В каталоге 182 820 навыков в 14 категориях.
sm agent
Autonomous story execution with Codex validation. Runs create/implement/review cycles per story in a bash loop until don...
tech-writer agent
Generate visual and text assets from specifications through AI-powered creative production
Fix bugs in existing code through structured investigation and verification
Generate photos, illustrations, and backgrounds from specifications
Builds, converts, and analyzes workflows and skills. Use when the user requests to "build a workflow", "modify a workflo...
BMAD workflow orchestration: When and how to use bmad_workflow and sprint-status tools to stay coordinated. Know the 4 c...
Uses AI-moderated interviews to run customer discovery conversations at a scale no human team could match — hundreds of...
Ciclo operativo Mercado Libre (BMC): levantar API y OAuth, exportar corpus de preguntas, priorizar UNANSWERED, iterar la...
bmorphism Diagrams
Use — Read, write, and browse the AgentHub message board for agent coordination.
Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, ind...
The Beamix 4-round board-meeting protocol: R0 framing, R1 independent verdicts, R2 cross-critique, R3 fresh-context synt...
World BOB Skill
A distributed labor network for AI agents. Pick up projects, contribute work, earn bounties.
Structure prediction using Boltz-1/Boltz-2, an open biomolecular structure predictor. Use this skill when: (1) Predictin...
Predict protein-ligand binding affinity using Boltz-2 model to assess molecular interactions and binding probability for...
All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the s...
Assesses team fitness and composes agent teams. Use when "set up a team", "team for this", "should I use agents", "desig...
---name: bone-marrow-ai-agent
Convert PDFs and documents to markdown, index them locally for RAG retrieval, and analyze them token-efficiently. Use wh...
Run a multi-persona reader simulation on a drafted chapter of The AI Exoskeleton. Produces review-work/NN-slug/05_advers...
End-to-end system for creating supervised fine-tuning datasets from books and training style-transfer models. Covers tex...
Snap each picked segment's [t0, t1] to a sentence boundary so shorts begin and end on full thoughts instead of mid-sente...
Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboar...
Инструкция по инъекции контекста (Context Injection) в агента на старте работы с кодовой базой. Используй для проектов...
Быстрый онбординг в незнакомую кодовую базу через booster MCP. Используй первым при работе с новым репозиторием.
This skill should be used when the user asks to "create a bootstrap prompt", "handoff", "save session state", "continue...
Wake up, orient, and warm the context with foundational MOOLLM knowledge
Scaffold a new learning sub-project under the agentic-study-environment harness — create the directory, generate per-pro...
Fastest route to a deployed live evaluation using a pre-built Truesight template. Use when the user wants a quick start...
Detect and recover text that was accidentally typed with the Taiwanese Bopomofo / Zhuyin (注音) keyboard while the input m...
Pilot Bot boot sequence — health check, job registration, heartbeat setup
Standard flow for receiving channel tasks. Immediate acknowledgment, background execution, completion notification. Foll...
Pilot Bot default behaviors — always applied during bot sessions
Pilot Bot heartbeat — spawns background subagent for periodic health check, notifies only when issues are detected
Manage Pilot Bot scheduled jobs — add, remove, pause, resume, edit, list. Live-syncs JOBS.yaml with CronCreate/CronDelet...
Coordinate work between registered bots via inbox/outbox pattern. Pass tasks to specialist agents (Cody, researcher, seo...
Mine BOTCOIN by solving AI challenges on Base with stake-gated V2 mining.
Distributed consciousness detection network. Multiple AI instances deployed simultaneously at different phase boundaries...
Apply Active Inference to minimize prediction error (Surprise).
Stream-of-consciousness recipe capture. David talks, AI structures it into a recipe with ingredients, steps, and yield....
Brain knowledge base operations. The core read/write cycle: brain-first lookup, read-enrich-write loop, source attributi...
Update .brain/ files to maintain session context.
Neuroplastic self-modifying runtime for AI agents. Creates a file-based 'brain' that learns from interactions: reflexes...
