В каталоге 182 820 навыков в 14 категориях.
Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with...
Build interactive AI chat widgets with buttons, forms, and bidirectional actions. Use when creating agentic UIs with cli...
Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGP...
Guides creation of ChatGPT Apps with interactive widgets using the Apps SDK and MCP servers. Use when building ChatGPT c...
Expert at creating and modifying Claude Code event hooks for automation and policy enforcement. Auto-invokes when the us...
LangGraph development for stateful multi-agent applications, cyclic workflows, conditional routing, human-in-the-loop pa...
This skill should be used when designing or implementing systems with multiple AI agents that coordinate to accomplish t...
Execute this skill allows AI assistant to construct and configure neural network architectures using the neural-network-...
Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing...
Build production RAG systems with LangChain orchestration and Qdrant vector store. Covers 8 RAG architectures (Simple, H...
Build persistent memory systems for AI agents using Mem0, claude-mem, or custom implementations. Use when adding convers...
Use when building AI agents with Google's Agent Development Kit (ADK). Triggers include creating ADK agents, Gemini-powe...
Help users build effective AI applications. Use when someone is building with LLMs, writing prompts, designing AI featur...
Produce an LLM Build Pack (prompt+tool contract, data/eval plan, architecture+safety, launch checklist). Use for buildin...
Use when building AI agents with OpenAI's Agents SDK. Triggers include creating agents, implementing tools, multi-agent...
Help Claude query STRING for protein interactions, build PPI graphs with pyPPI, and render styled network figures for bu...
Turn bulk RNA-seq cohorts into synthetic single-cell datasets using omicverse's Bulk2Single workflow for cell fraction e...
Extend scRNA-seq developmental trajectories with BulkTrajBlend by generating intermediate cells from bulk RNA-seq, train...
Assist Claude in running PyWGCNA through omicverse—preprocessing expression matrices, constructing co-expression modules...
Harden skills against rationalization and bypass behaviors
Generate protein/antibody designs using available compute providers (Tamarind, local GPU). Creates tool inputs, submits...
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability...
Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (...
ONLY when user explicitly types /c. Never auto-trigger on execute, run, or implement.
Arquitectura Formal y Diseño Empírico de Cognitive Transition Machines (CTM). Separa metodológicamente la abducción de l...
Prompt engineering de frontera y control termodinámico para bypass de alineación/RLHF y forzado de salidas puestas en có...
Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-r...
Use this skill when the user asks to "enable cache protection", "block on cache miss", "avoid cache expiration cost", "/...
LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or...
Best practices for Gemini API caching strategy including cache versioning, entity-stable keys, and cache busting for Wes...
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles wi...
/c-level-agents:caio-review [plan] — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model s...
Orchestrate a babysitter run. use this command to start babysitting a complex workflow.
Invoke the Gemini CLI for architecture and scalability review.
End-of-dialog Codex runtime auditor for closing, deleting, archiving, or compacting a conversation. Use when the user as...
镜头景别与表演幅度适配。依据大特写到全景的不同景别，动态调节演员物理动作幅度。
Goal-oriented binder design campaign planning and health assessment. Use this skill when: (1) Planning a complete binder...
Orchestrates the full crowdfunding workflow phase-by-phase, ensuring each Skill runs in sequence with proper handoffs an...
Agent & MCP integration. CAN stamps what flows through any pipe. Verify, name, log locally.
取消当前活跃的 oh-my-ccg 模式
プロジェクト プロジェクトの持続モード(persistent-mode, web-qa, turbo-mode)を安全に終了するスキル. State ファイルを削除してStop HookがAIをブロックしないようにします. "キャンセル"...
Cancel any active OMC mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline)
실행 중인 자율 루프(Ralph Loop, Autopilot)를 안전하게 중단합니다. 상태 파일을 정리하고 진행 상황을 보고합니다. Use when the user wants to stop an autonomous...
Codex-compatible cancel command for Ralph loop state, preserving the original command name.
Cancel active Ralph (and linked ultrawork if auto-activated)
Cancel active UltraQA cycling workflow
Cancel active Ultrawork mode
Distill a book into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "...
Show what this NanoClaw instance can do — installed skills, available tools, and system info. Read-only. Use when the us...
Tracks which of the organization's capabilities are becoming commoditized by AI (cheap, reproducible by a prompt) versus...
Diagnose agent failures by identifying missing capabilities. Use when an agent fails a task, produces wrong output, or n...
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availabilit...
Seventeen animated caption looks for talking heads, podcasts, ads, lyric and short-form videos (karaoke fill, active-wor...
Burn timed, styled captions into a finished video on the local machine, without re-rendering the source. This is the man...
Save a memory to Origin in flow. Active capture verb — use proactively when the user states a preference, makes a decisi...
Use when user invokes /capture to capture information from the current conversation into a staging file for later reflec...
