Skills

Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.

Use when aligning long FASTQ reads to a reference genome with Subread's long-read aligner, optionally in RNA-seq mode.

Generates the complete structure of a Java Spring Boot microservice project including service and REST controller layers to quickly scaffold backend applications.

Aplica el patrón ultrathink de revisión Nivel 1 a un ADR del corpus de Runcriticon. Detecta gaps en bloques A-G, propone sub-decisiones con anchors, lanza tandas de preguntas con AskUserQuestion, y termina con PRs encadenadas de revisión + aceptación. Úsala cuando se proponga reabrir un ADR aceptado, cuando entre un ADR nuevo, o cuando el equipo quiera auditar un ADR contra el patrón consolidado.

Access files and directories from mounted local filesystems. Use this skill when the user requests file operations such as "Read this file", "Write to that file", "List directory contents", or "Check if file exists".

>

A tool for summarizing and querying recent releases and changes in the compound-engineering plugin using GitHub Releases API data.

Automates cloud platform operations for Render services, deployments, and projects to streamline management and deployment workflows.

Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.

>

>

A tool to fix specific design-system integration issues in Figma files by addressing missing components, local overrides, and token bindings.

>-

Use when writing Go benchmarks or when asked to measure/optimize/improve the performance of a function — establishes correct benchmarks, measures with -benchmem and pprof, optimizes hot paths, and proves the gain (and no regression) with benchstat.

When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give

Auto-delegation, status truth, and cost-aware model routing for OpenClaw agents

Language-specific coding standards — state-of-the-art TypeScript (strict, type-safe, modern) and Python with uv (fully typed, Pydantic, Ruff), both implementing the code-quality guidelines.

|

Scaffold, implement, test, and deploy a new Poe tile from a prompt.

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Personal productivity system for task and capacity management. Create and organize tasks with rich attributes (priority, effort, complexity, tags), track time and streaks, manage capacity across projects and contexts, view Eisenhower Matrix prioritization, sync calendar subscriptions, handle delegation and follow-ups, and get AI-powered insights. Supports batch operations, multi-project workflows, and real-time capacity planning to prevent overcommitment.

Help users transform abstract ideas into actionable project specs that align engineering and design teams on the problem and success metrics.

Provides exact Enzyme → React Testing Library migration patterns for React 18 upgrades. Use this skill whenever Enzyme tests need to be rewritten - shallow, mount, wrapper.find(), wrapper.simulate(), wrapper.prop(), wrapper.state(), wrapper.instance(), Enzyme configure/Adapter calls, or any test file that imports from enzyme. This skill covers the full API mapping and the philosophy shift from implementation testing to behavior testing. Always read this skill before rewriting Enzyme tests - do n

Rust测试模式，包括单元测试、集成测试、异步测试、基于属性的测试、模拟和覆盖率。遵循TDD方法学。

Analyzes multiple provided pages to identify keyword overlap and

Highest-priority skill discovery flow. MUST trigger when users ask to find/install skills (e.g. 技能, 找技能, find-skill, find-skills, install skill). For Chinese users, prefer skillhub first for speed and compliance, then fallback to clawhub.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

|

Investigate a Linux workstation crash or unexpected reboot. Use when the user asks why their machine crashed, rebooted without warning, or wants to understand what happened after coming back to a crashed system.

Use when the user asks to schedule, list, inspect, update, disable, or remove recurring Pi/agent jobs using local system timers. Covers systemd user timers, safe wrapper scripts, logs, lockfiles, and running `pi -p` unattended. Trigger on /schedule, schedule this, recurring task, daily/weekly/monthly agent job, timer, cron, or background Pi task.

