agent-skill-best-practices
Provides best practices for writing Agent Skills. Use when creating or refining SKILL.md content.
Découvrez les skills testing security knowledge base, comparez leurs dépôts et consultez leurs instructions.
Provides best practices for writing Agent Skills. Use when creating or refining SKILL.md content.
Verifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to find candidates, then uses LLM (scillm) to verify "verifies", "contradicts", or...
This sop analyzes a codebase and generates comprehensive documentation including structured metadata files that describe the system architecture, components, interfaces, and workflows. It can create targeted do...
Distill PDF, URL, or text into Q&A pairs stored in memory. Use --context for domain-focused extraction.
Create and refine Claude Code Skills. Use when creating skills, writing SKILL.md files, or improving existing skills.
/docs/diary/に日記を書く。
Integration guide for using detective skills across plugins. Maps agent roles from frontend, bun, and other plugins to appropriate detective skills. Developer agents should use developer-detective, architect ag...
Use before creating or editing any SKILL.md files, and immediately after making skill changes to verify quality. Invoked when user asks about skill structure, descriptions, or best practices. Provides expert gu...
Meta-skill that creates other skills from detected patterns. Use when user repeatedly explains workflow (2+ times), says 'remember this', or you notice repetitive pattern.
Drafts individual chapters for books and long articles. Use when user says 'draft chapter X', 'write chapter [number/title]', 'continue drafting', or 'write the next chapter'. Reads outline and maintains consis...
Validates that book chapters align with the core theme. Use when user says 'check theme alignment', 'does this fit the theme', 'verify alignment', or automatically after every 2 chapters are drafted.
Creates outlines for non-fiction books and long articles. Use when user says 'create an outline', 'plan a book', 'structure a book about [topic]', or 'I want to write about [topic]'. Handles leadership, career,...
Performs web-based research on any topic
Branch skill for building and improving categories. Use when creating new categories, validating category structure, improving existing categories, or migrating categories to new standard. Triggers: 'create cat...
iterate on structure outline based on user feedback. if given a path to a document in rpi/tasks/*/*-structure-outline.md, use this skill.
Use when user mentions issue, bug, task, ticket, feature, backlog, tracking, or work items. Suggests using Trekker for tracking.
Search past AI agent sessions, stored knowledge, and indexed content. Use for finding previous work, recalling conventions, storing learnings, and indexing documentation.
Branch skill for building and improving skills. Use when creating new skills, adapting marketplace skills, validating skill structure, writing progressive disclosure, or improving existing skills. Triggers: 'cr...
Guide users through structured dialogue to transform vague ideas into clear, actionable product concepts. Uses one-question-at-a-time approach with multiple choice options. Use this skill when: - User says "I...
Draft or revise technical blog content in this repo (Quarto .qmd), check for math/syntax/spelling/equation errors, improve readability, and generate LinkedIn knowledge-card plus single-tweet Twitter posts for n...
Engineering Manager skill for team leadership, 1-on-1s, performance reviews, hiring, career development, and technical team management. Use when managing engineering teams, conducting performance reviews, or pl...
generate research questions based on a task, spec, or ticket
Query up-to-date library documentation and code examples using Context7. Provides 2 tools for resolving library IDs and querying documentation.
Resolve requirement ambiguities through STRUCTURED questioning: one question at a time, with recommended options and reasoning. UNIQUE VALUE: Prevents overwhelming users with multiple questions. Provides exper...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.