Registry durchsuchen

Alle Einträge, alphabetisch — insgesamt 57.265. Seite 47 von 230.

• code-health-checkRun a comprehensive codebase health analysis covering dead code, dependency freshness, test coverage gaps, sec
• code-historyTrace the git history of specific code — when a function, pattern, or file was added, modified, or removed, an
• code-hooks-playbookConfigure and maintain Claude Code hooks: choosing lifecycle events, writing matchers, selecting hook types (c
• code-humanizerUse when AI-written code needs structural cleanup or when implementing a change under a guard against AI codin
• code-hygieneLanguage-agnostic code hygiene -- honest comments, no dead/reinvented/duplicated code, truthful names, real im
• code-implementation-business-specificationsThis skill should be used when the user asks to implement code based on business requirements, build a project
• code-instrumentation-generatorAutomatically instruments source code to collect runtime information such as function calls, branch decisions,
• code-intelligenceRoute codebase-structure questions (who calls X, where used, what imports, change-impact) to a code-graph firs
• code-investigateDual-perspective code investigation. Use when: deep code analysis needing both Claude and Codex perspectives.
• code-janitorThe Ultimate Senior Fixer. Combines planning, specification, and coding into a single, high-speed execution mo
• code-kgBuilds and queries a SQLite+FTS5 knowledge graph over any codebase - import and dependency edges, symbols with
• code-knowledge-graphAI software team for Claude Code - 138 agents, 295 skills, 73 hooks. Self-learning, multi-agent swarm, autonom
• code-lintingRun Python (ruff) and JavaScript (Biome) linting.
• code-maturity-assessorSystematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmeti
• code-modeCode mode operational spec for the team lead. Returns lead identity, facilitator identity, mode-specific rules
• code-optimizerAnalyzes and optimizes code for better performance, memory usage, and efficiency. Use when code is slow, memor
• code-org-adoption-playbookA reusable playbook for adopting Claude Code across an organization, based on practices highlighted in Brex’s
• code-overviewProduces a human-readable, progressive-disclosure overview of unfamiliar code or a pull request's changes — wh
• code-overview-to-confluenceProduces a progressive-disclosure overview of unfamiliar code or a pull request's changes with code-overview a
• code-pattern-extractorAnalyze codebases to identify reusable code patterns, duplications, and implementation patterns for future dev
• code-planTurn a task description and repository into a structured implementation plan (files to create, files to modify
• code-plugin-basicsPackage and share Claude Code customizations using plugins, with a focus on when to use plugins and how to ins
• code-polishPRB's collection of agent skills
• code-polisherUse when refactoring messy code, improving readability, eliminating code smells, or applying SOLID/DRRY princi
• code-pr-review-loopTurn Claude Code Desktop into a tighter development loop: preview running apps, review local diffs before push
• code-pull-requestManage GitHub pull requests or GitLab merge requests: create, read/leave/respond to comments, and merge. Trigg
• code-qualityAgents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity
• code-quality-analyzerTriggered when the user submits code or requests a comprehensive code quality analysis. Automatically performs
• code-quality-guardCode police. Enforces automatic linting, formatting (Prettier/Black), static analysis, and architectural rules
• code-quality-guideUse when auditing existing code for quality WITHOUT changing it: a read-only pass that finds smells, grades th
• code-quality-lensCode quality review lens for evaluating design principles, error
• code-quality-principlesApplies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or revi
• code-quality-reviewRun an extremely strict maintainability and structural code quality review — flags abstraction issues, spaghet
• code-quality-reviewerReviews code and provides detailed quality assessment
• code-quality-trendsUse when checking code quality trends, tech debt accumulation, TODO/FIXME growth, test coverage ratios, PR siz
• code-readingUse this skill when navigating unfamiliar codebases, understanding legacy code, onboarding to a new project, o
• code-reconagent skills marketplace for mcp bundler(can be used with other ai tools with support of agent skills markepla
• code-refactorUse when refactoring Go code for better structure, maintainability, extensibility, or testability - follows SO
• code-refactoringUse when the user says 'refactor this', 'rename class', or 'move method'. Safely refactors code in any languag
• code-refactoring-advisorEnterprise code refactoring advisor that detects code smells, anti-patterns, and complexity issues with specif
• code-refactoring-assistantSuggest and apply code refactorings to improve readability, maintainability, and code quality. Use this skill
• code-refactoring-context-restoreUse when working with code refactoring context restore
• code-refactoring-refactor-cleanYou are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern sof
• code-refinerDeep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets comp
• code-remediateApply selected code-review fixes; rerun gates/report gaps; PR +review uses latest matching artifact.
