В каталоге 182 820 навыков в 14 категориях.
Translate an external competency framework like DigComp, GreenComp, or ISTE into classroom-ready activities. Use when im...
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a...
> Compiler: skill-compiler/1.0.0
Ralph Wiggum-style completion promise tracking for System 3 sessions. Use when starting a new session with user goals, w...
Multi-step reasoning patterns and frameworks for systematic problem solving. Activate for Chain-of-Thought, Tree-of-Thou...
Calculates a complexity score (1-50) from a user prompt. Analyzes keywords, scope indicators, quantity modifiers, and ne...
Critique a generated answer against the question and supplied evidence by calling the frozen Executor Model. Use for ans...
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration...
Master professional video compositing techniques for seamless visual effects integration including layering, masking, ro...
项目提供了可复用的配置和组件模板，位于 templates/ 目录：
Especialista em manutenção de contexto e memórias. Atualiza arquivos de arquitetura, regras de negócio e guias do projet...
Capture learnings (problems, decisions, gotchas) from sessions to make future agents more effective
Clusters similar lessons and synthesizes testable patterns
I-Lang compression engine. All internal planning uses I-Lang v4.0 syntax. Save 60%+ tokens. User never sees compressed o...
Recommends context compression strategies for bloated or quota-heavy sessions. Use when context feels sluggish or quota...
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typ...
Specialized skill for robot vision including feature detection, tracking, and camera calibration
Implement computer vision tasks including image classification, object detection, segmentation, and pose estimation usin...
Build computer vision systems using CNNs and modern architectures. Use for image classification, object detection (YOLO,...
SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-...
SOTA Computer Vision Expert. Specialized in YOLO, Segment Anything, Vision Language Models, and real-time spatial analys...
Assist with image analysis, object detection, and visual AI tasks
Build production computer vision pipelines for object detection, tracking, and video analysis. Handles drone footage, wi...
Shape replies to the smallest complete answer. Right-size to the ask — trivial asks get one bare sentence; bigger asks g...
Scholze-Clausen condensed mathematics bridge to sheaf neural networks via 6-functor formalism
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeou...
Set up conditional documentation loading to prevent context pollution. Use when organizing project docs, implementing pr...
Comprehensive assistance with conductor
Use when building slides, a poster, or a lightning talk from a manuscript, when a presentation must exist in Turkish and...
AGI: SteerConf confidence calibration protocol — generates calibrated confidence scores for any analytical output using...
Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns....
See the main Model Explainability skill for comprehensive coverage of confidence scoring and calibration.
Manage the user-level AIWG configuration file for persistent preferences across all projects
Seed JSON configuration files into database. Use ONCE at BAZINGA session initialization, BEFORE spawning PM.
Everything Claude Code のインタラクティブなインストーラー — スキルとルールの選択とインストールをユーザーレベルまたはプロジェクトレベルのディレクトリへガイドし、パスを検証し、必要に応じてインストールされたファイルを...
Everything Claude Code 的交互式安装程序 — 引导用户选择并安装技能和规则到用户级或项目级目录，验证路径，并可选择优化已安装文件。
Generate workspace-level forge binding prompts and agents from workspace.config.yaml topology.
Use when the user wants to view, edit, remove, or validate their grimoire settings — including reading current preferenc...
Select and configure a Coval metric for a concrete product criterion, choosing transcript, audio, trace or deterministic...
Use this skill to test whether value-investing reports follow required workflow, schema, output, data, and execution-gat...
Improves speculative decoding acceptance rates by exposing target model's intermediate reasoning through contemplate tok...
Inspect classifier errors with confusion matrices after predictions already exist. Use for per-class error analysis, thr...
Connect any AI agent to MCP servers through mcptoon — one config synced everywhere, one stdio gateway, 99.2% fewer token...
Pair the Apeiron web editor (a browser tab) with this Claude Code through the hosted relay
Agreement protocol in multi-agent systems
Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propa...
Multi-agent consensus voting with domain-weighted expertise for critical decisions requiring structured validation
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self...
A framework for aligning AI agents to be helpful, harmless, and honest using a principles-based critique loop. Use this...
