В каталоге 183 730 навыков в 14 категориях.
Automate Codeinterpreter tasks via Rube MCP (Composio). Always search tools first for current schemas.
AI 자율 개발 루프 제어 스킬. codeloop start/stop/status 서브커맨드로 Stop Hook 기반 무한 루프를 시작·중지·모니터링한다. Triggers: codeloop, codeloop sta...
Interactive project setup wizard for Codeloop — the AI autonomous development loop engine. Fixed stack: Vercel + Railway...
Create new documentation based on the current conversation context.
Create a git commit following the team's Conventional Commit conventions. Use when the user asks to commit changes or cr...
Create the OpenSpec specs of behaviour that already exists in the code, so the next change can modify or remove it inste...
Create a plan for the specified task and store it as GitHub issues in the repository of the current working directory. G...
Create a plan for the specified task and store it as GitLab issues in the repository of the current working directory. G...
Create a plan for the specified task.
Implement one phase of the plan specified by the user. Only implements a single phase per invocation, then stops for use...
Implement one phase of a plan stored as GitHub issues in the repository of the current working directory. Given the URL...
Implement one phase of a plan stored as GitLab issues in the repository of the current working directory. Given the URL...
Comprehensive guide for creating, configuring, and troubleshooting codemagic.yaml files for CI/CD workflows. Use when bu...
Drive Codeman, the session manager this agent is running inside, over its HTTP API: list sessions, start worker sessions...
Generate navigational codebase maps with architecture diagrams. Use when mapping a codebase, creating architecture docs,...
Use when the user wants to map, visualize, or understand codebase structure. Generates hierarchical code maps using LSP...
Use when indexing a codebase for agent navigation, generating or refreshing CODEMAP.md files, mapping large project stru...
Generate codebase maps with directory trees and relationships. Use for onboarding and architecture documentation.
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly...
Skill: codemap-sync
Codebase haritasını güncelle. "/codemap-update" komutuyla veya her feature implementation sonrasında otomatik çalışır. C...
Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable code transformations. T...
Automate large-scale codebase refactoring using AST transformations on React code.
Your pathfinder for navigating unknown codebases. Investigates with precision, implements surgically, and never assumes...
codenotify
ローカルで検証済みのブラウザ向け HTML、CSS、JavaScript を CodePen Prefill launcher に変換し、承認後に未保存の Pen を開く。フロントエンドのデモを CodePen で共有して、記事へ埋め込む準...
CodeQL is a static analysis framework that queries code as a database. Use when you need interprocedural analysis or com...
Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis. Trig...
Configure GitHub CodeQL analysis, run or write queries, interpret SARIF findings, and verify fixes for reported vulnerab...
Comprehensive guide for setting up and configuring CodeQL code scanning via GitHub Actions workflows and the CodeQL CLI....
Use when a task involves triaging CodeQL alerts or developing a CodeQL query against a defined codebase and language to...
Use to run CodeQL scans (full or high-precision) and process SARIF findings.
Advanced security analysis using GitHub CodeQL to find zero-day vulnerabilities, injection flaws, and security anti-patt...
Use when a CodeQL analysis step fails with "Invalid checksum for page N of the compressed relation ... The database is c...
Expert-level CodeQL for static analysis, vulnerability detection, and security code scanning
Configures and runs GitHub CodeQL - semantic-database SAST with queries written in the CodeQL declarative query language...
Run CodeQL semantic code analysis for security vulnerabilities
Execute CodeQL security scans with language detection, database caching, and SARIF output. Use when performing static se...
Write, edit, and refactor code with full tool access - Use when you need to actually write or modify code, create files,...
Write idiomatic GDScript 4.x for Godot 4.7 — use when writing any GDScript code, autoloads, or class definitions.
Implementa código passo-a-passo com verificação obrigatória e autocrítica. Use quando precisar implementar features, faz...
A skill for executing development tasks using the beans utility. Handles task initialization, child ticket management, s...
Run and supervise Lev-aware coding workers across Codex, Claude Code, Gemini, OpenCode, Pi, OmO Native (omo), or oh-my-p...
Write the actual code from a build plan — files, edits, and run-verify cycles. Invoke for every build step that produces...
Implementation Agent: Full TDD workflow in a single context window. Writes tests, implements code, and iterates until al...
Coder subagent — implements features and fixes using TDD in a git worktree, then commits
Run the Codex Optimized Development, Evaluation, and Remediation (CODER) Loop with an orchestration-only coordinator, no...