• code-repair-generation-comboAutomatically repair buggy code and generate comprehensive tests for Python, Java, and C++ programs. Use when
• code-researcherScope-specific code gap analysis — extracts referenced codes from project docs, researches what should apply,
• code-reviewAnalyser du code modifie et lister les problemes en se basant sur les regles et conventions koulia.
• code-review-and-qualityConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, a
• code-review-assistAugments human code review by summarizing changes, surfacing key review questions, assessing test coverage, an
• code-review-assistantAnalyzes code changes for security vulnerabilities, performance issues, and maintainability concerns. Provides
• code-review-basicsA curated collection of Claude Code skills for SpoonOS development and Web3 integrations. 57 Python scripts ac
• code-review-checklistA ten-category human code-review rubric — correctness, design, readability, testing, security, performance, do
• code-review-cn中文代码审查清单与报告生成。当需要审查代码质量、进行 Code Review 时使用。
• code-review-cskCode review discipline: severity-ranked, reasoned feedback on whether a change improves the system's overall c
• code-review-cycleRun a full code review cycle on recent changes: lint auto-fix, three-agent quality review (reuse, quality, eff
• code-review-excellenceMaster code review best practices with constructive feedback patterns, quality assurance standards, review che
• code-review-expertExpert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risk
• code-review-fixUse when the user wants to address, action, or fix findings from a code review — their own working diff review
• code-review-gateArchitect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement
• code-review-githubGitHub PR workflow orchestration for code review — list PRs, post comments, apply labels, and guarded auto-mer
• code-review-guideUse when writing, structuring, or labelling code-review feedback on a pull or merge request: Conventional Comm
• code-review-guidelinesWhen asynchronously reviewing peer code before merging into the main branch.
• code-review-helperA safe skill that helps with code review tasks
• code-review-levelsReference documents for deep code review (Level 3) and architecture review (Level 4). Used by code-reviewer ag
• code-review-orchestration6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and
• code-review-passReview code for correctness, security, UX regressions, and project conventions. Use when reviewing PRs, self-r
• code-review-patternsMulti-dimensional code assessment across security, quality, performance, and maintainability with confidence-g
• code-review-pipelineMulti-dimensional code review across correctness, security, performance, and maintainability with confidence-g
• code-review-preflightUse when the user asks for a pre-PR review or self-review of code they've written. Triggers on phrases like "r
• code-review-proComprehensive code review covering security vulnerabilities, performance bottlenecks, best practices, and refa
• code-review-receptionReceive and act on code review feedback with technical rigor. Use when you receive code review comments on a P
• code-review-reportTurn code changes into a single-file HTML code review report that pairs the diff with context a diff can't sho
• code-review-responseProcess code-review feedback with technical rigour — understand each point, check it against the actual codeba
• code-review-self提交/交付前自我代码审查时使用。像 reviewer 一样挑自己的刺。
• code-review-standardsDiscover and apply organization coding standards from .forge-review/ configuration
• code-review-webReview web application code for bugs, security issues, performance problems, and stack-specific anti-patterns.
