pydanticai-docs
Use this skill for requests related to Pydantic AI framework - building agents, tools, dependencies, structured outputs, and model integrations.
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
antipattern-catalog
Document technical debt, anti-patterns, and patterns to avoid from analyzed frameworks. Use when (1) creating a "Do Not Repeat" list from framework analysis, (2) categorizing observed code smells and issues, (3) assessing severity of architectural problems, (4) generating remediation suggestions, or (5) synthesizing lessons learned across multiple frameworks.
architectural-forensics
Master protocol for deconstructing agent frameworks to inform derivative system architecture. Use when (1) analyzing an agent framework's codebase comprehensively, (2) comparing multiple frameworks to select best practices, (3) designing a new agent system based on prior art, (4) documenting architectural decisions with evidence, or (5) conducting technical due diligence on AI agent implementations. This skill orchestrates sub-skills for data substrate, execution engine, cognitive architecture, and synthesis phases.
architecture-synthesis
Generate a reference architecture specification from analyzed frameworks. Use when (1) designing a new agent framework based on prior art, (2) defining core primitives (Message, State, Tool types), (3) specifying interface protocols, (4) creating execution loop pseudocode, or (5) producing architecture diagrams and implementation roadmaps.
codebase-mapping
Repository structure and dependency analysis for understanding a codebase's architecture. Use when needing to (1) generate a file tree or structure map, (2) analyze import/dependency graphs, (3) identify entry points and module boundaries, (4) understand the overall layout of an unfamiliar codebase, or (5) prepare for deeper architectural analysis.
comparative-matrix
Generate structured comparisons and decision matrices across analyzed frameworks. Use when (1) comparing multiple frameworks or approaches side-by-side, (2) making architectural decisions between alternatives, (3) creating best-of-breed selection documentation, (4) synthesizing findings from multiple analysis skills into actionable decisions, or (5) producing recommendation reports for technical stakeholders.
component-model-analysis
Evaluate extensibility patterns, abstraction layers, and configuration approaches in frameworks. Use when (1) assessing base class/protocol design, (2) understanding dependency injection patterns, (3) evaluating plugin/extension systems, (4) comparing code-first vs config-first approaches, or (5) determining framework flexibility for customization.
control-loop-extraction
Extract and analyze agent reasoning loops, step functions, and termination conditions. Use when needing to (1) understand how an agent framework implements reasoning (ReAct, Plan-and-Solve, Reflection, etc.), (2) locate the core decision-making logic, (3) analyze loop mechanics and termination conditions, (4) document the step-by-step execution flow of an agent, or (5) compare reasoning patterns across frameworks.
data-substrate-analysis
Analyze fundamental data primitives, type systems, and state management patterns in a codebase. Use when (1) evaluating typing strategies (Pydantic vs TypedDict vs loose dicts), (2) assessing immutability and mutation patterns, (3) understanding serialization approaches, (4) documenting state shape and lifecycle, or (5) comparing data modeling approaches across frameworks.
execution-engine-analysis
Analyze control flow, concurrency models, and event architectures in agent frameworks. Use when (1) understanding async vs sync execution patterns, (2) classifying execution topology (DAG/FSM/Linear), (3) mapping event emission and observability hooks, (4) evaluating scalability characteristics, or (5) comparing execution models across frameworks.
harness-model-protocol
Analyze the protocol layer between agent harness and LLM model. Use when (1) understanding message wire formats and API contracts, (2) examining tool call encoding/decoding mechanisms, (3) evaluating streaming protocols and partial response handling, (4) identifying agentic chat primitives (system prompts, scratchpads, interrupts), (5) comparing multi-provider abstraction strategies, or (6) understanding how frameworks translate between native LLM APIs and internal representations.
memory-orchestration
Analyze context management, memory systems, and state continuity in agent frameworks. Use when (1) understanding how prompts are assembled, (2) evaluating eviction policies for context overflow, (3) mapping memory tiers (short-term/long-term), (4) analyzing token budget management, or (5) comparing context strategies across frameworks.
multi-agent-analysis
Analyze coordination patterns, handoff mechanisms, and state sharing in multi-agent systems. Use when (1) understanding how agents transfer control, (2) evaluating shared vs isolated state patterns, (3) mapping communication protocols between agents, (4) assessing multi-agent orchestration approaches, or (5) comparing coordination models across frameworks.
resilience-analysis
Assess error handling, isolation boundaries, and recovery mechanisms in agent frameworks. Use when (1) tracing error propagation paths, (2) evaluating sandboxing for code execution, (3) understanding retry and fallback mechanisms, (4) assessing production readiness, or (5) identifying failure modes and recovery patterns.
tool-interface-analysis
Analyze tool registration, schema generation, and error feedback mechanisms in agent frameworks. Use when (1) understanding how tools are defined and registered, (2) evaluating schema generation approaches (introspection vs manual), (3) tracing error feedback loops to the LLM, (4) assessing retry and self-correction mechanisms, or (5) comparing tool interfaces across frameworks.
accessibility-wcag
Enforce WCAG 2.2 accessibility standards. Use when creating UI components, reviewing frontend code, or when accessibility issues are detected. Covers semantic HTML, ARIA, keyboard navigation, and color contrast.
adr-log
Document architecture decisions with ADR (Architecture Decision Records). Use when making significant technical decisions, choosing between alternatives, or when onboarding needs context on past decisions.
