laitszkin
117 verified skills351 total stars
spec
將用戶模糊的複雜需求拆解為有嚴格實作範圍的規格文檔。產出包含 tasks.md、checklist.md、設計方案、架構 diff 與測試策略。形成完整規格包。不用於已有明確實作方案的簡單任務，不用於不需 spec 的單檔案變更。
testing3
commit
提交指引與提交前的必要品控閘門。將變更提交到 git repo 或推送到 remote 前，需完成所有品控項目。包括審查、文檔同步與 changelog 門檻。
documentation3
novel-to-short-video
Convert novel text into a loopable short-form video by extracting the single most compelling story segment, generating images and voiceover, and assembling a Remotion render. Use when users ask to turn novels or chapters into a 50-60 second narrative short, teaser reel, or looping story clip that feels self-contained yet leaves strong lingering curiosity.
tools3
codex-memory-manager
Manage persistent Codex user-preference memory from recent conversation history. Use when users ask to learn from the last 24 hours of chats, update `~/.codex/AGENTS.md`, maintain reusable preference-first memory under `~/.codex/memory/*.md`, or sync new preference categories discovered in `~/.codex/sessions` and `~/.codex/archived_sessions`.
development3
open-source-pr-workflow
PR-focused workflow for open-source repositories. Use when the user asks to prepare a PR branch from existing changes, draft/open/update a PR, or push a ready contribution branch. Do not use this skill for implementing product features or editing business logic; use it after code changes are already prepared. Enforce branch naming as codex/{change_type}/{changes}, open PRs directly by default without waiting for draft confirmation, show drafts only when the user explicitly asks to review them first, default forked repositories to open PRs against the upstream parent repository unless the user explicitly requests the fork, and write PR content in English by default with required sections for related issues or motivation, engineering decisions with rationale, and test results with commands. For code-affecting changes, run code-simplifier before opening the PR.
development3
openclaw-configuration
Build, audit, and explain OpenClaw configuration from official documentation. Use when configuring `~/.openclaw/openclaw.json`, mapping config options, adjusting skills or secrets, generating validated snippets, or diagnosing config errors with `openclaw config`, `openclaw configure`, and `openclaw doctor`.
development3
video-production
Generate long-form videos (more than 10 minutes) by following user instructions and invoking related skills only when needed (`openai-text-to-image-storyboard`, `docs-to-voice`, `remotion-best-practices`). For text inputs, extract a complete long-form story arc, generate fresh storyboard images (no reuse of previously generated pictures), and render a 16:9 animated long-form video.
documentation3
version-release
協助完成自動化版本發佈。同步文檔、更新版本號、推送 tag 並建立 GitHub Release。
tools3
marginfi-development
Build or analyze integrations on the Solana-based marginfi protocol using the official TypeScript SDK, Rust CLI, and protocol docs. Use when implementing or reviewing marginfi deposits, withdrawals, borrows, repayments, flash loans, liquidations, permissionless banks, bank configuration, account-health logic, or raw instruction mapping, and ground the work in official marginfi documentation before coding.
tools3
solana-development
Build or maintain Solana applications in Rust using official Solana development docs. Use when users ask for native Solana programs, Rust SDK clients, account modeling, instruction design, PDAs, CPIs, local testing, deployment, upgrades, or Solana-specific debugging in Rust codebases.
tools3
maintain-project-constraints
基於 repo 最新程式碼與文檔，更新 CLAUDE.md 和 AGENTS.md 這兩份項目規範文件。注意兩者服務不同的 coding agent：CLAUDE.md 給 Claude Code，AGENTS.md 給 Codex 等非 Claude agent。
development3
harden-app-security
Evidence-first adversarial security audit workflow focused on vulnerability discovery only. Use when users ask to find exploitable flaws, reproduce them with concrete evidence, and report prioritized risks across agent systems, financial programs, and common software/web apps (including SQL injection and related attacks).
development3
improve-observability
Add focused observability to an existing system so opaque workflows become diagnosable. Use when users ask to improve observability, add instrumentation, expand logs/metrics/traces, expose failure reasons, or make a business flow easier to debug without changing the product behavior itself.