• code-reviewingReview code for quality, security, and best practices. Use when the user asks for code review, wants feedback
• code-roadmapOrientation map for the start of a coding task. Reads your intent, matches it against the skills currently ava
• code-runnerExecutes code snippets by saving them to a temporary file and running them via bash commands (e.g., node, pyth
• code-saurabh-autoplanAutomated full review pipeline skill. Use when the user wants to run a complete plan review in one command, au
• code-saurabh-benchmarkPerformance benchmarking skill — baseline and compare page load times, Core Web Vitals, bundle sizes, and API
• code-saurabh-brand-guidelinesApply brand voice, tone, colors, typography, and visual style consistently across any artifact. Use when the u
• code-saurabh-code-reviewerReview code changes for bugs, security issues, performance problems, and style before shipping. Use when the u
• code-saurabh-commit-messageWrite clean Conventional Commits messages and pull request descriptions from staged changes or diffs. Use when
• code-saurabh-doc-coauthoringStructured co-authoring workflow for PRDs, design docs, RFCs, decision docs, proposals, and any substantial wr
• code-saurabh-frontend-designDesign and implement distinctive, production-ready web interfaces. Use when creating or substantially redesign
• code-saurabh-internal-commsWrite clear, well-structured internal communications — incident reports, post-mortems, launch announcements, t
• code-saurabh-mcp-builderBuild production-grade MCP (Model Context Protocol) servers that connect AI agents to external APIs, databases
• code-saurabh-office-hoursPre-code ideation and startup validation skill. Use when the user wants to validate a product idea, stress-tes
• code-saurabh-pdfRead, extract, create, merge, split, and manipulate PDF files. Use whenever a .pdf file is involved — extracti
• code-saurabh-plan-eng-reviewEngineering plan review skill — architecture, data flow, edge cases, and test plan before coding begins. Use w
• code-saurabh-pptxCreate, edit, read, and design PowerPoint presentations (.pptx). Use whenever a .pptx file is involved — creat
• code-saurabh-prompt-engineerDesign, iterate, test, and version prompts for LLMs — system prompts, few-shot examples, chain-of-thought, str
• code-saurabh-skill-creatorCreate new skills, improve existing skills, and test skill quality. Use when the user wants to build a skill f
• code-saurabh-technical-writerWrite, structure, and maintain all forms of technical documentation — READMEs, API docs, runbooks, architectur
• code-saurabh-theme-factoryGenerate and apply complete design themes — color palettes, typography pairings, and spacing systems — to any
• code-saurabh-webapp-testingAutomated end-to-end web application testing using Playwright. Use when the user wants to write automated test
• code-saurabh-xlsxCreate, read, edit, and analyse Excel spreadsheet files (.xlsx, .xlsm, .xltx, .csv, .tsv). Use whenever a spre
• code-searchSearch code symbols, find function calls, and analyze codebase
• code-search-assistantSearch code repositories for code related to a given code snippet, ranking results by call chain similarity, t
• code-securitySecurity guidelines for writing secure code. Use when writing code, reviewing code for vulnerabilities, or ask
• code-simplificationUse when refactoring code for clarity without changing behavior. Use when code works but is harder to read, ma
• code-simplifierUse when user asks to simplify, clean up, or refactor recently modified code for readability, consistency, or
• code-simplifySimplify working code without changing behavior — reduce complexity, remove dead abstractions, favor clarity o
• code-slopDetect AI-generated code patterns ("slop") in PHP/Laravel and TypeScript/React source — comment narration, gen
• code-slop-reviewReview code quality across multiple layers and report issues clearly.
• code-smell-detectorIdentify and report code smells indicating poor design or maintainability issues in Python code, including dup
• code-span-exampleA skill whose body demonstrates markdown link syntax inside inline code, to make sure the reference checker do
• code-standardsApply a disciplined engineering workflow to any code change. Use whenever implementing a feature, fixing a bug
• code-standards-adopterInfers a codebase's implicit coding conventions (naming, structure, imports, comments, error handling) by anal
• code-statsAnalyzes code files and reports statistics including line counts, file counts by extension, and total size. Us
• code-structureLanguage-agnostic structural craft -- decompose on responsibility not size, prefer deep modules over shallow p
• code-style程式碼風格規範。定義命名慣例、格式化規則、import 排序等。 所有開發類 agent 應注入此 skill。
• code-style-lintDiscipline for code style and static analysis, adopt the ecosystem's established formatter as the non-negotiab
• code-subagentsImplementation subagent dispatch patterns. Use when independent implementation work is available and subagents
• code-submitCross-platform code submission workflow - Lint check, non-destructive review, manual verification document, sm
• code-summarizerGenerate concise summaries of source code at multiple scales. Use when users ask to summarize, explain, or und