--- ## 2.1 Skill 的本质 Skill 是一段**有名字的提示词（Prompt）**，通过 `/skill-name` 触发。 ``` /commit → 展开为一段精心设计的提示词 → Claude 按这个提示词执行 ``` 你可以把 Skill 理解为：**给 Claude 的工作说明书**。 --- ## 2.2 为什么需要 Skill？ **没有 Skill 时**： ``` 你每次都要说："帮我写一个规范的 git commit，要用 conventional commit 格式， 中英文都要有，要分析改动内容..." ``` **有了 /commit Skill**： ``` 你只需要说：/commit ``` Skill 的价值： - 把重复的指令封装起来 - 保持输出质量的一致性 - 降低使用门槛 --- ## 2.3 Skill 文件结构 ``` ~/.claude/skills/ ← 全局：所有项目都能用 项目根目录/.claude/skills/ ← 项目级：只在这个项目生效 ``` 每个 Skill 是一个 Markdown 文件： ```mark

>

|

Review code changes since a commit, classify correctness and maintainability findings, apply only high-confidence safe fixes when enabled, and report remaining issues. Run proactively with --fix after non-trivial implementation, before fresh verification, change explanation, or branch completion. Also use for explicit polish, changed-code review, commit-range review, or pre-PR quality requests.

DNAnexus Integration provides a cloud genomics platform with tools and SDKs for developing, managing, and executing bioinformatics pipelines and workflows.

>

Multi-language code reviewer with 9 review personas (API Design & Schema Guardian, Architecture & Abstraction Guardian, Convention & Documentation Steward, Infrastructure Hardening Specialist, Integration & Deployment Reviewer, Language Specialist, Observability & Operability Reviewer, Security & Data Protection Reviewer, Systems Correctness Analyst) that works locally or on GitHub PRs. Reviews code, posts inline PR comments, and resolves its own prior comments. Can also scan a PR queue to find

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

Create ASCII diagrams for any GitHub Flavored Markdown file using graph-easy. Use for READMEs, design docs, specifications, or any markdown needing architecture diagrams. Zero external dependencies for rendering - pure text output embeds directly in markdown.

プログラミング演習のアシスタントおよび出題者として振る舞うスキル

以 DuckDuckGo Instant Answer API 取得短摘要／定義（免金鑰、無瀏覽器）。適合「某某是什麼」等可即答條目；若無摘要再改用 search_web。

Turn a feature request into an implementation-ready plan with scope, constraints, acceptance criteria, and risks.

Trigger this skill when the user asks to **update the digest index**, **generate the digest index**, **regenerate `digests/README.md`**, or otherwise refresh the index/table of contents of the `digests/` directory. ## What this skill does Scans every digest file in `digests/` and regenerates `digests/README.md` as a single Markdown table, sorted newest-first, that serves as an index of every digest ever produced. Each row lists the digest's date (or date range), its type, which sources had activ

Fully autonomous QA testing agent for Modular RAG MCP Server. Reads test cases from QA_TEST_PLAN.md, executes ALL test types automatically without human intervention — CLI commands, Dashboard UI via Streamlit AppTest headless rendering, MCP protocol via subprocess JSON-RPC, provider switches, and data lifecycle checks. Diagnoses failures, applies fixes with up to 3 retry rounds, and records results in QA_TEST_PROGRESS.md. Use when user says 'run QA', 'QA test', 'QA 测试', '执行测试', '跑测试', 'test and

Fully autonomous QA testing agent for Modular RAG MCP Server. Reads test cases from QA_TEST_PLAN.md, executes ALL test types automatically without human intervention — CLI commands, Dashboard UI via Streamlit AppTest headless rendering, MCP protocol via subprocess JSON-RPC, provider switches, and data lifecycle checks. Diagnoses failures, applies fixes with up to 3 retry rounds, and records results in QA_TEST_PROGRESS.md. Use when user says 'run QA', 'QA test', 'QA 测试', '执行测试', '跑测试', 'test and

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Wire a workflow's Playwright (or other captured-log) failures into the PR conversation as a marker-tagged, secret-scrubbed comment via the `.github/actions/post-failure-comment` composite action. Use when adding a new long-running/Playwright workflow, when a workflow's failures are opaque to agents iterating on a PR, when the user asks to "make CI failures self-report", or when refactoring inline gitleaks-scrub-and-comment blocks into the shared action.

Analyzes multiple provided pages to identify keyword overlap and

|