development3
docs-project
以 repo 程式碼為唯一依據，維護標準化的 docs/features/、docs/architecture/、docs/principles/ 文檔， 並清理已失效或重複的舊文檔。每條文檔記述必須可追溯至實際程式碼證據。
testing3
implement
Loads the PROMPT.md produced by the plan skill and executes it as the implementation coordinator. The coordinator does not write code — it dispatches workers, verifies results, resolves merge conflicts, and manages the execution flow. All execution logic is defined in PROMPT.md.
development3
test-case-strategy
Designs test strategy based on risk analysis — selects the right test level and method for the current context. Not for exploratory tasks without tests, nor for tasks where the test type is already predetermined.
testing3
spec
Transforms user requirements into strictly-scoped business specification documents (SPEC.md). Must dispatch subagents to research the repository before writing (skippable for greenfield repos). Produces batch specs when requirements exceed 5 BDD items. Not for discussion without PROPOSAL.md, nor for single-file changes that don't need a spec.
testing3
systematic-debug
Systematically investigates unexpected behavior — reproduces the issue by writing a test, fixes the root cause, and establishes a regression test. Not for simple fixes where the root cause is already known, nor for intuitive fixes without test verification.
development3
review-codebases
Repository-wide code review workflow that requires reading the full codebase before judging, prioritizes architecture findings over implementation details, and publishes one GitHub issue per confirmed finding through open-github-issue. Use when users ask for a code review, repository audit, architecture review, maintainability review, or complete codebase inspection.
development3
recover-missing-plan
Recover a missing or mismatched `docs/plans/...` plan set by verifying the path, checking archives and git history, reading the authoritative issue context, and restoring or reconstructing `spec.md`, `tasks.md`, `checklist.md`, `contract.md`, and `design.md` before implementation continues.
testing3
scheduled-runtime-health-check
Use a background terminal to run a user-specified command immediately or in a requested time window, and optionally explain findings from the captured logs after the run. Use when users want timed project execution, bounded runtime checks, or post-run log-based findings.
testing3
record-spending
Maintain monthly multi-account bookkeeping ledgers in Excel. Use when the user asks to record income, expenses, transfers, deposits, withdrawals, balance changes, account additions, account renames, or monthly asset/liability reviews. Always read ACCOUNT.md first, use the spreadsheet skill to keep one worksheet per account plus a monthly summary sheet, and keep ACCOUNT.md and CHART.md synchronized.
data-ai3
financial-research
Research the most important tradeable instruments to watch for the coming week by reviewing the most recent completed local week of financial and economic news, then produce a standardized PDF market report. Use when the user asks for a weekly market briefing, macro recap, market sentiment summary, key financial news review, or a next-week trading watchlist.
testing3
feature-propose
Professional product-management workflow for proposing features from an existing codebase. Use when the user asks to understand an application, classify features from a user perspective into MVP/Important/Enhancement/Performance tiers, ask 3-5 clarifying questions when needed, propose numbered feature recommendations, publish accepted proposals through `open-github-issue`, record accepted items in AGENTS.md/CLAUDE.md, and remove implemented items from AGENTS.md/CLAUDE.md.
development3
answering-questions-with-research
This skill should be used when the user asks a question that needs complete, evidence-based answers by combining repository discovery with web research.
development3
deep-research
在互聯網上對特定主題進行深度搜索。 驗證資訊正確性。 生成附有官方來源的完整研究報告。
research3
cjk-pdf
Handle CJK PDF font selection, rendering requirements, and visual QA for Chinese-compatible PDF output. Use when any skill needs to render PDFs with Chinese or mixed CJK text, verify font paths, apply content safety rules, and perform screenshot-based visual QA.
testing3
develop-new-features
從零開始打造新專案。將產品需求轉化為可批准的 spec，再實作為可驗證的交付成果。
development3
commit
提交指引與提交前的必要品控閘門。將變更提交到 git repo 或推送到 remote 前，需完成所有品控項目。包括審查、文檔同步與 changelog 門檻。
documentation3
docs-to-voice
Convert text and document content into audio files and sentence-level subtitle timelines under project_dir/audio/{project_name}/. Supports both macOS say and Alibaba Cloud Model Studio API modes.