• code-synthesizerSynthesizes exploration findings into unified analysis with deep investigation capabilities and completeness e
• code-teacherInteractive code-learning workflow for AI coding agents and CLI assistants. Use when the learner wants to deep
• code-team-playbookA practical playbook of Claude Code usage patterns across teams (navigation, testing, debugging, prototyping,
• code-testing-agentGenerate or add unit tests for existing code, from one function to a complete project-wide suite. ALWAYS USE w
• code-testing-extensionsProvides file paths to language-specific extension files for the code-testing pipeline. Call this skill to dis
• code-that-fits-in-your-headSoftware-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-
• code-to-contentUse when transforming a codebase into developer content. Activates for: - Blog posts, tutorials, or technical
• code-to-imageGenerate beautiful code snippet images with syntax highlighting. Use when users want to share code as an image
• code-to-prd345 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable re
• code-to-specReverse-engineer a SPEC document from an existing project. Analyzes code, config, tests, and structure to prod
• code-tourUse when a user asks for a code tour, onboarding walkthrough, architecture tour, or PR tour — creates persona-
• code-transferTransfer code between files with line-based precision. Use when users request copying code from one location t
• code-translationConvert code between programming languages while preserving functionality and semantics. Use when: (1) Transla
• code-ultrareviewEight-axis judgment code review for the current diff — Correctness, Simplification, Tests, Documentation, Styl
• code-understandBuild a ranked, citation-backed focus map of a codebase — the files and symbols an architecture actually hangs
• code-understandingProvides adversarial code comprehension for security research, mapping architecture, tracing data flows, and h
• code-verificationPost-implementation verification system that catches AI-introduced bugs. Covers 7 categories — TDZ errors, imp
• code-walkthroughWalks a person through code changes one step at a time in conversation, starting at the entry point and follow
• code-with-beto-shipScaffold production-ready React Native apps using the @codewithbeto/ship CLI. Use when the user wants to creat
• code-writingWrite clean, correct, production-quality code.
• code-yeongyu-agent-browserAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the u
• code-yeongyu-debuggingMUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong respon
• code-yeongyu-frontendMUST USE for frontend/web UI/UX/visual work: building, styling, redesigning pages/components, React setup, per
• code-yeongyu-github-triageRead-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open it
• code-yeongyu-refactorIntelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modern
• code-yeongyu/oh-my-openagentomo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For you
• codeact-installInstall or reconfigure codeact. Auto-detects best backend (monty or hyperlight), runs preflight checks, discov
• codeact-install-hyperlightSwitch codeact to the Hyperlight backend (micro-VM sandbox via WebAssembly, stronger isolation). Use when user
• codeact-install-montySwitch codeact to the Monty backend (Pydantic Monty — minimal Python interpreter in Rust, sub-microsecond star
• codeaholicguy-changelogAI DevKit · Update CHANGELOG.md Unreleased items from git commits since the latest release. Use when users ask
• codeaholicguy-dev-implementationAI DevKit · Implementation phase guidance for executing feature plans and checking implementation against desi
• codeaholicguy-security-reviewAI DevKit · Review code, skills, and prompts for security vulnerabilities — OWASP Top 10, prompt injection, bu
• codeaholicguy-tddAI DevKit · Test-driven development — write a failing test before writing production code. Use when implementi
• codeaholicguy-technical-writerAI DevKit · Review and improve documentation for novice users. Use when users ask to review docs, improve docu
• codeaholicguy-verifyAI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success.
• codealive-ai-copywritingWrite, rewrite, or improve marketing copy for any page — homepage, landing pages, pricing pages, feature pages
• codealive-ai-email-sequenceCreate or optimize email sequences, drip campaigns, nurture flows, onboarding emails, welcome series, re-engag
• codealive-ai-seo-auditAudit, review, or diagnose SEO issues on the site. Use for "SEO audit," "technical SEO," "why am I not ranking
• codealive-ai-ubiquitous-languageMaintain a project thesaurus (domain glossary) following DDD ubiquitous language principles. Use PROACTIVELY w
• codealive-context-engineSemantic search, grep, and Q&A across codebases and documentation indexed in CodeAlive. Use when the user ment
• codebanana-skill-guideComplete specification for Skill development and management. Use this skill for CRUD operations on Skills. Tri
• codebase-advisorSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER
• codebase-analysisProduce a structured codebase analysis report with architecture overview, critical files, patterns, and action
• codebase-analyzerStatistical rule discovery from Go codebase patterns.
