6.3K skills · sorted by relevance
Search HMDB for metabolites, proteins, diseases, or pathways and receive concise Markdown summaries. Keep searches focused on one category, with an option to save the full response when more detail is needed.
Search a collection of notes using exact keywords, meaning, or both. Find past decisions, meeting records, and information about people, then retrieve relevant passages or check new notes for duplicates and related material.
Clean up hard-wrapped Markdown and .qmd files by joining mid-sentence line breaks and placing each sentence on its own line. Preserve headings, code blocks, lists, quotes, and YAML metadata while adjusting paragraph whitespace.
Optimize oversized agent instruction files using progressive disclosure. Handles CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex / GitHub Copilot agents), and copilot-instructions.md (GitHub Copilot). Auto-detects all three formats in your repo, analyzes content tiers, creates sub-documents using each format's native mechanism, and rewrites the main file with zero information loss. Triggers: optimize CLAUDE.md, AGENTS.md too long, reduce copilot-instructions.md, agent instructions file too large, shrink context file, apply progressive disclosure, instructions file bloated
The English summary is being prepared. Showing the original description.
開発作業ドキュメントを自動生成します。YYYYMMDD_要件名の形式でディレクトリを作成し、requirements.md、design.md、tasklist.md、testing.mdを生成します。「開発作業ドキュメント作成」「開発ドキュメント作って」「ドキュメント生成」などで呼び出されます。
The English summary is being prepared. Showing the original description.
新規機能開発の作業ドキュメントを自動生成します。YYYYMMDD_要件名の形式でディレクトリを作成し、requirements.md、design.md、tasklist.md、testing.mdを生成します。「開発作業ドキュメント作成」「新規開発のドキュメント作って」「ドキュメント生成」などで呼び出されます。パフォーマンス改善作業には generate-performance-docs を使用してください。
The English summary is being prepared. Showing the original description.
パフォーマンス改善作業の開発ドキュメントを自動生成します。YYYYMMDD_要件名の形式でディレクトリを作成し、requirements.md、design.md、tasklist.md、testing.mdを生成します。「パフォーマンス改善のドキュメント作って」「最適化作業のドキュメント」「高速化のドキュメント生成」などで呼び出されます。
The English summary is being prepared. Showing the original description.
開発作業ドキュメントを自動生成します。YYYYMMDD_要件名の形式でディレクトリを作成し、requirements.md、design.md、tasklist.md、testing.mdを生成します。「開発作業ドキュメント作成」「新規開発のドキュメント作って」「ドキュメント生成」などで呼び出されます。
The English summary is being prepared. Showing the original description.
Turn a Caveman token-usage report into specific edits to instruction files, repeated context, and memory. Review each proposed change before approval, then measure the result and distinguish confirmed file reductions from less certain session-level effects.
Build a single-page SaaS product landing page with features, testimonials or logos, optional pricing, and clear action buttons. Follow the colors, fonts, and layout rules in DESIGN.md, and deliver one self-contained HTML file.
Create a structured HANDOFF.md briefing so a fresh Claude session can resume ongoing work. Capture the goal, current state, relevant files, failed approaches and their causes, constraints, and concrete next steps.
Audit a Claude Code setup for installation problems, broken settings, unused extensions, and duplicated instructions. It reviews local usage evidence, recommends cleanup, and applies approved fixes, with separate confirmation for permission changes.
Analyze a codebase to create project-specific AGENTS.md instructions and supporting rule files. Detect the package manager and relevant conventions, preview proposed changes, or update existing guidance when the project’s tools change.
Generate coding agent instruction files from a project's actual code using AgentRC. Capture detected languages, frameworks, and conventions in one shared file or split rules by topic and project area, with a preview before writing.
Turn repeated workflows into reusable Picoclaw skills, or update and review existing ones. Organize SKILL.md instructions, scripts, reference documents, and output assets, then check the structure and test representative tasks.
Prepare medical device regulatory strategies and submission documents for FDA, EU, and other markets. Compare application routes, organize technical and clinical evidence, draft responses to regulator questions, and track submission schedules.
Turn recurring lessons in Claude's automatic memory into concise project rules. Choose a project-wide, file-specific, or personal rule location, include concrete commands, and clean up the original memory entry after confirmation.
Create a Wren MDL project, a model layer for database queries, from an existing database. Discover tables and relationships, normalize column types, generate YAML files, and validate and build the project before indexing its schema.
Learn how to organize an AI agent skill using a sample SKILL.md file. It covers basic metadata, procedural instructions, supporting folders, and relative paths, and serves as an example for testing the OpenSkills loader.
Audit a completed AI development phase to check whether its planned evaluations were implemented. Produce EVAL-REVIEW.md with a score, verdict, identified gaps, and a plan to address missing coverage.
Review recent conversation history against global and project CLAUDE.md files, which hold agent instructions. Identify rules that were missed, useful additions, and outdated guidance, then organize findings into shared and project-specific improvements.
Search watched registries, collections of community legal skills, by name and description. Compare matching entries, preview the full SKILL.md before choosing what to install, and add new registries to the watchlist after confirmation.
Compare code changes since the latest Git tag with English, Chinese, and Japanese documentation. Update affected guides and CLAUDE.md, check links and contents pages, or report inconsistencies without changing files.
Proofread English academic prose in Quarto .qmd documents for grammar, typos, punctuation, and clarity. Receive a separate Markdown report organized by section, with suggested revisions and reasons, while keeping the source file unchanged.