development3
enhance-existing-features
在既有系統上安全地增強或調整產品行為。 先讀懂受影響模組，再判斷直接實作或走 spec。 非平凡變更必須通過 test-case-strategy。
testing3
financial-research
Research the most important tradeable instruments to watch for the coming week by reviewing the most recent completed local week of financial and economic news, then produce a standardized PDF market report. Use when the user asks for a weekly market briefing, macro recap, market sentiment summary, key financial news review, or a next-week trading watchlist.
testing3
improve-observability
Add focused observability to an existing system so opaque workflows become diagnosable. Use when users ask to improve observability, add instrumentation, expand logs/metrics/traces, expose failure reasons, or make a business flow easier to debug without changing the product behavior itself.
development3
katex
Render and embed math formulas with KaTeX using official documentation-backed patterns. Use when an agent needs inline or display math in HTML, Markdown, MDX, or other text-based outputs, or when it should generate insertion-ready KaTeX snippets from TeX.
development3
open-github-issue
Publish structured GitHub issues across multiple issue categories with deterministic auth fallback, target-repo resolution, README-based language detection, and draft-only fallback when authentication is unavailable. Use when users ask to open GitHub issues from confirmed findings, accepted proposals, documentation gaps, security risks, observability gaps, or prepared issue content.
development3
merge-changes-from-local-branches
將 spec 相關的本地實作分支合併回當前分支。按 coordination.md 的建議順序解決衝突。
tools3
open-source-pr-workflow
PR-focused workflow for open-source repositories. Use when the user asks to prepare a PR branch from existing changes, draft/open/update a PR, or push a ready contribution branch. Do not use this skill for implementing product features or editing business logic; use it after code changes are already prepared. Enforce branch naming as codex/{change_type}/{changes}, open PRs directly by default without waiting for draft confirmation, show drafts only when the user explicitly asks to review them first, default forked repositories to open PRs against the upstream parent repository unless the user explicitly requests the fork, and write PR content in English by default with required sections for related issues or motivation, engineering decisions with rationale, and test results with commands. For code-affecting changes, run code-simplifier before opening the PR.
development3
optimise-skill
Applies prompt engineering to optimize agent skill SKILL.md files — reduces redundancy, separates behavioral guidance from format, aligns with proven methodology. Reads the target skill's full directory, analyzes its structure, and produces an optimized rewrite.
development3
record-spending
Maintain monthly multi-account bookkeeping ledgers in Excel. Use when the user asks to record income, expenses, transfers, deposits, withdrawals, balance changes, account additions, account renames, or monthly asset/liability reviews. Always read ACCOUNT.md first, use the spreadsheet skill to keep one worksheet per account plus a monthly summary sheet, and keep ACCOUNT.md and CHART.md synchronized.
data-ai3
resolve-review-comments
Read GitHub pull request review comments, analyze each thread, decide whether to adopt feedback, implement adopted changes, push updates to the same PR branch, and resolve addressed review threads. Use when users ask to process PR review feedback by PR number or current branch context.
testing3
discover-security-issues
Discovery-only adversarial audit: map trust boundaries, run module catalogs (`agent-system`, `financial-program`, `software-system`, `combined`), reproduce exploitable behavior with payloads/commands and `path:line` evidence; prioritize impact × exploitability—**no code edits, no PRs, no auto-remediation**. Use for security review, vuln hunting, SQLi/XSS/auth/IDOR checks, agent prompt-injection/tool abuse, money-path races **STOP** when user wants patches shipped—hand off findings… BAD single vague “looks fine”… GOOD two-pass repro, hypothesis vs confirmed…
tools3
maintain-skill-catalog
Maintain this SKILL catalog repo: reconcile `SKILL.md` frontmatter/`Dependencies`, `agents/openai.yaml`, README inventory, classify vendored vs external vs unpublished-local aliases, prefer extracting shared workflows over duplicating long prose, and always rerun `apltk validate-skill-frontmatter` plus `apltk validate-openai-agent-config` before finishing—never invent package names or installers for unverified deps. Use when CI metadata breaks, users ask to “sync skills”, or dependency docs drift. Do not use for random application repos that are not this catalog layout. Bad: marketing a `~/.claude` draft as an npm dependency… Good: label it “local optional” and link once in README instead of pasting the blurb into five skills…
development3
ship-github-issue-fix
Resolve a GitHub issue in an existing repository and submit the fix directly to the requested branch without opening a PR or doing release work. Use when users ask to read issue N, implement the fix, decide whether planning artifacts are needed, run the relevant tests, and commit/push the result to `main` or another specified branch.