• codebase-architectureDesigns, deepens, and hardens TypeScript codebase architecture in three modes: folder structures, module contr
• codebase-argusPortable Codebase Argus agent playbook for evidence-first multi-agent review of GitHub pull requests, CI failu
• codebase-audit全面代码库审计 — 自适应并行深度分析（前后端契约、数据完整性、异常处理/安全、架构/技术债、配置/缓存），结构化 findings + 对抗验证 + 基线对比，输出按严重程度排序的统一报告和修复路线图。支持 quick
• codebase-cleanup-tech-debtYou are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in s
• codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interfac
• codebase-documenterGenerates comprehensive documentation explaining how a codebase works, including architecture, key components,
• codebase-healthScore your codebase 0-100 across complexity, coupling, cohesion, test coverage, documentation, churn hotspots,
• codebase-indexGenerate a pre-computed component index from a design system codebase — YAML infrastructure files containing a
• codebase-insightWhen the user wants to deeply understand a codebase, map its architecture, or build a persistent mental model
• codebase-inspectionInspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios.
• codebase-intelUnified codebase intelligence. Handles all questions about structure, logic, risk, and dependencies. Combines
• codebase-mappingAutomatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry poi
• codebase-memory-mcpUse when a configured codebase-memory-mcp server can assist with graph-backed code discovery, architecture ori
• codebase-migrationFour-phase skill for planning and executing large-scale codebase migrations using full-context AI analysis. Pr
• codebase-onboardingUse when entering a new codebase, needing a fast architecture map, or generating onboarding notes from an unfa
• codebase-orientationMaps an unfamiliar or large codebase before implementation by locating entry points, ownership, execution path
• codebase-overviewSystematic codebase exploration and architecture mapping.
• codebase-reconReconstruct a repository as cited
• codebase-summarizerScans repository structure and generates comprehensive architecture documentation including system overview, e
• codebase-syncConvention discovery and rule generation from codebase analysis. Scans project structure, builds search indexe
• codebase-to-courseTurn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non
• codebase-visualizerGenerate an interactive tree visualization of your codebase. Use when exploring a new repo or understanding pr
• codebase-wikiHow to work in a Codebase Wiki project (the `codebase-wiki` starter pack): an agent-authored, source-grounded
• codeception-testingExpert-level Codeception testing skill for PHP applications. Covers acceptance, functional, and unit testing w
• codeckcodeck entry point. Scans local files for materials, shows pipeline dashboard with diagnostic intelligence, gu
• codeck-designDesigner role. Reads deck.md, generates a single HTML presentation file with CSS design system + JS slide engi
• codeck-exportInternal publisher module for /codeck. Exports deck to PDF or PPTX with post-export QA. User-facing export req
• codeck-outlineEditor role. Reads local materials, asks narrative questions, plans story arc. Outputs $DECK_DIR/deck.md as th
• codeck-reviewReviewer role. Opens rendered HTML, inspects every slide visually, fixes problems in custom.css or slides.html
• codeck-speechInternal speech module for /codeck. Reads deck content, asks about style and duration only when missing, gener
• codedrobe-adapter-devAdd, inspect, repair, or validate CodeDrobe Core adapters for Chromium/Electron AI desktop applications. Use w
• codedrobe-themeCreate, inspect, convert, apply, replace, verify, troubleshoot, update, publish, or restore reversible CodeDro
• codegen-htmlScaffold and iterate on standalone Preact + HTM applications with zero build dependencies
• codegen-reactScaffold and iterate on Vite + React applications
• codegen-validationUse when building or debugging a compiler backend, codegen, or assembler and you need to prove the generated m
• codegraph-usageHow to use CodeGraph well — which tool answers which question, when to reach for it and when not, and the gotc
• CodeGraphContext/CodeGraphContextAn MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistant
• codeium-ui-skillsCodeium's UI design system. Use when building interfaces inspired by Codeium's aesthetic - dark mode, Inter fo
• codely-doc-createCreate new documentation based on the current conversation context.
• codely-git-conventional-commitCreate a git commit following the team's Conventional Commit conventions. Use when the user asks to commit cha
• codely-plan-create-githubCreate a plan for the specified task and store it as GitHub issues in the repository of the current working di
• codely-plan-create-subagentsCreate a plan for the specified task.
