escapewu
20 verified skills20 total stars
codex-review
AI-powered code review using OpenAI Codex CLI. Use when the user asks to review, audit, or check their code — including "代码审核", "代码审查", "审查代码", "review", "code review", "帮我审核", "检查代码", "审一下". Performs lint + codex review in an isolated context, auto-updates CHANGELOG, and adapts reasoning effort based on change size.
tools1
grok_search
自适应 AI 搜索与最新信息检索 skill。会先评估任务复杂度，再在 grok-4.20-fast / grok-4.20-auto / grok-4.20-expert 之间做路由，必要时采用“fast 侦察 + fast 补缺 + expert 综合”的组合流程，在速度与质量之间取平衡。
data-ai1
codex-design-review
Targeted design/code review via Codex CLI. Use when a specific design document, implementation plan, code module, or feature scope needs focused review — not a blanket "review all uncommitted changes". Outputs a structured review report to `docs/feature/<module>/review-<slug>.md` as a collaboration artifact between the orchestrating agent and Codex. Use when the user asks to "review this design", "审查方案", "让 codex 审查", "review this feature", or when a design document needs validation before implementation begins.
tools1
project-analysis
深度项目分析工具。用于在现有 docs 不足、代码链路复杂、harness M0/M1 需要补足 TaskNode 输入上下文、或需要梳理系统架构、模块数据流、时序、性能风险时进行只读取证和结构化分析。常与 `project-docs-workflow`、`harness-engineering-plan` 配套使用；也可在用户明确要求架构分析、数据流分析、时序图、调用链梳理或性能排查时直接使用。默认应落文档：优先更新或新建 `docs/` 下合适长期文档，不停留在仅终端输出的 analysis-only 模式。
documentation1
autonomous-codex-supervision
Use when planning, launching, supervising, or integrating Codex/agent implementation work: tmux/cron supervisors, TaskNode task boards, Release-the-Hounds parallel worktrees, L1 full-auto project ownership, validation gates, bounded repair, and safe checkpointing.
development1
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
tools1
perplexity-search
Use when searching with escapeWu/perplexity-ai through its OpenAI-compatible HTTP endpoint. Provides config-driven quick/balanced/expert/deep routing over /v1/chat/completions, matching the current perplexity-ai model IDs.
data-ai1
mermaid-live-preview
Generate Mermaid diagram preview URLs for mermaid.live. Use when the user asks to preview, share, or create a link for a Mermaid diagram. Encodes Mermaid diagram code into a clickable mermaid.live/edit URL using pako (zlib) compression + URL-safe base64 encoding.
tools1
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
development1
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
tools1
template-skill
Replace with description of the skill and when Claude should use it.
tools1
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
development1
news-fetcher-api
Use when working with the news fetcher REST API at <news-fetcher-host> for supported-site lookup, domain article discovery, URL fetching, batch fetch/crawl workflows, fetch history queries, and Bearer-authenticated integration examples.
development1
harness-engineering-plan
Harness engineering planning skill. Decomposes software goals into milestones, TaskNodes, dependency-aware execution waves, stage gates, and validation evidence. Use when the user asks to plan a feature implementation, create a task breakdown, design milestones, create a TaskBoard, or structure a multi-step engineering effort.
development1
code-organization-harness
Use when adding a new feature module, fixing a bug, refactoring, or deciding where code/tests/docs should live. Guides agents to discover context with targeted grep, choose module boundaries, place files by domain and layer, and follow project-specific Next.js, Python, and Java code organization patterns.
development1
harness-setup
Bootstrap or retrofit a repo-wide harness setup: author AGENTS.md, docs overview/index maps, taskBoard control planes, and progressive-disclosure documentation that stays business- and stack-agnostic.
documentation1
project-docs-workflow
项目 docs 维护编排器。用于非 trivial 的开发任务、功能开发、bug 修复、重构、API 变更、跨模块修改前后：先扫描 docs/OVERVIEW.md、feature-*、reference-*，把相关文档作为半可信上下文；判断是否需要升级使用 project-analysis 做深度分析；实现完成后判断哪些文档受影响，并先询问用户确认后再更新。看到用户要“实现/修改/开发/修复”项目代码时，应优先触发此技能，而不是等用户主动提及 docs。
development1
progressive-disclosure-docs
Design, audit, or refactor project documentation so AI agents navigate by progressive disclosure: AGENTS.md/OVERVIEW.md as maps, feature/reference/archive indexes as routing layers, and detailed docs/task boards loaded only on demand. Use when creating or refactoring project docs for AI coding agents, auditing docs compatibility with context engineering, adding AGENTS.md or docs indexes, or migrating scattered Markdown into a navigable docs-first structure.
development1
project-dev-standards
create and refresh repository-specific development standards for an existing local codebase. use when the user wants to analyze a local repository, extract coding conventions from real files, generate docs/ai-dev-standards, create code review checklists, or update existing agents.md or claude.md files so future coding agents load the right standards before development. do not use for generic programming advice detached from a repository.
development1
database-schema-analyzer
analyze postgresql or mysql database schemas from ddl files, schema-only dumps, migration sql, or read-only database metadata. use when the user wants table structure summaries, primary keys, foreign keys, indexes, inferred table relationships, er diagrams, dbml, mermaid erd, schema documentation, or database relationship analysis for postgres/mysql schemas.
documentation1