testing3
text-to-short-video
Generate 30-60 second short videos by directly calling an OpenAI-compatible video generation API from text. Keep role consistency by using roles.json as role prompt source and only updating role descriptions.
development3
discover-edge-cases
Diff-first (or full-repo) discovery of **reproducible** edge-case risks: boundaries, null/empty, failure paths, concurrency, observability; evidence via code/tests/runtime—**no edits, no new tests, no PRs**. For code-affecting scope, cross-check with **`discover-security-issues`** before final report. Use for edge-case review, hardening gaps, unusual inputs/error paths, pre-merge risk pass **STOP** implementation or “just fix it here”… BAD unproven alarm list… GOOD path:line + double repro…
development3
version-release
協助完成自動化版本發佈。同步文檔、更新版本號、推送 tag 並建立 GitHub Release。
tools3
learning-error-book
A learning-focused error-book workflow. When the user asks to summarize mistakes, the agent summarizes mistakes made while solving questions, writes structured reference data, and renders polished PDFs directly without Markdown as an intermediate.
documentation3
archive
將已完成的spec歸檔到 `docs/archive/` 下。當你需要將spec歸檔時，調用這個技能。
documentation3
feature-propose
Professional product-management workflow for proposing features from an existing codebase. Use when the user asks to understand an application, classify features from a user perspective into MVP/Important/Enhancement/Performance tiers, ask 3-5 clarifying questions when needed, propose numbered feature recommendations, publish accepted proposals through `open-github-issue`, record accepted items in AGENTS.md/CLAUDE.md, and remove implemented items from AGENTS.md/CLAUDE.md.
development3
analyse-app-logs
Comprehensive application log investigation workflow that reads logs end-to-end, correlates signals with code paths and runtime context, and identifies evidence-backed issues with impact and remediation steps. Use when users ask to analyze logs, investigate incidents, find root causes from log records, explain recurring warnings/errors, or check whether logs reveal hidden system problems.
development3
read-github-issue
Read and search remote GitHub issues via GitHub CLI (`gh`). Use when users ask to list issues, filter issue candidates, inspect a specific issue with comments, or gather issue context before planning follow-up work. Prefer the bundled CLI tools when they are present and working, but fall back to direct `gh issue list` / `gh issue view` commands when the tools are missing or fail for repository-specific reasons.
tools3
openai-text-to-image-storyboard
Generate storyboard images by using agent-decided prompts and calling an OpenAI-compatible image generation API. Use when users want chapters, novels, articles, or scripts converted into image sets under pictures/{content_name}, with API URL and API key loaded from this skill folder's .env by default.
development3
novel-to-short-video
Convert novel text into a loopable short-form video by extracting the single most compelling story segment, generating images and voiceover, and assembling a Remotion render. Use when users ask to turn novels or chapters into a 50-60 second narrative short, teaser reel, or looping story clip that feels self-contained yet leaves strong lingering curiosity.
tools3
implement-specs
當你需要在當前分支之中實作spec時，使用這個技能。
tools3
shadow-api-model-research
Investigate gated or shadow LLM APIs by capturing real client request shapes, separating request-shape gating from auth/entitlement checks, replaying verified traffic patterns, and attributing the likely underlying model with black-box fingerprinting. Use when users ask how Codex/OpenClaw/custom-provider traffic works, want a capture proxy or replay harness, need LLMMAP-style model comparison, or want a research report on which model a restricted endpoint likely wraps.
