GitHub
plan-and-solve-agent
Breaks down complex queries into a step-by-step plan before execution, improving performance on multi-hop reasoning tasks.
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
regulatory-drafter
Drafts regulatory documents (FDA, EMA) with audit trails and specific "Thinking Block" reasoning. Use for high-stakes compliance writing.
GitHub
opentrons-protocol-agent
Generates executable Python protocols for Opentrons OT-2 and Flex robots from natural language descriptions.
GitHub
multimodal-medical-imaging
Analyzes medical images (X-ray, MRI, CT) using multimodal LLMs to identify anomalies and generate reports.
GitHub
scienceworld-act
Take a ScienceWorld action in the active session. Returns observation, reward, done. No session_id needed - uses active session from executive_node.
GitHub
generate-note
Generate new text or code content from scratch using natural language prompt via LLM. Use to collect thoughts or generate a coherent statement on a topic
GitHub
mc-say
Send chat message in Minecraft - social/debugging/alignment. Returns acknowledgement only
GitHub
assess
Boolean test of text content against a natural language predicate. Features auto-chunking for long texts (returns "true" if ANY chunk matches).
GitHub
refine
Extract or transform information from unstructured or semi-structured text using an LLM. Edits existing content only; does not add new information.
GitHub
mc-stop
Stop all movement - cancel embodied motion. Critical for safety, interrupts, reflection pauses
GitHub
is-question
Check if text contains a question
GitHub
improve-skill
Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.
GitHub
claude-code-guide
Answer questions about Claude Code CLI, Claude Agent SDK, and Claude API. Use when asked about: - Claude Code features (hooks, skills, MCP servers, settings, IDE integrations, keyboard shortcuts) - Building cus...
GitHub
document
Capture solved problems as searchable documentation for future reference. Use when a problem is solved, after saying "that worked", "it's fixed", or when you want to document a solution so it can inform future...
GitHub
ideate
Turn ideas into validated designs through collaborative dialogue with built-in expert review. Use when asked to "design a feature", "plan an approach", "think through implementation", or when starting new work...
GitHub
review
Run expert review on a plan with parallel reviewer agents. Presents findings as Socratic questions. Use when asked to "review the plan", "get feedback on the design", "check this approach", or before implementa...
GitHub
workflow-to-skill
将用户的手工SOP/工作流抽取为可复用的Agent Skill规格与SKILL.md草案。适用于“把这个流程封装成skill/把步骤做成skill/从手工步骤生成SOP+分支+质量门禁+技能文件/元prompt做成skill”等请求。Use when the user describes a m...
GitHub
03-mofa-studio-dataflow
Dora dataflow authoring and wiring for MoFA Studio dynamic nodes. Use when editing voice-chat.yml, adding dynamic nodes, or debugging dataflow connections and signals.
GitHub
imagegen
Generates and edits images via Gemini API. Use when creating new images or modifying existing ones.
GitHub
rule-creator
Creates and manages Claude Code rules files. Use when creating .claude/rules/ files or applying conditional rules to specific files/situations.
GitHub
skill-creator
Creates and manages Claude Code skills. Use when creating new skills, updating existing skills, or converting repeated prompts into reusable skill packages.
GitHub
claude-agent-sdk
Python으로 Claude Agent SDK 에이전트를 구축할 때 사용. 커스텀 도구, 훅, 서브에이전트, MCP 연동 코드를 생성합니다.
GitHub
claude-guide
Guides Claude Code setup and configuration. Use when setting up CLAUDE.md, rules, hooks, or skills structure for projects.
GitHub
agent-creator
Creates and manages custom Claude Code sub-agents. Use when automating workflows as dedicated agents, delegating recurring tasks, or modifying .claude/agents/ files.
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.