• codely-plan-phase-implementImplement one phase of the plan specified by the user. Only implements a single phase per invocation, then sto
• codely-plan-phase-implement-githubImplement one phase of a plan stored as GitHub issues in the repository of the current working directory. Give
• codelytv-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• codelytv-testingTesting conventions and patterns. Use when writing or modifying tests, creating mocks, or using object mothers
• codemapMantém o CODEMAP.md — o índice de todo arquivo de código do projeto com uma linha sobre o núcleo de cada um, p
• codemod-generatorGenerate codemods (automated code transformation scripts) for design system migrations — token renames, compon
• codenavUnified code-navigation doctrine combining four persistent tools on four distinct axes — qdrant (memory/time),
• codenaviYour pathfinder for navigating unknown codebases. Investigates with precision, implements surgically, and neve
• codeqlCodeQL operational workflow — discover/config, run/inspect, triage SARIF findings (rule/query ID, source→sink,
• codeql-security-analysisAdvanced security analysis using GitHub CodeQL to find zero-day vulnerabilities, injection flaws, and security
• codeql-security-scanner用于通过 CodeQL 执行语义代码扫描、安全查询、自定义规则、SARIF 报告和 GitHub Code Scanning 集成。
• coderWrite, edit, and refactor code with full tool access - Use when you need to actually write or modify code, cre
• coderabbit-autofixSafely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execu
• coderabbit-code-reviewAI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AN
• coderabbitloopIteratively drives a GitHub PR to zero unresolved CodeRabbit (coderabbitai[bot]) findings. Reads each inline c
• codereviewMulti-lens pull request review.
• CoderGamester/mcp-unityModel Context Protocol (MCP) plugin to connect with Unity Editor — designed for Cursor, Claude Code, Codex, Wi
• codesearch-installInstall flupkede/codesearch — a local Rust MCP server for multi-repo semantic code search (vector + BM25 hybri
• codeshux-mockhunterAudit a live web page to find mock data, hardcoded values, LLM-fabricated metrics, and broken endpoints. Opens
• codeshux-tokenwiseInstall TokenWise routing rules into the user's Claude Code config (CLAUDE.md and settings.json). Probes the u
• codesplainUse when working in a coding project owned by a non-coder - when the project root contains CODESPLAIN.md, when
• codestyleCoding standards and formatting for Maven/Java projects using spring-javaformat and Checkstyle. Use when the u
• codetreker/blueprintflowBlueprintflow - Multi-agent collaboration workflow skills
• codexOpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail g
• codex-abRun an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, live
• codex-advisorThis skill should be used when the user asks for a "GPT second opinion", wants a "cross-model review", needs t
• codex-agentUse when you want a second-opinion review via Codex CLI, cross-verification after another agent implements cha
• codex-agent-collaborationDelegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a
• codex-architectCodex architecture consulting. Use when: designing features, evaluating architecture, getting second opinion o
• codex-autoresearchRun or resume a measured improvement loop in a local project. Use for benchmark-driven optimization, qualitati
• codex-brainstormAdversarial brainstorming via Claude+Codex debate. Use when: exploring solutions, feasibility analysis, exhaus
• codex-ccDelegates coding tasks from Codex to local Claude Code in print mode while preserving Claude's normal runtime
• codex-claude-pmCodex as product manager and reviewer for delegating coding implementation to Claude Code. Use when the user w
• codex-cliInteract with OpenAI Codex CLI for plan review, code review, and complex problem discussion. Supports either C
• codex-cli-bridgeBridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execu
• codex-cli-reviewCode review via Codex CLI with full disk access. Use when: deep review needing full codebase read, uncommitted
• codex-cli-rulesOperational rules for driving Codex CLI from scripts: success-signal contract, diff-feeding semantics, worktre
• codex-cli-specialistOpenAI Codex CLI and cross-platform skill authoring. Use when setting up Codex CLI, converting or syncing skil
• codex-code-reviewCode review using Codex MCP. Use when: PR review, code audit, second opinion on changes. Not for: doc review (
• codex-collabUse when the user asks to invoke, delegate to, or collaborate with Codex on any task. Also use PROACTIVELY whe
• codex-coordinationCoordinate multiple Codex instances across machines. Use when a machine needs to check for, discuss, decide, o
• codex-deadA fixture Codex skill that is installed but never invoked.
• codex-delegateDelegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it y
• codex-discussIterative non-code discussion between the local agent and Codex CLI on any open-ended topic: diet, fitness, wr
• codex-docs-drift-scoutInstall the AutoHub docs-drift Codex automation from signed AutoVault skill resources and audit its render fid
• codex-env-config记录、迁移和排查 Codex CLI 环境配置。适用于 Codex 安装升级、订阅制认证、代理注入、Homebrew、skills 同步及远端环境适配。