tools3
exam-pdf-workflow
Create, typeset, and grade exam-style PDF deliverables for study workflows. Use when the user asks to read lecture or exam PDFs, generate mock exams, produce matching solution books, render math-heavy content with KaTeX, or grade completed answer-book PDFs into a scored graded PDF.
content-media3
document-vision-reader
Convert rendered non-plain-text files into temporary screenshots, inspect those screenshots as images, and answer the user's request from the visible visual output. Use when an agent needs to inspect PDFs, PPT/PPTX decks, scanned documents, forms, spreadsheets, or other files whose rendered appearance matters more than raw text extraction.
documentation3
document-vision-reader
Convert rendered non-plain-text files into temporary screenshots, inspect those screenshots as images, and answer the user's request from the visible visual output. Use when an agent needs to inspect PDFs, PPT/PPTX decks, scanned documents, forms, spreadsheets, or other files whose rendered appearance matters more than raw text extraction.
documentation3
systematic-debug
系統性排查非預期行為。透過撰寫測試重現問題，修復後建立回歸測試防止再次出現。不用於已明確知道根因的簡單修復，不用於不需測試驗證的直覺式修正。
development3
implement
在當前分支或獨立 worktree 中依 spec 完成實作。按 tasks.md 逐項實作，按 checklist.md 逐項驗收，最後回填 spec 以反映實際代碼狀態。不用於不需 spec 的單檔案變更，不用於無明確 tasks.md 的探索性任務。
testing3
enhance-existing-features
在既有系統上安全地增強或調整產品行為。 先讀懂受影響模組，再判斷直接實作或走 spec。 非平凡變更必須通過 test-case-strategy。
testing3
fix
依照 code review report 中的建議方案修復代碼問題。P0-P3 等級逐一處理。不用於沒有 code review report 的情境，不用於未經審查直接修復，不用於非代碼問題的修復。
development3
develop-new-features
從零開始打造新專案。將產品需求轉化為可批准的 spec，再實作為可驗證的交付成果。
development3
deep-research
在互聯網上對特定主題進行深度搜索。 驗證資訊正確性。 生成附有官方來源的完整研究報告。
research3
init-project-html
Initialize the project architecture atlas. Use the apltk CLI to map feature and submodule relationships into a renderable HTML architecture diagram following the C4 model (Context → Container → Component → Code).
tools3
update-project-html
Incrementally refresh the architecture atlas when the project diagram drifts from actual code. Measures drift before updating to determine scope, then updates the base atlas and re-renders HTML.
development3
design
Reads SPEC.md, validates technical feasibility through web research, finds quality reference implementations, confirms tech stack compatibility, then produces DESIGN.md (architecture design, external dependencies), CHECKLIST.md (verification strategy), and Architecture Diff. Not for use without a SPEC.md.
development3
qa
Reads spec documents and the review output REPORT.md, then generates a self-contained fix coordinator prompt (FIX.md) with issue inventory, dependency analysis, batch scheduling, regression test design, and pre-written worker prompts. The generated FIX.md is consumed directly by the fix skill.
testing3
commit-and-push
提供提交指引以及作為提交前的必要品控閘門。當你需要將變更提交到git repo或者是推送到remote，使用這個技能。
tools3
archive-specs
將已完成的spec歸檔到 `docs/archive/` 下。當你需要將spec歸檔時，調用這個技能。
documentation3
implement-specs-with-worktree
當你需要在獨立分支和工作樹之中實作spec時，使用這個技能。
tools3
implement-specs-with-subagents
當有多份規格文檔需要被實作時，且環境允許使用subagents，建議使用本技能調度subagents完成任務
data-ai3
merge-conflict-resolver
Resolve git merge conflicts using deterministic rules that preserve correct functionality. Use when branch consolidation encounters merge conflicts and needs automated resolution guidance that reads both parent versions and applies scenario-specific strategies.
testing3
jupiter-development
Build integrations against Jupiter's official Solana APIs and SDKs, including Ultra Swap, Metis Swap, Tokens API V2, Price API V3, Lend, Trigger, Recurring, and Portfolio. Use when implementing Jupiter-based swaps, token search, pricing, lending, DCA, limit-order, or portfolio features, or when updating code that depends on Jupiter official developer docs.
