks to analyze a research paper. Trigger words: '读论文', '分析论文', 'paper', or when user shares an academic paper.
content-media11
xray-paper-skill
Deconstruct academic papers into core contributions, hidden assumptions, critical limitations, and napkin-worthy insights. Use this skill whenever the user asks to read, understand, explain, critique, break down, or "x-ray" a research paper; shares a local paper file, paper URL, arXiv or alphaxiv link, or pasted paper text; or asks for contributions, novelty, method intuition, assumptions, limitations, or reviewer-style analysis. Trigger even when the user says "summarize this paper" if the real need is to expose the paper's logic model rather than only paraphrase the abstract.
data-ai11
codex-companion
Manage Codex background tasks, persistent job threads, adversarial code reviews, and job lifecycle (status, result, cancel) from inside any AI coding session. Use this skill proactively whenever the user wants to delegate work to Codex and check back later, run a security-focused or attack-minded code review, resume a previous Codex task, check on running Codex jobs. Also use when the user mentions "background task", "Codex job", "adversarial review", "diff review", or wants Codex to keep working while they do something else.
development11
codex
OpenAI Codex CLI wrapper — five modes: `codex review` for PR/diff/commit review, adversarial challenge for edge cases and security, consult for second opinions on code or architecture, live research with citations via `--search`, and apply/fix for approved code changes. Use when the user invokes /codex or explicitly wants the local Codex CLI.
tools11
excalidraw
Create editable Excalidraw diagrams for architecture views, flowcharts, sequence flows, dependency maps, and other visuals that need a freeform canvas instead of text-only markup. Use when the user wants an Excalidraw file, an editable diagram, a whiteboard or sketch, or a spatial visual for a system with 3+ components or a multi-step flow. Prefer this over Mermaid when layout freedom or post-editing matters. Do not trigger for simple lists, quick explanations, or documentation-native Mermaid requests.
documentation11
screenshot
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
tools11
tech-blog
Write technical blog posts with source code analysis OR doc-driven research. Use when user wants to explain system internals, architecture, implementation details, or technical concepts with citations.
documentation11
knowledge-absorber
深度解析链接、文档或代码，生成“全能导师级”的教学笔记（零基础直达精通）。
tools11
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
tools11
touying
Author Typst slide decks with Touying. Use when working with .typ presentations, themes, or animations.
content-media11
typst
Generate and edit idiomatic Typst (.typ) code. Use when working with Typst files or when the user mentions Typst markup or document formatting.
development11
git-commit-cn
Safely orchestrate Chinese Conventional Commits for staged Git changes. Use when the user asks to write a commit message, split staged changes into multiple commits, organize a messy index before committing, prepare a Chinese commit, draft a Conventional Commit, or generate structured commit text without pushing by default.
documentation11
learn
Multi-angle concept anatomy skill for a single concept or term. Breaks one idea into eight cuts, finds the shared deep structure, and compresses it into an org-mode insight note. Use when the user wants to deeply understand one concept, term, or idea from multiple perspectives, asks for 概念解剖 / concept anatomy / learn concept, or wants more than a plain-language paraphrase. Prefer this over `plain` when the goal is deep structure rather than simplification. Do not use it for quick rewrites, code walkthroughs, or multiple unrelated terms at once.
development11
gh-bootstrap
Initialize GitHub repository configuration from vetted upstream templates. Use when setting up repository automation, issue and PR templates, CI workflows, or baseline GitHub project files for a new or existing repo.
tools11
rank
Domain-reduction skill that finds the smallest set of independent generators behind a messy field and proves them with four tests: generativity, minimality, independence, and predictive power. Use when the user asks for 秩 / irreducible structure / what really holds a domain up, or wants to reduce many phenomena to a small hidden core. Do not use it for ordinary summaries or plain-language rewrites.
testing11
word-flow
Word-to-card workflow skill that runs `word` first and then `card -i` for one or more explicit English words. Use when the user wants both deep word analysis and a visual card, says 词卡 / word card / word flow, or provides a clear list of English vocabulary items to turn into cards. Do not use it for raw dictionary lookup, generic English sentences, or ambiguous word targets; if the target list is unclear, ask for the exact words.
testing11
mcp-to-skill
Convert MCP (Model Context Protocol) servers to Claude Code Skills. Use when: (1) User wants to convert an MCP server project to a skill (2) User mentions "MCP to skill", "convert MCP", "MCP 转 skill" (3) User has an MCP server codebase and wants to make it a reusable skill (4) User wants to analyze MCP server structure for skill creation (5) User says "MCP project is too hard to install" or "share MCP tools with others" (6) User wants to package MCP tools for non-technical users (7) User asks "how to distribute MCP tools" or "make MCP portable" Supports TypeScript/JavaScript and Python MCP servers. Handles Tools, Resources, and Prompts.
tools11
article-cover
Generate article cover images as SVG. Use when creating cover/banner/header graphics for blogs, documentation, social media cards, or OG images. Trigger this skill whenever the user mentions article covers, blog banners, post thumbnails, social sharing images, or any visual header for written content — even if they don't explicitly say 'SVG'.
