AI Skills Hub - Browse 180,000+ Agent Skills

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

Apply chronicle event effects to world state. Use when events need to modify entities (battles change force strength, treaties change relationships, deaths remove agents). This is the core simulation engine.

Emit and query WSC chronicle events. Use when recording world events, checking event history, tracing causality chains, or finding events by type, location, or participants.

Initialize and manage WSC world state. Use when creating a new world, loading world state, advancing simulation ticks, or checking world status.

Create, validate, and query WSC world entities (polities, agents, regions, forces, locales, holdings). Use when working with entity JSON files, checking entity consistency, or finding entities by type, tag, or relationship.

Manages Wire dependency injection providers in go-kratos microservices. Adds constructors to ProviderSets and regenerates Wire code. Use when integrating new components into dependency injection.

Generates gRPC/HTTP service handlers for go-kratos microservices. Creates service structs, handler methods, and integrates with protobuf definitions. Use when implementing RPC handlers, adding API endpoints, creating dual transport (HTTP/gRPC) handlers, or connecting transport layer to business logic in kratos services.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Cross-referencing in R Markdown documents using bookdown. Use when creating Rmd files that need references to figures, tables, equations, or sections. Triggers on requests for academic reports, technical documents, or any R Markdown with numbered cross-references.

Token-efficient codebase navigation through intelligent symbol loading and querying. Use this skill when implementing new features (find existing patterns), exploring codebase structure, searching for components/functions/types, or understanding architectural layers. Reduces token usage by 60-95% compared to loading full files. Layer split enables 50-80% additional backend efficiency.

Unified execution engine for all development workflows. Progressive disclosure for phase execution, quick features, story completion, and scaffolding. Integrates with artifact-tracking and meatycapture-capture. Use when running /dev:execute-phase, /dev:quick-feature, /dev:implement-story, /dev:complete-user-story, or /dev:create-feature commands.

Compact Snakemake workflow patterns. Keep rules short, complex logic in Python modules.

Analyze codebase health - large files, test coverage gaps, duplicate code, dead/legacy code, and documentation issues. Use when asked to scan, audit, or assess code quality, find refactoring targets, or identify technical debt.

GitHub操作の統合スキル。issue作成、PR作成、レビュースレッド操作を提供。 使用ケース:（1）issue作成、（2）PR作成（事前チェック統合）、 （3）レビューコメント取得、（4）スレッド返信、（5）スレッド解決

Use when adding features, changing behavior, or modifying architecture. Creates change proposal with specs and tasks. ALWAYS ask for approval before proceeding to implementation. Do NOT use for bug fixes or trivial changes.

Load when starting work in 10x-Mapmaster or when unsure about project standards. Covers file organization, naming conventions, type constraints, SQL style, and project-specific limits (200-char descriptions, answer enums). Use to understand how the codebase is structured and what standards to follow.

Test game via browser with Chrome DevTools. Navigate UI, play through game flow, observe behavior and report issues.

Use when working with geographic queries, geometry filtering, ST_* functions, or region-based candidate filtering. Load for PostGIS spatial operations, polygon intersections, distance calculations, or geographic bounds. Covers ST_Intersects, ST_Contains, GiST indexes, and geometry storage patterns.

Use for ANY bug, test failure, or unexpected behavior. Use BEFORE proposing fixes. Four phases: investigate, analyze, hypothesize, implement. Ensures understanding before attempting solutions.

Use when working through any task checklist (not just OpenSpec). Complete one task, verify, mark done, then next. No skipping, no adding, no reordering.

REQUIRED before implementing any game feature, scoring logic, state transition, or decision-making. ALL business logic lives in PostgreSQL - frontend is presentation only. Load this to understand where code belongs: database function vs component. Covers RPC patterns, SECURITY DEFINER, and anti-patterns.

Cria e configura um ambiente de desenvolvimento Docker para NestJS com hot-reload, Dev Containers, e zero dependências no host.

Analyzes Claude Code session history to identify repeated workflows and suggest slash commands to automate them

Use when working with the Cloudflare Sandbox SDK, container lifecycle, session management, or OpenCode integration. Covers SDK patterns, security considerations, and common operations.

