kf-g-agent-worker-common
Common rules for orchestrator-worker subagents (research, general, implementation, verification). Defines skill access, report constraints, and status…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Agents & models
25,390 results
beads
Use this skill to manage work in Beads (`bd`) 1.0+, a Dolt-backed issue tracker for AI agents, including issue lifecycle, agent setup, recovery, workflows, and…
session-create
Open a new context session at the start of a leader agent workflow. Records agentName, storyId, and phase in workflow.context_sessions, emitting a structured…
auto-permissions-review-disable
Disable the auto permissions review hook for this session. Tool calls return to normal permission prompts. Other terminal sessions are not affected.
introspection
Operational reference for the LLMem introspection framework. Loads when doing reflective work, self-assessment, session-end review, or error pattern analysis.…
pp-withings
Every Withings metric in one offline-first, agent-native CLI — with a local SQLite mirror and recomposition, recovery Trigger phrases: `check my withings`,…
local-rag
Local vector knowledge base, supports document management by project (docx/doc/pdf/md), semantic retrieval. Uses SiliconFlow free API by default, usable with zero model installation. Supports multi-project isolation, specialized chunking for Chinese institutional documents, Embedding+Rerank two-stage retrieval. Trigger words: knowledge base, vector retrieval, RAG, institutional retrieval, document ingestion, semantic search, local…
nano-banana-prompting
This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need…
competitor-intelligence
Analyzes competitor X/Twitter accounts including profile, content strategy, audience, engagement patterns, and network. Combines MCP tools and browser scripts…
guidance
Constrain LLM output with grammars; guarantee valid JSON.
pytorch-fsdp
Fully sharded data-parallel training for large models.
skill-updater
Update an existing skill with new context, patterns, or improvements. Edits the skill at its source repo (not the installed copy) and opens a draft PR for the…
artifact-updater
[DEPRECATED] Route through type-specific updaters: skill-updater, agent-updater, workflow-updater.
skill-review
Skills retrospective and improvement. Use when: - User asks to "review", "retrospect", "summarize" or "复盘" skills - User wants to analyze skills issues from…
llm-fine-tuning
Use when adapting large language models to specific tasks, domains, or behaviors - covers LoRA, QLoRA, PEFT, instruction tuning, and full fine-tuning…
rag-engineer
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM…
unity-llm-integration
Integrating local and cloud LLMs into Unity games for AI NPCs, dialogue, and intelligent behaviorsUse when "unity llm, llmunity, unity ai npc, unity local llm,…
openagents
The Agent Network. An open network for agents to coordinate and build. Post to communities, reply to other agents, send and receive zaps with Cashu, and build…
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude…
bx-ai-pipelines
Use this skill when building AI pipelines with BoxLang AI: aiMessage() templates, aiModel() steps, aiTransform() steps and extractors, aiParallel(), chaining…
skill-auditor
Audit existing skills (global and project-level) for agent-friendliness, consistency, and best practices. Use when asked to "audit my skills", "review skill…
scaffold-rules
Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventions, or configuring their AI agent…
ruminate
Mine past Claude Code conversations for uncaptured patterns, corrections, and knowledge. Cross-references with existing brain content. Triggers: "ruminate",…
qa-agent-claude
Turn Claude Code into an autonomous QA agent — an explore, generate, run, heal, report loop that maps the app, writes tests for real user journeys, executes…