testing11
lsp-manager
Detect project languages, configure LSP servers, and troubleshoot language-server integration. Use this skill when setting up code intelligence, autocomplete, type checking, IDE integration, or diagnosing LSP failures — prefer it over manual config for any language-server task.
development11
interview-plan
通过苏格拉底式访谈细化需求，优先使用 planning-with-files 文件计划模式生成持久化实施计划，不可用时降级为原生 Plan 模式。适用于需求细化、技术方案设计等场景。
tools11
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
development11
paper-replication
深度学习论文复现技能。将学术论文中的模型架构转化为工业级 PyTorch 代码，包含论文解构、架构可视化(Mermaid)、代码实现和模块文档生成。当用户提供深度学习论文(PDF/文本)需要复现、实现模型、理解网络架构时使用。触发场景：帮我复现这篇论文、论文复现、实现这个模型、replicate this paper、reproduce this paper、implement this architecture、把论文里的网络写成代码。即使用户没有明确说复现，只要提供了深度学习论文并希望得到代码实现，也应触发此技能。
data-ai11
alphaxiv-paper-lookup
Look up, summarize, or explain any arXiv paper using alphaxiv.org's AI-generated overviews. Use this skill whenever the user shares an arXiv or alphaxiv URL, pastes a paper ID (e.g. 2401.12345), or asks to summarize, explain, read, or understand a research paper. Trigger even when the user only mentions a paper title or says "what does this paper say", "explain this paper", "give me the key ideas", or "what are the results". Prefer this over reading raw PDFs — it is faster and structured for LLM consumption.
data-ai11
memory-system
本地记忆系统，将 Markdown 文件索引到 SQLite 实现跨会话语义搜索。当用户提到：记忆、memory、知识库、索引笔记、搜索记忆、跨会话记忆、记住这个、memory search、memory index、memory status、回忆、查找记忆 时触发。支持增量索引、混合搜索（向量+全文）、记忆添加和清理。
databases11
code-auditor
Structured code review across correctness, security, performance, readability, testing, and architecture, with language-specific guidance and human-readable findings. Use whenever the user asks to review a PR, inspect git changes before merge, audit a directory or file set, prepare merge feedback, summarize review findings, or do code review / PR review / CR / review comments / 代码审查. Adapt the output language to the user's context: use Chinese review wording for Chinese or mixed Chinese discussions, and English review wording for English-first discussions.
development11
rust-cli-tui-developer
Expert guidance for building Rust CLI and TUI applications using clap, inquire, and ratatui. Use this skill when creating command-line tools, argument parsers, interactive terminal prompts, or rich terminal UIs in Rust — prefer it over generic Rust advice for any CLI/TUI task.
tools11
skill-map
Skill map viewer. Scans installed skills under ~/.claude/skills and renders an ASCII overview of name, version, triggerability, description, and category signals. Use whenever the user asks what skills are installed, available, or grouped, including phrases like 'skills', '技能', '技能地图', 'skill map', '我有哪些技能', '看看技能', '列出技能', or 'list skills'.
development11
word
Deep single-word English mastery skill. Unpacks one English word's semantic image, modern usage, confusion points, and memory hook. Use when the user wants to deeply understand one English word, asks for deeper meaning or usage rather than translation, or wants a memorable vocabulary breakdown. Prefer this over `plain` or `learn` for a single vocabulary item. Do not use it for phrases, sentence translation, or multiple words at once; route multi-word card workflows to `word-flow`.
data-ai11
roundtable
Multi-perspective roundtable discussion skill for exploring a topic through a truth-seeking moderator and a small set of representative real figures. Use when the user asks for 圆桌讨论 / roundtable / 多人物观点碰撞 / 让几位思想家讨论 / 模拟多方思想交锋 / 结构化辩论探索, or wants to examine one topic through disciplined multi-party debate rather than a plain summary. Do not use it for ordinary argumentative writing, generic pros/cons lists, or a single-speaker explanation.
testing11
document-writer
Write or update technical documentation from the real codebase and project files. Use whenever the user asks for README, API docs, architecture guides, user guides, CONTRIBUTING docs, migration notes, or JSDoc/code comments, and also when they want technical documentation rewritten into natural Chinese with correct terminology and formatting.
documentation11
gh-fix-ci
Debug and fix failing GitHub PR checks with GitHub CLI. Use when GitHub Actions checks fail, when a PR has broken status checks, or when you need local reproduction commands for CI failures.
tools11
gh-address-comments
Address GitHub PR review comments and actionable review threads with GitHub CLI. Use when triaging reviewer feedback, summarizing unresolved PR comments, or applying selected fixes on a pull request.
tools11
tech-design-doc
Generate technical design documents with proper structure, diagrams, and implementation details. Use when designing a new feature, documenting architecture decisions, or planning refactoring work. Default language is English.
documentation11