Git 项目版本发布自动化工具。支持语义化版本号升级 (major/minor/patch)， 基于 Angular commit 规范自动生成 CHANGELOG，创建 git tag 并推送到远程仓库。 触发关键词： - "发布版本"、"升级版本"、"更新版本"、"版本发布"、"发新版" - "更新版本并提交"、"升级并提交"、"发布并推送" - "bump version"、"release"、"new release" - "打tag"、"创建发布"、"创建tag" - "大版本更新"、"小版本更新"、"补丁版本" - "major release"、"minor release"、"patch release"

Documentation for Kubernetes Agent Sandbox - a CRD-based system for managing isolated AI agent execution environments. Use for queries about Sandbox CRDs (Sandbox, SandboxTemplate, SandboxClaim, SandboxWarmPool), Python SDK (SandboxClient, SandboxRouter, ComputerUseExtension), network policies, security configurations, and implementation examples. Keywords kubernetes sandbox, agent sandbox, CRD, python sdk, agentic-sandbox-client, isolated environment, gvisor, network policy.

Run and debug Rust tests for glhf. Use when running tests, fixing test failures, or adding new test cases.

This skill should be used when the user needs to visualize BAM alignment files in IGV (Integrative Genomics Viewer). Triggers include requests to generate IGV screenshots, visualize genomic regions with multiple BAM tracks, or create batch visualizations for WGS analysis results.

Markdownドキュメントの記述規約、スタイルガイド、markdownlint検証ルールを定義する。Markdownファイル作成時、README作成時、ドキュメント編集時、またはユーザーがドキュメント標準、Markdown形式、markdownlint、ドキュメントスタイルに言及した際に使用する。

N8N workflow automation platform. Use for workflow automation, integrations, nodes, credentials, API development, RAG/AI workflows, and low-code automation solutions.

life-os/ 目录的文件读写规范。处理 Markdown 笔记、YAML frontmatter、wiki-links、模板变量。当需要在 life-os/ 目录中创建、编辑、查找笔记时使用此技能。

Test the Java parser by parsing JDK source files and fixing parse errors. Use when asked to find/fix parse errors, test the parser, or improve JDK compatibility.

NixOS configuration advisor using MCP tools. Use when helping with NixOS/Home Manager configs, searching packages/options, or providing NixOS-specific guidance. Validates packages exist before suggesting them.

Guide for the fort control plane - secure inter-host communication system. Use when adding capabilities to hosts, writing handlers, understanding the GC protocol, or debugging control plane issues. Triggers on questions about fort.host.capabilities, fort.host.needs, the fort CLI, handler scripts, or inter-host calls.

SSO integration guidance for fort-nix services. Use when adding authentication to a service, choosing an SSO mode, configuring oauth2-proxy, or troubleshooting auth issues. Triggers on fort.cluster.services sso config, oauth2-proxy setup, OIDC integration, or auth header injection.

Build and orchestrate tasks using Nuke build system. Use when task involves running Nuke build targets, orchestrating complex build workflows, or managing build pipelines.

Use when ending a session, switching context, or wanting to preserve state for a future session to pick up

Run formatting, linting, and tests using uv + Ruff + pytest

Extracts design tokens from Figma files and generates production-ready CSS, SCSS, JSON, TypeScript, and W3C DTCG format files using the Figma MCP server

Manage git worktrees for AI agent workflows. Use when creating, listing, removing, or pruning worktrees, especially for ticket-based development where the agent needs to create isolated working directories for feature branches. Supports creating worktrees in .worktrees/ subdirectory, automatic branch creation from base branch (main), and cleanup of stale worktrees.

Erlang-style message passing via /tmp file system. Use when simulating actor model with actual message synchronization between processes. Provides send/receive primitives with blocking and pattern matching.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Reproduce, isolate, and fix a bug (or failing build/test), then summarize root cause, fix, and verification steps.

Verify changes follow nearest-scoped AGENTS.md rules: group changed files by nested scope, auto-fix formatting, run lint/tests, and report violations.

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

Develop and test API routes in the Next.js App Router. Use this when the user asks to create, modify, test, or debug API endpoints, handle API responses, validate request parameters, or work with the /api directory.

Foundational knowledge for writing BUGS/JAGS models including precision parameterization, declarative syntax, distributions, and R integration. Use when creating or reviewing BUGS/JAGS models.

Search RAG database for relevant content. Use for semantic queries over processed documents, code, or papers.