development3
test-case-strategy
基於風險分析設計測試策略，選擇最適合當前脈絡的測試層級與方法。不用於不需測試的探索性任務，不用於已有明確定義的單一測試類型任務。
testing3
implement-with-subagents
當有多份規格文檔需並行實作時，調度 subagents 按依賴關係分批完成各份 spec，並將變更合併回當前分支。不用於單一 spec 的實作（請使用 implement），不用於無 coordination.md 的 batch spec。
data-ai3
maintain-project-constraints
基於 repo 最新程式碼與文檔，更新 CLAUDE.md 和 AGENTS.md 這兩份項目規範文件。注意兩者服務不同的 coding agent：CLAUDE.md 給 Claude Code，AGENTS.md 給 Codex 等非 Claude agent。
development3
submission-readiness-check
Prepare a repository for safe submission by synchronizing `CHANGELOG.md`, project docs, `AGENTS.md/CLAUDE.md`, and completed planning artifacts before commit, push, PR creation, or release. Use when a workflow is about to submit changes and must avoid missing finalization steps such as stale `Unreleased` notes, unarchived completed spec sets, or unsynchronized agent constraints.
testing3
iterative-code-performance
Improve an existing codebase through repeated evidence-based repository-wide performance scans, module-by-module deep-read coverage, and behavior-safe speed optimizations until no known in-scope actionable bottleneck or unvisited in-scope module remains: measure hot paths, reduce algorithmic complexity, remove avoidable repeated work, optimize IO and batching, control allocation churn, improve caching only where invalidation is clear, and add benchmark or regression guardrails while preserving intended business behavior and the system's macro architecture. Use when users ask for comprehensive speed, latency, throughput, CPU, memory-allocation, query, batching, or hot-path optimization across a repository.
development3
iterative-code-quality
Improve an existing codebase through repeated evidence-based repository-wide scans, module-by-module deep-read coverage, and behavior-safe refactors until no known in-scope actionable quality issue or unvisited in-scope module remains: clarify poor names, simplify or extract reusable functions, split mixed-responsibility code, repair stale or missing logs, and add high-value tests where guardrails are missing, while preserving intended business behavior and the system's macro architecture. Use when users ask for comprehensive refactoring, code cleanup, maintainability hardening, naming cleanup, log alignment, or test coverage improvement across a repository.
development3
answering-questions-with-research
This skill should be used when the user asks a question that needs complete, evidence-based answers by combining repository discovery with web research.
development3
deep-research-topics
Research specific topics deeply and turn them into evidence-based deliverables. Use when users need a structured research report, briefing, background memo, literature scan, or decision-support document grounded in authoritative sources. Default to PDF output, but switch to DOCX or PPTX when the user explicitly asks for those formats.
development3
align-project-documents
整理及維護項目文檔。當你需要管理項目說明文檔時，使用此技能。
documentation3
learn-skill-from-conversations
Learn and evolve the local skill library from recent Codex conversation logs. Use when users ask to learn from past chats, mine ~/.codex/sessions or ~/.codex/archived_sessions, or automatically create/update skills from recurring lessons. The workflow reads all sessions from the last 24 hours, exits immediately if none exist, cleans up stale session files after reading, and applies skill changes through skill-creator with a default bias toward creating new skills.
development3
docs-to-voice
Convert text and document content into audio files and sentence-level subtitle timelines under project_dir/audio/{project_name}/. Supports both macOS say and Alibaba Cloud Model Studio API modes.
development3
generate-spec
當你需要將用戶模糊的複雜需求拆解成有嚴格實作範圍的spec時，使用這個技能
tools3
katex
Render and embed math formulas with KaTeX using official documentation-backed patterns. Use when an agent needs inline or display math in HTML, Markdown, MDX, or other text-based outputs, or when it should generate insertion-ready KaTeX snippets from TeX.
