GitHub
compound-docs
Capture solved problems as searchable documentation with pattern detection. This skill auto-triggers when users confirm a fix worked ("that worked", "it's fixed", "working now") or manually via /compound comman...
Skills IA tools llm ai
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools llm ai
tools llm ai Effacer les filtres
Explorer
GitHub
code-review
Automated PR code review with multi-agent analysis
GitHub
sage-agent-execution
Sage Agent 执行引擎开发指南，涵盖 UnifiedExecutor、Subagent、Lifecycle 管理
GitHub
sage-prompt-engineering
Sage Prompt 工程规范，学习 Crush 的模板化方案，包含 system prompt 设计最佳实践
GitHub
sage-learning-system
Sage 独有的学习系统设计，包含模式识别、用户偏好学习、纠正反馈机制
GitHub
sage-llm-integration
Sage LLM 客户端集成开发指南，涵盖多 Provider 支持、Fallback、Rate Limiting、Streaming
GitHub
sage-context-management
Sage 上下文管理开发指南，涵盖 Token 估算、消息裁剪、自动压缩、摘要生成
GitHub
sage-skill-development
Sage Skill 开发规范，遵循 Agent Skills 开放标准，兼容 Claude Code 格式
GitHub
agents-md-generator
Analyze repository structure and generate standardized AGENTS.md files that serve as contributor guides for AI agents. Measures LOC to determine character limits and produces 5-section documents covering overvi...
GitHub
skill-maker
Create new AI agent skills following the SKILL.md guidelines. Generates complete skill structure including SKILL.md with YAML frontmatter, optional bundled resources (scripts/, references/, assets/), and update...
GitHub
ai-sdk-ui
This skill should be used when the user asks to "add AI chat", "implement streaming UI", "use useChat hook", "add AI completion", "implement useCompletion", "create conversational interface", "add streaming tex...
GitHub
code-recall
Use semantic memory from code-recall MCP to remember decisions, patterns, and learnings across sessions. Call get_briefing at session start, check_rules before major changes, and store_observation after importa...
GitHub
authoring-stitch-prompts
Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Follows Stitch best practices with s...
GitHub
code-explanation
Explains complex code through clear narratives, visual diagrams, and step-by-step breakdowns. Use when user asks to explain code, understand algorithms, analyze design patterns, wants code walkthroughs, or ment...
GitHub
skill-name
What this skill does. Use when user mentions "keyword1", "keyword2", or "keyword3". Keep under 1,024 characters and include specific trigger keywords.
GitHub
deep-research
Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic, investigate best practices, look up information, find patterns, or explore architectu...
GitHub
domain-driven-design
Expert guidance for Domain-Driven Design architecture and implementation. Use when designing complex business systems, defining bounded contexts, structuring domain models, choosing between modular monolith vs...
GitHub
write-docs
Write AI-scannable technical documentation.
GitHub
upskill
Meta-skill that learns new capabilities from NPM and pip package registries. Use when user asks to integrate with a service (e.g., "I need to use Asana"), mentions an API we don't have a skill for, or explicitl...
GitHub
design-api
API設計エージェント - リファクタリング後のマイクロサービスAPI設計。REST/GraphQL/gRPC/AsyncAPIの仕様書、API Gateway設計、認証・認可設計を策定。/design-api [対象パス] で呼び出し。
GitHub
query-graph
GraphDB探索エージェント - RyuGraphデータベースを自然言語またはCypherで探索し、関連するコードや仕様書を返却。/query-graph [クエリ] で呼び出し。
GitHub
lifesciences-graph-builder
Orchestrates life sciences APIs to build knowledge graphs using the Fuzzy-to-Fact protocol, combining MCPs for nodes and curl for edges, then persisting to Graphiti. This skill should be used when the user asks...
GitHub
auto-trigger
Workflow automation hooks for agent-playbook skills. This skill defines automatic triggers between skills - DO NOT use directly, it's a configuration skill that other skills reference.
GitHub
self-improving-agent
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/err...
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.