Patterns for hierarchical/multilevel Bayesian models including random effects, partial pooling, and centered vs non-centered parameterizations.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Git から指定範囲のコミットを収集し、Quarto（reveal.js）でスライド（HTML/PDF）を生成する。 タスクID、コミット範囲、ブランチ間の差分など、柔軟な指定方法に対応。

Manage dotfiles with chezmoi. Use when working with dotfiles, chezmoi templates, machine-specific configuration, syncing configs across machines, or when the user mentions chezmoi, dotfiles, or configuration management.

セッションログから価値ある発見を抽出し、カテゴリ別に整理する。「棚卸し」「セッションログの整理」「発見をまとめて」などと言われたら実行。

Manage authentication, authorization, and user sessions. Use when dealing with login, sign-up, API protection, middleware, or user data fetching.

Create and manage Inngest functions for reliable background jobs, workflows, and scheduled tasks.

MUST be loaded when setting up, installing, migrating, reviewing, auditing, or checking CLAUDE.md files in projects. Covers installing the promode CLAUDE.md into new projects, migrating existing CLAUDE.md content to READMEs (progressive disclosure), and auditing projects for conformance. Invoke PROACTIVELY when user mentions CLAUDE.md, project setup, agent configuration, or code meta files.

Organize and manage Jira boards, issues, and sprints. Use when the user wants to: (1) List, create, update, or transition Jira issues, (2) View or manage sprints, (3) Assign issues or change status, (4) Query issues with JQL, (5) Manage Jira boards. Requires environment variables JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN, and optionally JIRA_PROJECTS_FILTER.

목적과 사용 시점. 자동 트리거를 위해 PROACTIVELY USE 또는 MUST BE USED 포함.

Best practices for writing efficient, clean Stan programs

Guidelines for Stan models with ODE-based dynamics using modern interfaces

Use when (1) PROJECT_MANIFEST.json exists and you need to generate INITIAL_PLAN.md, (2) user wants a detailed implementation roadmap, (3) translating manifest into actionable milestones. Generates comprehensive project plan from the manifest.

Use when (1) PROJECT_MANIFEST.json and INITIAL_PLAN.md exist, (2) ready to execute setup.sh to initialize the project, (3) renaming template to project name. Wraps setup.sh with preflight checks and validation.

Create a Pull Request for the current issue branch

AWS CLI reference for Vessel staging environment (account 643610656178, ca-central-1). Use when troubleshooting staging infrastructure, checking logs, monitoring RDS/EC2/ECS, investigating slow queries, or debugging application errors. Covers CloudWatch Logs, RDS, EC2, ALB, Lambda, ECS, S3, SNS/SQS, Secrets Manager, WAF.

Use when building Towns Protocol bots - covers SDK initialization, slash commands, message handlers, reactions, interactive forms, blockchain operations, and deployment. Triggers: "towns bot", "makeTownsBot", "onSlashCommand", "onMessage", "sendInteractionRequest", "webhook", "bot deployment", "@towns-protocol/bot"

LaTeX 论文写作助手，负责章节、段落、图表、代码块等正文内容的撰写与组织。不涉及模板格式调整。

协助用户将阅读/观看素材转化为有深度的个人反思文章。读取sparks/文件夹中的原始素材和用户思考笔记，通过对话深化用户观点，最终输出结构化的写作蓝图(idea.md)。适用于：读后感、观后感、学习笔记、思维感悟类文章的构思阶段。

Safely install a Python package, verify it imports correctly, and pin it to requirements.txt

Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.

Skill/MCPの使い分けと組み合わせ設計を支援するガイド。外部ツール接続はMCP、手順・品質基準はSkillという分離原則、衝突回避、実例（財務バリュエーション/ミーティング準備）を参照し、どちらを使うか判断・設計したいときに使う。

Before calling roo_task, load this skill to handle Roo follow-ups. Use when coordinating Roo responses that return resultType/needsReply: ask the user with numbered options, summarize prior results, and re-send as a new Roo task (Roo cannot append in place).

Use this skill when the user asks about Rust module dependencies, dependency graphs, architecture visualization, cycle detection, DAG analysis, or module structure. Activate when you see phrases like "show module structure", "dependency graph", "visualize architecture", "check for circular dependencies", or "Mermaid diagram of modules".