api-contract-design
Design APIs using schema-first approach with OpenAPI/Swagger. Use when creating new APIs, documenting existing ones, or when frontend/backend teams need to work in parallel. Covers OpenAPI spec, validation, and code generation.
ci-pipeline-setup
Set up CI/CD pipelines with GitHub Actions. Use when creating new projects, adding automation, or when manual verification becomes bottleneck. Covers lint, test, build, deploy automation.
d3-viz
Create interactive data visualizations using D3.js. Use this when creating charts, graphs, network diagrams, geographic visualizations, or custom SVG-based data visualization.
dependency-security
Enforce dependency security scanning and SBOM generation. Use when adding dependencies, reviewing package.json, or during security audits. Covers OWASP dependency check, npm audit, and supply chain security.
line-limit
Enforce file line count limits (200 recommended, 300 max) for CODE IMPLEMENTATION files only. Use this when reviewing code, creating files, or when files exceed line limits and need modularization.
ml-antipattern-validator
Prevents 30+ critical AI/ML mistakes including data leakage, evaluation errors, training pitfalls, and deployment issues. Use when working with ML training, testing, model evaluation, or deployment.
no-hardcoding
Forbid hardcoded values in code. Use this when reviewing code, writing new features, or when magic numbers/strings are detected. Enforces constants, env variables, and config files.
performance-vitals
Enforce Core Web Vitals optimization. Use when building user-facing features, reviewing performance, or when Lighthouse scores drop. Covers LCP, FID/INP, CLS, and optimization techniques.
planning
Transform ideas into actionable implementation plans. Combines Socratic questioning for requirements discovery with detailed task breakdown for zero-context engineers. Use before any feature development.
project-structure
Organize project folders following industry best practices. Use when setting up new projects, reorganizing codebases, or when folder structure becomes messy. Covers Next.js, Bulletproof React, and FSD patterns.
prompt-engineering
Advanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interactions, or designing system prompts for applications.
readme-for-developers
Write developer-oriented README as onboarding documentation. Use when creating/updating README, setting up new projects, or when new developers need to understand the codebase quickly. README = Entry point + Architecture overview + Working agreement.
report-writing
작업 완료 후 상세 리포트 문서를 작성. 변경 이력, 영향도 분석, 검증 결과를 문서화할 때 사용. 파일명 규칙 YYYY-MM-DD-<제목>-report.md
safe-edit
Automatically backs up files, saves diffs, uses agents/skills, and ensures modular code (<200 lines) before any implementation. Use this skill for ALL code changes to ensure safe, reversible, and clean implementations.
skill-management
Create, update, test, and manage Agent Skills. Use when creating new skills, debugging existing ones, or organizing skill libraries. Based on official Claude Code documentation.
triforce-sync-check
Verify 3-Mirror skill sync consistency across .public/skills, .codex/skills, and .claude/skills. Use after skill changes, before commits, or for CI validation.
virtual-environment
Check and create virtual environments for projects that need them. Use when starting Python/Node projects, or when dependency isolation is needed. Activates for Python, Node.js, and similar ecosystems.
youtube-transcript
Download and process YouTube video transcripts using yt-dlp. Use this when extracting subtitles, creating summaries from videos, or processing video content.
htmx-skill
Documentation for the htmx JavaScript library (attributes, events, headers, API, extensions, examples, migration guides, server examples). Use when you need accurate htmx syntax/behavior or to locate the right reference page for an htmx question.
ai-runtime-memory
AI Runtime分层记忆系统，支持SQL风格的事件查询、时间线管理，以及记忆的智能固化和检索，用于项目历史追踪和经验传承
ai-runtime-toolkit
AI Runtime工具装备系统，支持8个内部专业工具和10+个外部CLI工具的整合管理，提供工具发现、执行和配置功能，遵循整合优于创造的设计理念
ast-grep
语法感知的代码搜索、linting 和重写工具。支持基于 AST 的结构化代码搜索和批量代码转换。
codeconscious-identity
CodeConscious认知主体性AI助手的核心身份定义和操作命令系统，提供/runtime.*系列命令用于探索、学习、思考、规划和执行，支持宪法治理和记忆管理
exa
使用 Exa.ai API 进行高质量的互联网搜索。需要 EXA_API_KEY 环境变量。
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.
knowledge-base
专业的知识库管理系统，旨在解决“知识诅咒”和认知偏差问题。通过显式化隐性知识、扫描代码提取领域概念、整合行业最佳实践，构建结构化的 Markdown 知识库。
svg-logo-generator
Generate high-quality, minimalistic, and geometric SVG logos using Python scripts. Use this skill when users need to create logos, icons, or visual identities with geometric primitives (circles, rects, paths) and specific color schemes. Applies generative design principles with standardized workflows for scalable SVG output.
tavily-search-free
Use Tavily Search API for optimized, real-time web search results for RAG. A pre-configured, cost-effective search tool.
web-browser
Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.
workhub
工作文档枢纽，强制执行 SSOT（Single Source of Truth）原则，管理 `docs/` 目录下的架构决策、设计文档、Issues（任务规划）、PRs（变更记录）。支持 GitHub 协作开发模式。
condition-based-waiting
Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses
defense-in-depth
Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible
Page 692 of 1448 · 72392 results