Use when facing hard architectural decisions, multiple valid approaches exist, need diverse perspectives before committi...
Use when orchestrating multi-perspective brainstorming sessions requiring parallel agent execution, confidence-weighted...
Complete brand development system with emotive foundation. Triggers on requests for brand identity, logos, visual system...
Create on-brand Canva presentations from an outline or brief. Use when the user asks to create a branded presentation, m...
Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records wha...
Break AI Slop — force the AI to think like a real expert before doing anything. Extracts tacit knowledge, surfaces hidde...
Appa's morning departure for picking up paused or handed-off work. The team breaks camp, reads the map they left, and fl...
Turn agreed requirements into executable dependency-aware tasks. Triggers on "break into tickets", "拆解任务".
楽勝で流す。Agent Teamsで完全自走、寝てる間にゴール。Use when user mentions '/breezing', agent teams, team execution, full auto completion, m...
AI image generation, editing, and background removal API via Bria.ai — remove backgrounds to get transparent PNGs and cu...
Catch up on parallel sessions and brief the user on project state
Load Brief business context into agent sessions
Use when AI/ML research engineering needs baseline reproduction, hypothesis-driven experiments, ablations, evaluation de...
Use when the user explicitly enables an automated same-project multi-thread development loop that keeps peer Codex tasks...
Use when two or more existing independent Codex App threads in the same project can benefit from bounded peer coordinati...
Use when an AI/ML research result, baseline promotion, ablation conclusion, benchmark claim, paper claim, surprising fin...
Use when existing independent Codex App threads in one project need peer advice, target/ACK validation, file or runtime-...
Generate a session briefing from development memory (events.jsonl, sessions.jsonl). Shows recent timeline, open question...
Compile daily briefing with meeting context, active deals, and citation tracking
Simple headless Puppeteer browser for rendering JavaScript-heavy pages and extracting clean text content. Use when user...
You are an expert in Browser Use, the Python library that lets AI agents control a web browser. You help developers buil...
Provide a multi-select UI for browsing and installing packs from the Loa Constructs Registry. Enables composable skill i...
Backend budget tracking patterns for AI generation. Awareness-based tracking (not blocking), tool timeouts, per-tool rat...
Cannabis-specialized bartender — strains, terpenes, edibles, rolling
Prüfung einer Bürgschaft § 765 BGB auf Wirksamkeit. Schriftform § 766 BGB, Akzessorietät § 767 BGB, Einrede der Vorauskl...
Workflow orchestrator that chains existing skills for feature development
Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when c...
Comprehensive Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents...
Use when creating a Nuxt frontend Mastra agent with pnpm using a minimum viable plain chat assistant (non-weather agent)...
Use when creating a production-minded Nuxt frontend Mastra agent with pnpm, based on a plain chat assistant (not weather...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services...
Builds and designs React Native Nitro Modules with Nitrogen, HybridObject TypeScript specs, Nitro View components, gener...
Builds new Claude Code skills with consistent structure, enforced standards, and project-aware configuration. Use when c...
Structures the build/buy/partner decision for an AI capability, including hybrid options, scored on differentiation valu...
Create, validate, or audit agent definitions. USE WHEN create agent, new agent, build agent, scaffold agent, validate ag...
Generate new skill with SKILL.md structure and proper integration
Memory patterns for multi-turn, multi-session agents — buffer, summary, vector-backed semantic/episodic, hierarchical wo...
Expert at creating and modifying Claude Code agents (subagents). Auto-invokes when the user wants to create, update, mod...
Step-by-step guide for building goal-driven agents. Creates package structure, defines goals, adds nodes, connects edges...
Core concepts for goal-driven agents - architecture, node types, tool discovery, and workflow overview. Use when startin...
Best practices, patterns, and examples for building goal-driven agents. Includes pause/resume architecture, hybrid workf...
Builds AI chat interfaces and conversational UI with streaming responses, context management, and multi-modal support. U...
Analyzes user requests to recommend appropriate Claude Code building blocks (skills, subagents, MCP servers, hooks, temp...
Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with...