Guide for writing FoundationDB simulation workloads in Rust. Use when

Behavior-Driven Development (BDD) で振る舞いを定義・シナリオ化するためのガイド。Given-When-Then と Gherkin で受け入れ条件やエッジケースを整理し、失敗パターンや小さく始める導入ステップを含めて、業務言語で明確なシナリオを書くときに使う。

Scan project folder structure, validate organization, clone GitHub repository, and generate an inventory of available materials. First step of writer workflow. Use when starting a new manuscript project.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Codex needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

ChatBotプロジェクトの開発全般を支援するスキル。プロジェクト構造、コーディング規約、開発ワークフローに関する知識を提供します。ChatBotプロジェクトで作業する時、プロジェクト構造について質問された時、コーディング規約について質問された時、新しい機能を追加する時に使用してください。

Merge multiple documentation sources (docs, GitHub, PDF) with conflict detection. Use when combining docs + code for complete skill coverage.

Package skills into uploadable ZIP files for Claude. Use after skill-builder/skill-enhancer to create final upload package.

Web search via the DDGS metasearch library. Use for searching for unknown documentation, facts, or any web content. Lightweight, no browser required.

Run Codex CLI inside a Podman container with full internet access but filesystem exposure limited to the repo root + explicit bind mounts; use when you want yolo/web-search without giving the agent access to your whole host filesystem.

Interactive browser automation via Chrome DevTools Protocol. Use when you need to interact with web pages, test frontends, or when user interaction with a visible browser is required.

Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.

Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.

Use the local Context7 CLI in this repo to search libraries and fetch Context7 context for skills or documentation tasks. Trigger when you need to run `c7 search`/`c7 context`, resolve library IDs, or retrieve text/json outputs from Context7 via the CLI.

Debug and analyze {{PROJECT_NAME}} LangGraph agent traces. Use when investigating agent behavior patterns, finding failures, analyzing latency, or understanding why Orchestrator/Analyst responses went wrong. Covers trace queries by agent tags, pattern analysis across runs, and common debugging scenarios.

Debug and analyze {{PROJECT_NAME}} errors and exceptions. Use when investigating crashes, error patterns, performance issues, or understanding what went wrong in production. Covers error queries by agent, exception types, and common debugging scenarios.

Synchronize knowledge base documentation with current codebase implementation. Performs full, incremental, or targeted audits of source code and updates code maps, PRDs, patterns, SOPs, and user-facing docs to match reality. Use when: - After major refactors - Periodic maintenance (monthly) - Before starting new phase of work - When docs feel stale - User says "update kb", "sync docs", "audit docs"

Programmatic verification of KB state: tickets, phases, tests, integrity. Provides scripts for automated checking at each workflow stage. SCRIPTS: - check_ticket.py: Ticket docs, tests, final status → next step - check_phase.py: Phase progress, all tickets complete? - check_tests.py: Trajectory, RED verification, coverage vs spec - check_integrity.py: Index.md matches dirs, roadmap has all active items Use when: - Checking ticket/phase completion - Validating before commit/archive - CI/CD automation - User says "status", "check", "verify"

Restructure unorganized text into readable markdown documents using Gemini AI. Use when processing article scraps, converting messy notes to structured documents, or translating English content to Korean.

Add timestamped log entry to daily note when user wants to log their work

Process data with plugin

Download public Google Slides, Docs, and Sheets to local files.

Use when working with Emacs org-mode - provides elisp patterns for headings, properties, tables, links, and org-mode manipulation

This skill should be used when the user asks "what is LoRA", "compare models", "which model is best for Chinese", "SFT vs DPO", "how to handle overfitting", "class imbalance solution", "model architecture", "training method comparison", or needs reference information about LLM fine-tuning. Provides structured knowledge base for models, methods, architectures, and troubleshooting.

Add a new one-time shop boost (buyable item) consistent with the app’s cat-petting theme and design-concept-reference.png. Produces the boosts.json entry, icon filename/path, accessible imageDescription, and concise icon generation instructions.

Acelera a criacao e manutencao de skills do Claude. Automatiza o scaffolding de pastas, validacao de metadados YAML e empacotamento ZIP correto.

Toolkit for interacting with and testing local web programs using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Apply Terraform changes safely in this infrastructure monorepo. Use when user asks to apply terraform, run terraform plan/apply, make infrastructure changes, update cloud resources, modify node pools, change cluster configuration, or update provider versions. Handles TFC remote execution.

Configure and operate Midnight Network infrastructure including proof servers, indexers, and network endpoints. Use when setting up development environment, troubleshooting connections, or configuring deployments. Triggers on network, proof server, indexer, or testnet questions.