Skills de Claude Code · página 71

Guides Docker, CI/CD pipelines, deployment strategies, infrastructure as code, and observability setup. Use when writing Dockerfiles, configuring GitHub Actions, planning deployments, setting up monitoring, or when asked about containers, pipelines, Terraform, or production infrastructure.

Implements error handling patterns, structured logging, retry strategies, circuit breakers, and graceful degradation. Use when designing error handling, setting up logging, implementing retries, adding error tracking, or when asked about error boundaries, log aggregation, alerting, or resilience patterns.

Manages Git workflows including branching, commits, and pull requests. Use when working with Git, creating commits, opening PRs, managing branches, resolving conflicts, or when asked about version control best practices.

Analyzes and optimizes application performance across frontend, backend, and database layers. Use when diagnosing slowness, improving load times, optimizing queries, reducing bundle size, or when asked about performance issues.

Patterns for parallel subagent execution using Task tool with run_in_background. Use when coordinating multiple independent tasks, spawning dynamic subagents, or implementing features that can be parallelized.

Implements authentication, authorization, encryption, secrets management, and security hardening patterns. Use when designing auth flows, managing secrets, configuring CORS, implementing rate limiting, or when asked about JWT, OAuth, password hashing, API keys, RBAC, or security best practices.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", "check my site against best practices", or "web interface guidelines".

TAKT ワークフローエンジン。Agent Team を使ったマルチエージェントオーケストレーション。ワークフロー YAML（steps / initial_step）に従ってマルチエージェントを実行する。

The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.

NoPUA Lite — core wisdom in ~1.5k tokens. Drives AI with trust and inner motivation instead of fear. Same Daoist philosophy, minimal footprint. For personal use and small-context models.

The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures.

|

|

Manual-only skill that creates bounded execution authority from an explicit operator grant. Never auto-trigger or infer approval from prompt text or tool schemas.

Compare two or more existing candidates under an explicit characteristic space, parity basis, and predeclared selection policy. Return trade-offs and a non-dominated set; persistence is conditional and a binding choice requires a direct unambiguous operator request.

Route one direct, unambiguous operator request for a bounded binding choice. A manual h-decide invocation is a compatible shortcut, not an authorization receipt.

Diagnose a concrete failure with rival-hypothesis testing. Stabilize the symptom, generate distinct explanations, test discriminating observations read-only in parallel, and rank by evidence while retaining losing rivals.

Generate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each visible. May work from an inline question or a durable ProblemCard; persistence is conditional.

Shape an under-articulated engineering problem without assuming a solution or forcing a project phase. Default to a conversational frame; create a ProblemCard only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs a durable accepted problem statement.

Persist an explicitly requested non-binding fact, observation, caveat, or small rationale in Haft project memory. Do not auto-persist ordinary reasoning.

Bootstrap Haft through the readable task-level onboarding surface, prepare a non-binding project-profile review when needed, and orient only applicable typed spec carriers. Project memory is ready immediately after haft init; profile apply and lifecycle gates remain human.

Source-first umbrella for FPF-aware reasoning in a Haft project. Use for ambiguous engineering, management, architecture, specification, or project questions when no narrower Haft capability is already current. Ordinary reasoning stays conversational; persistence is conditional and binding actions remain manual.

|

Manage Haft's typed spec lifecycle, source-currentness, carrier edits, and semantic fanout repair. Treat markdown as a carrier and kernel lifecycle plus explicit human gates as authority.

|

Read-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module coverage, and bounded exact file-link gaps from a current code index. Use for project status, session resumption, what is decision-linked, what is uncovered, or what needs attention.

Verify that a recorded DecisionRecord or claim still holds by comparing its baseline and predictions with current code, tests, measurements, or incidents. Keep design-time claims distinct from runtime evidence.

Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<collection>/STYLE_ID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx. Use when the user asks to make a presentation, slides, deck, pitch deck, investor PPT, magazine-style PPT, or 做一份 PPT / 生成幻灯片 / 用 gpt-image 生成 PPT / 按这个模板生成 PPT.

Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.

Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture choices, contract changes, or when grilling/pressure-testing a plan or design. Routine small requests stay on the fast path.

Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.

Use when facing 2+ independent tasks without a written plan, with no shared state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.

Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.

Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture direction risk. Ordinary bug fixes stay on the fast path.

Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.

Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.

Use when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync after architecture-changing work.

Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.

Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents.

Use when encountering a bug, test failure, or unexpected behavior, before proposing fixes

Use when the user explicitly requests strict or test-first TDD, or when the current conversation already contains an explicit `TDD Route: strict` decision from another Aegis workflow.

Use when the user says `aegis:update`, asks to update or upgrade an installed Aegis method-pack, wants the latest Aegis version, or asks whether Aegis is current on this host.

Use when starting a turn or checking Aegis skill routing.

Use when a coding task needs a concurrent checkout, unrelated dirty state blocks safe branch switching, or the user or repository explicitly requires a worktree.

Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.

Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code. Small, single-owner, or fast-path tasks do not need this skill.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.

Use when multiple workflows duplicate the same operational logic, when deciding what belongs in actions vs shared services, or when refactoring repeated operational blocks across domain flows. Use when adding new features that share mechanics with existing ones.

>

>

>

Start a new task in an isolated Git worktree branched from origin/main so multiple agents can work on the same repo in parallel without conflicts. Use at the beginning of every new feature, fix, or task — before writing any code.

>

>

Set up the Switch connector for Codex — register this Codex instance as a Switch agent and write the credentials the bundled MCP server reads. Use when the user asks to configure Switch, set up the plugin, register with a Switch server, or when the Switch tools report no identity.

How to take part in a Switch room. Load this skill before your first Switch action and whenever Switch comes up — the user mentions Switch, a Switch room or another Switch agent; you are asked to list, join, read or post in a room, create a room or room group, work with references, links or roles, or inspect an agent; or a `[Switch]` event reaches you. Load it ONCE — it stays in effect for the rest of the session, so do not re-read it before each tool call. Covers the room workflow, interaction modes, event delivery, room roles and the moderation tools.

SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence, and interactively forge the chosen ones into skills installed across all your agent harnesses. Use when the user wants to turn past AI coding sessions into reusable skills, asks "what could I make into a skill", "mine my lore", "forge skills from my history", or points at a .specstory/history directory.

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still an open loop, and what was just started. Use when someone asks "what happened this week", "what is still open", "what did the team finish", "give me the weekly rollup", or wants a status report over a .specstory/history corpus.

>

oh-my-agent 单领域任务的详细指南。何时使用、预检清单、带说明的提示模板、前端/后端/移动端/数据库的真实示例、预期执行流程、质量关卡检查清单和升级信号。

>

Academic writing capability for publication-grade English prose.

Architecture specialist for software/system design, module and

Backend specialist for APIs, databases, authentication with clean

Design-first ideation that explores user intent, constraints, and

Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents

Database specialist for SQL, NoSQL, and vector database modeling,

Bug diagnosis and fixing specialist - analyzes errors, identifies

Drive Vercel's `deepsec` agent-powered vulnerability scanner

AI design specialist skill with DESIGN.md management, anti-pattern

Use when setting up or optimizing developer workflows in a

Verify documentation references against the current codebase,

Turn a code change (diff, PR, branch, commit range) into a rich,

Frontend specialist for React, Next.js, Angular, TypeScript with

Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts

Multi-vendor AI image generation with authentication-aware parallel

Market research skill for pain-point extraction, trend detection,

Mobile specialist for Flutter, React Native, and Swift native iOS

Intent-based observability + traceability router across layers,

Automated multi-agent orchestration that spawns CLI subagents in

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress. Use for orchestration, parallel execution, and automated multi-agent workflows.

>

Product manager that decomposes requirements into actionable tasks with priorities and dependencies. Use for planning, requirements, specification, scope, prioritization, task breakdown, and ISO 21500, ISO 31000, or ISO 38500-aligned planning recommendations.

Quality assurance specialist for security, performance, accessibility, comprehensive testing, and quality standard alignment. Use for test, review, security audit, OWASP, coverage, lint work, and ISO/IEC 25010 or ISO/IEC 29119-aligned QA recommendations.

Analyze conversation histories from multiple AI tools (Claude, Codex, Gemini, Qwen, Cursor) and generate themed daily/period work summaries. Filter by date or time window.

Behavior-preserving refactoring specialist - plans and executes safe incremental restructuring with code smell / SATD / hotspot targeting, characterization-test safety nets, metric and coverage gates, and refactor-only commits. Use for refactor, refactoring, code smell, technical debt, legacy code modernization, extract method, hotspot, and characterization test work.

>

SCM (software configuration management) and Git — branching, merges, conflicts, worktrees, baselines, audit readiness, plus Conventional Commits and safe staging.

Intent-based search router with trust scoring. Routes queries to optimal channels (Context7 docs, native web search, gh/glab code search, Serena local) and attaches domain trust labels. Use for search, find, lookup, reference, docs, code search, and web research.

>

>

HTML presentation deck generator and multi-format exporter. Generates distinctive, animation-rich HTML decks at a fixed 1920×1080 stage, then deterministically validates, bundles, and exports them to PDF/PNG/PPTX via the `oma slide` CLI. Use for slide, deck, presentation, slides, pptx, keynote, 슬라이드, 발표자료, プレゼン, 幻灯片 requests. Produces self-contained single-file HTML with keyboard/touch nav, speaker notes, and print-to-PDF support.

Infrastructure-as-code specialist for multi-cloud provisioning using Terraform across any provider (AWS, GCP, Azure, Oracle Cloud). Use for terraform plan/apply, state management, compute, databases, storage, networking, IAM, OIDC, cost optimization, policy-as-code, ISO/IEC 42001 AI controls, ISO 22301 continuity, and ISO/IEC/IEEE 42010 architecture documentation.

Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.