Retrieve universal coding patterns from vector database using true two-stage retrieval. Auto-invokes before complex task...
Store universal coding patterns into vector database. Auto-invokes after difficult tasks with broadly-applicable lessons...
Coder CLI commands for workspace management, templates, and platform operations
Triage and address CodeRabbit automated review comments on a pull request.
AI-powered automated code review, PR summarization, and interactive developer feedback / Review kode otomatis berbasis A...
Optimize CodeRabbit costs through tier selection, sampling, and usage monitoring. Use when analyzing CodeRabbit billing,...
Implement CodeRabbit PII handling, data retention, and GDPR/CCPA compliance patterns. Use when handling sensitive data,...
Collect CodeRabbit debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, prep...
Implement fixes for specific CodeRabbit review issues. Runs in isolated subagent context with focused task. Verifies fix...
Create a minimal working CodeRabbit example. Use when starting a new CodeRabbit integration, testing your setup, or lear...
Install and configure CodeRabbit SDK/CLI authentication. Use when setting up a new CodeRabbit integration, configuring A...
Systematic workflow for CodeRabbit reviews - local CLI, PR threads, and commit attribution
Configure CodeRabbit local development with hot reload and testing. Use when setting up a development environment, confi...
Set up comprehensive observability for CodeRabbit integrations with metrics, traces, and alerts. Use when implementing m...
Use after completing file changes - strongest for source code (AST-aware linting, security, tests), lighter support for...
Unified CodeRabbit CLI execution via WSL with self-healing loop. Use this skill when running automated code review befor...
Perform code review using CodeRabbit. Must use this skill if instructed to perform a CodeRabbit review.
Use CodeRabbit CLI to receive external code review feedback and address identified issues. Invoke this skill when the us...
Integrates CodeRabbit for automated PR code review. Use after PR creation to get AI-powered review feedback before human...
Apply production-ready CodeRabbit SDK patterns for TypeScript and Python. Use when implementing CodeRabbit integrations,...
Analyze code review findings and create execution plan. Decides parallel vs sequential fixing based on issue severity an...
Triage unresolved CodeRabbit feedback on the current GitHub pull request. Use for read-only disposition and, only when s...
Automate Codereadr tasks via Rube MCP (Composio). Always search tools first for current schemas.
Structured code review covering style, readability, and security concerns with actionable feedback. Use when reviewing p...
Adversarial code review of uncommitted or staged changes. Includes a security scan via /security for full-tier reviews (...
Brutally honest code review in the style of Linus Torvalds, focusing on data structures, simplicity, and pragmatism. Use...
Expert code writer - produces clean, production-ready code
Create, manage, and optimize GitHub Codespaces cloud development environments. Configure devcontainers, manage resources...
Analyze code for style violations, pattern compliance, and quality issues
AI context persistence - tags in code = permanent memory across sessions
Develop CODESYS Structured Text and Python ScriptEngine workflows; troubleshoot fieldbus and OPC UA integration in a tes...
Generates interactive code flow diagrams (.cgraph files).Invoke when users ask: "how does X work", "show me the flow of...
Codev project management CLI quick reference. Use when running codev commands to check correct syntax for init, adopt, u...
Generate a structured product knowledge base from codebase scanning. Creates a codewiki/ folder with architecture docs,...
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implemen...
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "a...
AI peer review via OpenAI Codex CLI. Use when reviewing code changes, validating technical decisions, comparing implemen...
Use quando o usuário pede para executar Codex CLI (codex exec, codex resume) ou referencia OpenAI Codex para análise de...
A radically minimal, blank-canvas interface built as a pure edge-to-edge surface, with almost no color and typography ca...
Delegate narrow, mechanical coding tasks to OpenAI Codex Command Line Interface (CLI) — Claude orchestrates and judges,...
Drive the codex CLI (GPT-6 astra) as a delegate — debugging, test writing, scoped implementation. Not for reviews, which...
Codex CLI を read-only sandbox で実行し、OpenAI 側のセカンドオピニオンを得る。
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refacto...
This skill should be used ONLY when the user explicitly mentions "codex" by name. Trigger phrases: "use codex", "ask cod...
Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second o...
Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fix...
Bridge to the OpenAI Codex CLI for high-reasoning tasks using gpt-5.3-codex.
Get alternative perspectives via OpenAI Codex on complex design decisions, architecture trade-offs, stuck debugging, or...