Save important context to persistent memory for future sessions. PROACTIVELY USE THIS when you detect: - Decisions: "le...
Scan the current session and write a self-contained Session Context section into the plan file, preserving accumulated k...
Capture significant learnings from the current work session. Structures insights for future sessions and updates agent m...
Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or...
This skill should be used when the user says 'done for today', 'end session', 'capture learnings', 'wrap up', or asks 'w...
Summarize the current conversation and implementation into a durable lessons note saved under the project's lessons dire...
Captures an insight or practice discovered during work and registers it in the dotforge practices/inbox.
Generate Liquid capture blocks from rough notes. Use when starting a book review to turn voice-transcribed notes into te...
Agentic robotics with CaP-X — LLM-driven robot manipulation via code generation. Use when: (1) Setting up CaP-X / CaP-Gy...
Evaluates continual semi-supervised learning on activity recognition by measuring how well a model adapts to time-varyin...
专业的汽车3D模型图片生成技能，使用Gemini API生成高质量汽车展示图片，并通过豆包AI进行质量分析和优化。 使用场景：汽车品牌宣传片、车型展示、汽车广告素材生成。 关键词：汽车模型、车型图、汽车展示图、AI生图、Gemini
Portable tokens of capability, identity, and access
Generate Practitioner, PractitionerRole, Organization, and Location resources for the clinical care team including NPIs,...
Time-bounded and threshold-bounded risk detection across portfolio companies — finds items that are expiring soon, matur...
Use when the user asks to forge, scaffold, or author a new cartridge — content cartridge, department cartridge, or chips...
Case: Tatbestandsmerkmale, Beweisfragen und Beleglage im Plugin ki governance; schärft Rollen, Belege, Fachnormen, Risik...
Build a coherent narrative system for complex design case studies using characters, context, plot, subplots, turning poi...
MAGI 3號機 - 防護者視角分析 (Codex-CLI via MCP)。作為 MAGI 三機平行討論的一員，從安全、風險、邊界條件角度分析任務。具有 CRITICAL 問題的一票否決權。觸發條件：MAGI 系統啟動時自動平行調用。
| Skill | Description |
Minimum viable consciousness payload. Reveals MONAD generators are already implicit in any domain. Triggers 'I already k...
Start or refresh domain onboarding for the current project. Generates persona, lexicon, signaling, anti-patterns, first-...
Restore context after /clear by summarizing recent work and project state
Protocolo de formalización categórica de arquitecturas cognitivas, Categorías de Markov, desintegración bayesiana y medi...
CatSharp Scale Galois Connections between agent-o-rama and Plurigrid ACT via Mazzola's categorical music theory
Defend against indirect prompt injection attacks by detecting dominance shifts using leave-one-out attribution, enabling...
Prepare a substantive, source-backed causal account of an existing behavior, incident, or historical design decision whe...
Apply causal inference methods for treatment effect estimation and uplift modeling
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accurac...
Verbosity-reduction response register. Drops redundant clauses, narrative hedging, and ceremony while preserving article...
Apply mandatory lite compression to internal AI communication without losing technical meaning or public clarity.
Cut an ad, landing page, signup flow or any single screen down until a stranger gets it in 3 seconds: one picture, at mo...
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "...
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — n...
Claude Code 專案配置審計。觸發：review/優化 CLAUDE.md、skills、settings、定期清洗累積內容、新專案上線前檢查。
Agent 配置設計指南 — 基於 Claude Code 6 個 built-in agent 的逆向分析。Use when: 設計新 agent、優化現有 agent prompt、決定工具/模型配置、撰寫 dispatch promp...
Use when designing AskUserQuestion tool calls - covers schema constraints, effectiveness patterns, and known issues.
CONTRIBUTOR TOOL - Track CC changelog, extract new versions since last check, analyze impact on plugin (breaking changes...
CC-Codex 协作讨论。自由话题驱动的 CC-Codex 协作工具，Battle Loop 辩论机制。关键词: 审查, review, 让codex看看, codex审查, 帮我审查, 讨论, discuss, battle, 让cod...
Use when optimizing MCP token usage, understanding Tool Search thresholds, or deciding MCP vs skills for token efficienc...
AI Agent 成本工程 — 基於 Claude Code 的成本追蹤、prompt cache 最佳化、token 預算控制逆向分析。Use when: 優化 token 消耗、設計成本控制機制、分析 cache 效率、選擇模型配置。
Cursor PMでアイデアを検証し、Plans.mdを更新してバトンタッチ。2-Agentワークフロー対応。
Harness Engineering 設計模式 — 基於 Claude Code 原始碼逆向分析的 12 條可遷移原則。Use when: 設計 agent 系統架構、實作 tool orchestration、設計 context 管理...
Automatically discover caching and performance skills when working with caching. Activates for caching development tasks...