AI consultation CLI quick reference. Use when running consult commands to check syntax for PR reviews, spec reviews, pla...
Use this skill when Claude needs an outside perspective on complex problems, is stuck on a technical challenge, needs va...
Multi-turn consultation with Codex CLI for second opinions, brainstorming, or collaborative problem-solving. Use when th...
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a ver...
Single source of truth for all contacts, PAs, and WhatsApp groups. Use when: looking up a phone number, email, address,...
Review Docker and Kubernetes configurations for AI workloads — covering privileged container risks for GPU access, model...
Every Claude Code session starts fresh—no memory of past discoveries. The Continuous Learning Skill solves this by extra...
正文生成(四模式)
Creates beautiful, branded HTML content assets — industry reports, landing pages, comparison sheets, one-pagers — from s...
Turn a batch of ideas (or your content pillars) into a 2-week reel posting calendar with hooks, formats, and a daily pla...
Extract content ideas from long-form content (transcripts, videos, articles) and organize them into detailed, platform-s...
This skill should be used when the user asks to generate content such as titles, slogans, dialogues, or scripts. It prov...
AI-powered document, image, and flowchart generation. Use this skill when generating images with fal.ai, creating flowch...
Context window management. Use when: - User asks about "context window", "context usage", "context limit" - User mention...
Получение контекста пользователя и credentials
[Utilities] Load project context for current session
Use when the user runs /context or asks for a briefing on his Personal OS — who he is, how he thinks, how he wants AI to...
CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Densit...
Context window conservation rules. Invoke when approaching context limits or before large tasks.
Runtime context passed to compiled closures — the world as seen from inside
Context optimization extends the effective capacity of limited context windows through strategic compression, masking, c...
Proactive context window management via token monitoring, intelligent extraction, and selective rehydration. Use when ap...
Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automa...
Create/update atomic documentation (blocks, foundations, stacks). Use when user asks to "create atomic doc", "add a bloc...
Audit current context composition and identify optimization opportunities. Use when context window is overloaded, agents...
Comprehensive quality audit for CLAUDE.md context files. Use when performing thorough quality checks, preparing for rele...
Understand agent context isolation and write effective prompts for spawned agents. Use when orchestrating multi-agent wo...
Synchronize task state and metadata across Claude, Cursor, and Factory Droid sessions. Use when handing off tasks betwee...
Tracks approximate context window usage during a session. Reports estimates periodically and warns when approaching limi...
审计并减少 Codex 在 instructions、skills、tools、MCP、retrieval 和 memory 上的上下文与 Token 开销。适用于会话臃肿、加载材料过多、集成重叠，或用户要求在不降低质量的前提下省 Toke...
Analyzes Claude Project context budget under the automatic-RAG-by-window model: knowledge files vs. threshold-exempt ove...
Context budget tracking and skill loading limits for agent sessions. Monitors token consumption per agent, enforces prel...
Use when a coding session is burning context fast, output is drowning in noise, the model keeps forgetting earlier decis...
Audits Claude Code context window consumption across agents, skills, MCP servers, rules, and CLAUDE.md files — identifie...
Build BUSINESS.md and ICP.md context files for a ghostwriting client from raw info, notes, a website, or a call transcri...
Audit what auto-loads into an agent session's context window and suggest lean, reversible fixes to cut startup tokens.
Zbiera, zapisuje i ładuje kontekst osobisty i firmowy w 20 warstwach informacyjnych. Tryb zapisu: "zapamiętaj że...", "z...
Design and evaluate compression strategies for long-running sessions
Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compressio...
Use Tokenless for large files and noisy tool outputs before they enter context. Must be used when commands, Read output,...
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need...
Compress selected context to a target token budget while preserving decisions, evidence, constraints, and unresolved que...
When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approa...
Compress long task context into a verified handoff that preserves goals, authority, constraints, decisions, evidence, ar...
Context compression and summarization methodology. Techniques for reducing token usage while preserving decision-critica...
High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops...
Use when starting a complex task to load relevant context from Memory MCP and suggest appropriate skills based on task t...
Context management tools for Claude Code - provides intelligent codebase mapping with Python, Rust, and C++ parsing, dup...
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent f...
Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is es...