development3
optimise-skill
當你需要優化 agent skills 的 `SKILL.md` 時，調用這個技能。
data-ai3
spec-to-project-html
Sync the project HTML architecture atlas to active planning specs by driving `apltk architecture --spec <spec_dir>`. The CLI writes overlay YAML under `<spec_dir>/architecture_diff/atlas/` and re-renders only the affected proposed-after HTML pages — macro SVG and per-sub-module internal-dataflow diagrams stay zoomable like the base atlas — so `apltk architecture diff` pairs before/after by path under `docs/plans/**/architecture_diff/`. Preserve the two-layer rule and the responsibility split: **subagents only** — each subagent reads ONE affected feature and declares EVERY intra-feature overlay change; the main agent **waits until all subagents finish**, then aggregates outbound summaries and declares **only** cross-feature edges. **Exact CLI spelling:** always `apltk architecture --help`. Ground every declaration in repo evidence; mark `TBD` when code is missing.
tools3
review-spec-related-changes
當你需要審查規格文檔相關變更時，調用此技能
tools3
read-github-issue
Read and search remote GitHub issues via GitHub CLI (`gh`). Use when users ask to list issues, filter issue candidates, inspect a specific issue with comments, or gather issue context before planning follow-up work. Prefer the bundled CLI tools when they are present and working, but fall back to direct `gh issue list` / `gh issue view` commands when the tools are missing or fail for repository-specific reasons.
tools3
solve-issues-found-during-review
當你需要修復 code review report 之中發現的問題時，調用這個技能。
development3
cjk-pdf
Handle CJK PDF font selection, rendering requirements, and visual QA for Chinese-compatible PDF output. Use when any skill needs to render PDFs with Chinese or mixed CJK text, verify font paths, apply content safety rules, and perform screenshot-based visual QA.
testing3
review-change-set
Unbiased **git diff** review: architecture (boundaries, duplication, ownership) then simplification (real deletes/flattening, not churn)—discard conversation bias. For diffs spanning multiple files/modules, **prefer dispatching one read-only subagent per scope cluster** (each owns its files end-to-end), then aggregate confirmed findings on the main agent without re-reading delegated files. Use for pre-commit/pre-PR review, refactor/abstraction second opinion, “review my branch” **STOP** greenfield feature design from scratch—use planning skills… BAD style-only nits… GOOD evidence + named abstraction target…
development3
text-to-short-video
Generate 30-60 second short videos by directly calling an OpenAI-compatible video generation API from text. Keep role consistency by using roles.json as role prompt source and only updating role descriptions.
development3
openai-text-to-image-storyboard
Generate storyboard images by using agent-decided prompts and calling an OpenAI-compatible image generation API. Use when users want chapters, novels, articles, or scripts converted into image sets under pictures/{content_name}, with API URL and API key loaded from this skill folder's .env by default.
development3
learning-error-book
A learning-focused error-book workflow. When the user asks to summarize mistakes, the agent summarizes mistakes made while solving questions, writes structured reference data, and renders polished PDFs directly without Markdown as an intermediate.
documentation3
analyse-app-logs
Comprehensive application log investigation workflow that reads logs end-to-end, correlates signals with code paths and runtime context, and identifies evidence-backed issues with impact and remediation steps. Use when users ask to analyze logs, investigate incidents, find root causes from log records, explain recurring warnings/errors, or check whether logs reveal hidden system problems.
development3
weekly-financial-event-report
Read a user-specified PDF that marks the week's key financial events, deeply research each marked event with current sources, capture any additional breaking financial developments, and produce a concise Chinese-capable PDF briefing that explains what happened and why it matters.
development3
weekly-financial-event-report
Read a user-specified PDF that marks the week's key financial events, deeply research each marked event with current sources, capture any additional breaking financial developments, and produce a concise Chinese-capable PDF briefing that explains what happened and why it matters.
development3
review
Reviews spec-related code changes across six dimensions and produces a structured review report (REPORT.md) with findings only — no fix suggestions. Not for non-spec changes, direct code modification, or contexts without a spec.
development3
video-production
Generate long-form videos (more than 10 minutes) by following user instructions and invoking related skills only when needed (`openai-text-to-image-storyboard`, `docs-to-voice`, `remotion-best-practices`). For text inputs, extract a complete long-form story arc, generate fresh storyboard images (no reuse of previously generated pictures), and render a 16:9 animated long-form video.
documentation3
discuss
Helps users clarify vague requirements through structured conversation, producing a high-level design (PROPOSAL.md) with functional module decomposition. Does not read any repo files — relies entirely on conversation. Suitable for requirement discussions, feature ideation, or greenfield project planning.
testing3
fix
Loads the FIX.md produced by the qa skill and executes it as the fix coordinator. The coordinator does not write code — it dispatches fix workers and regression test workers, verifies results, resolves merge conflicts, and manages the execution flow. All execution logic is defined in FIX.md.
development3
plan
Converts SPEC.md + DESIGN.md + CHECKLIST.md into a self-contained coordinator prompt (PROMPT.md) with complete task decomposition, dependency analysis, batch scheduling, and pre-written worker prompts. The generated PROMPT.md is consumed directly by the implement skill.
testing3
init-project-html
為項目初始化架構圖。透過 apltk CLI 將功能模塊與子模塊的關係轉化為可渲染的 HTML 架構圖，採用 C4 模型層級（Context → Container → Component → Code）。
tools3
archive
將已完成的spec歸檔到 `docs/archive/` 下。當你需要將spec歸檔時，調用這個技能。
documentation3
update-project-html
當項目架構圖與實際程式碼脫節時，增量刷新架構圖資源。包括基礎 atlas 與渲染 HTML。更新前先測量 drift 程度決定更新範圍。
development3
shadow-api-model-research
Investigate gated or shadow LLM APIs by capturing real client request shapes, separating request-shape gating from auth/entitlement checks, replaying verified traffic patterns, and attributing the likely underlying model with black-box fingerprinting. Use when users ask how Codex/OpenClaw/custom-provider traffic works, want a capture proxy or replay harness, need LLMMAP-style model comparison, or want a research report on which model a restricted endpoint likely wraps.
tools3
exam-pdf-workflow
Create, typeset, and grade exam-style PDF deliverables for study workflows. Use when the user asks to read lecture or exam PDFs, generate mock exams, produce matching solution books, render math-heavy content with KaTeX, or grade completed answer-book PDFs into a scored graded PDF.
content-media3
resolve-review-comments
Read GitHub pull request review comments, analyze each thread, decide whether to adopt feedback, implement adopted changes, push updates to the same PR branch, and resolve addressed review threads. Use when users ask to process PR review feedback by PR number or current branch context.
testing3
implement-with-worktree
在獨立分支及工作樹中實作 spec。按 tasks.md 逐項實作，按 checklist.md 逐項驗收。完成後提交到子分支，保持主分支乾淨。
testing3
docs-project
以 repo 程式碼為唯一依據，維護標準化的 docs/features/、docs/architecture/、docs/principles/ 文檔， 並清理已失效或重複的舊文檔。每條文檔記述必須可追溯至實際程式碼證據。
testing3
ship-github-issue-fix
Resolve a GitHub issue in an existing repository and submit the fix directly to the requested branch without opening a PR or doing release work. Use when users ask to read issue N, implement the fix, decide whether planning artifacts are needed, run the relevant tests, and commit/push the result to `main` or another specified branch.
testing3
merge-changes-from-local-branches
將 spec 相關的本地實作分支合併回當前分支。按 coordination.md 的建議順序解決衝突。
tools3
open-github-issue
Publish structured GitHub issues across multiple issue categories with deterministic auth fallback, target-repo resolution, README-based language detection, and draft-only fallback when authentication is unavailable. Use when users ask to open GitHub issues from confirmed findings, accepted proposals, documentation gaps, security risks, observability gaps, or prepared issue content.
development3
qa
審查規格文檔相關的程式碼變更。從六個維度產出 code review report：幻覺代碼、冗餘、偏移、遺漏、架構、性能。不用於非 spec 相關的變更審查，不用於直接修改代碼，不用於沒有 spec 的情境。
development3