Skills de Claude Code · página 128

Map testable surfaces, audit existing tests for quality, and write test specifications that prevent AI shortcuts. Use when asked to "audit tests", "specify tests", "test architect", "map test coverage", or invoke /test-architect. Two modes — audit (evaluate existing tests against Beck's principles) and specify (write test specs for new code). Powered by Carmack × Beck quality-testing.md reference doc. Stack: Next.js App Router / TypeScript / Vitest / Cypress / tRPC / Prisma / Neon.

CRISP Execute — Sprint execution loop with change request management, security gates, product gates, and stakeholder reporting. Use after Phase S (Spec) is complete and crisp-state.json shows ready_for_execute: true. Triggers on "start sprint", "begin build", "execute", "sprint 1", "run sprints", or when handed off from crisp-orchestrator.

CRISP session manager — detects project state and routes to the right entry point. Use /crisp to start or resume any CRISP engagement. Handles new projects (discovery), existing codebases (archaeology), active sprints (execute), and validation (prove). Reads docs/crisp-state.json to know where you are.

Generate a beautiful single-file HTML report from the project's docs/ folder. Works after any CRISP phase, after Archaeology, or at sprint close in Execute. Triggers on "generate report", "export docs", "create HTML report", "share docs", or automatically at sprint close in CRISP Execute.

Begin a CRISP product discovery session — Phase C (Clarify)

The Mileva Method (CRISP) — Phase 1: Clarify. Problem definition, eliciting, painkiller test, buy vs build, AI justification gate, Go/No-Go. Use at the start of any AI implementation project. Triggers on "clarify", "phase 1", "start discovery", "define the problem", "what problem are we solving", or at the beginning of a new client engagement.

The Mileva Method (CRISP) — Phase 2: Results. Outcome alignment, stakeholder register, baseline measurement, success metrics, tradeoff negotiation. Use after problem definition is complete. Triggers on "results", "phase 2", "define success", "success metrics", "what does done look like", or after Phase C exit checklist is complete.

The Mileva Method (CRISP) — Phase 3: Investigate. Process mapping for existing or greenfield processes, user journey mapping, UX discovery, project goals, system architecture (integration map + data flow). Use after outcome alignment. Triggers on "investigate", "phase 3", "map the process", "process mapping", "user journey", "as-is process", or after Phase R exit checklist is complete.

The Mileva Method (CRISP) — Phase 4: Spec. Full implementation readiness package including solution design, UX direction, tech stack, backlog, MVP prioritization, risk assessment, and AI architecture for Claude Code projects — CLAUDE.md, skill mapping, AI specs, sprint planning, quality gates. Triggers on "spec", "phase 4", "build ready", "implementation plan", "CLAUDE.md", "sprint planning", "backlog", "AI spec", or after Phase I exit checklist is complete.

The Mileva Method (CRISP) — Phase 5: Prove. Success validation against Phase R baseline metrics, test log review, and AI justification validation. Use after deployment. Triggers on "prove", "phase 5", "validate", "did it work", "success criteria", "measure results", or after go-live.

[One sentence — what this agent does and when it's triggered. Be specific enough that Claude can decide whether to invoke it.]

Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.

Explain how an OpenHermit agent behaves for the people interacting with it — owners, users, and guests. Covers roles, identity linking, the agent's tools, access levels, channels, the policy model, and the approval flow. Use when someone asks how an OpenHermit agent works from a caller's perspective. For deploying or administering the platform itself, see openhermit-admin.

Create, structure, and validate new skills. Use when designing a skill, scaffolding a skill directory, or improving an existing skill.

HX Audio Player for music and sound playback. Use when implementing music playback, sound effects, HXMusic, HXSound, or audio in HXAudioPlayer. Library is in the hxaudio module.

기존 근로계약서의 근로조건을 변경할 때 사용하는 근로조건 변경 합의서 자동 작성 스킬. 임금·근무장소·업무내용·근무시간 변경, 5인 미만/이상 분기, 2026년 최저임금 10,320원 검증 포함.

일용근로자(일당제·건설·배달·행사 스태프 등) 근로계약서 자동 작성 스킬. 일당·시급 검증, 1일 단위 계약, 4대보험(고용보험 1개월·건강보험 1개월 기준), 노무비 원천징수(2.7%), 2026년 최저임금 10,320원 반영.

한국 사업자를 위한 근로계약서 자동 작성 스킬. 주40시간 정규직·계약직, 근로기준법 §17 필수 기재 항목, 2026년 최저임금(10,320원/시), 4대보험 의무를 반영. 5인 이상/미만, 수습기간, 고정OT, 포괄임금제 지원.

유연근무제(탄력근로·선택근로·재택근무) 적용 근로계약서 자동 작성 스킬. 근로기준법 §51·§52 서면합의 요건, 5인 이상/미만 분기, 2026년 최저임금(10,320원/시) 자동 검증.

개인 프리랜서·1인 사업자와의 용역 계약서 자동 작성 스킬. 민법 위임·도급 규정, 3.3% 원천징수, 지식재산권 귀속 조항을 반영한 프리랜서 계약서 초안 생성.

한국 사업자용 계약서 작성 진입점 스킬. 시작하자마자 9개 하위 스킬을 번호 메뉴로 제시하고, 번호 입력 즉시 해당 스킬 인터뷰로 직행한다.

법인·사업체 간 외주용역 계약서 자동 작성 스킬. 민법 도급 규정, 하도급법, 불법파견 방지 조항을 반영한 외주용역 계약서 초안 생성.

단시간 근로자·아르바이트용 근로계약서 자동 작성 스킬. 카페·편의점·일반 업종 지원, 주15시간 이상/미만 분기, 2026년 최저임금(10,320원/시) 자동 검증, 5인 이상/미만 분기, 주휴수당 자동 계산.

연봉 갱신 시 사용하는 연봉계약서 자동 작성 스킬. 기본급·수당·연봉 총액 명시, 2026년 최저임금 10,320원 검증, 고정OT 포함 포괄임금제, 5인 미만/이상 분기 지원.

Systematic logic error isolation.

Auditing for unsafe code and secrets.

Basic syntax error resolution.

Debugging compiler errors and tracing lifetimes.

Generating PEG parsers with pest.

Managing configuration and serialization.

Analyzing user intent and delegating tasks.

Implementing idiomatic, safe, and performant Rust code.

Model selection strategy and routing. Use when choosing between models for different task types, subagent configurations, or optimizing token cost vs quality tradeoffs.

RESTful API design patterns and best practices. Use when creating endpoints, designing APIs, or implementing routes.

Architecture design skill: ADR records, system design checklists, scalability assessment, architecture patterns. Use for complex system design and architecture decisions.

Backend development patterns for services, error handling, logging, caching. Use when building backend services, APIs, or microservices.

Strategic compaction skill: suggests context compression at logical breakpoints. Use to suggest compaction at logical intervals during development sessions.

Database design, query optimization, migrations, and indexing. Use when designing schemas, writing queries, or managing migrations.

Systematic debugging methods, log analysis, and performance diagnostics. Use when debugging issues, analyzing errors, or troubleshooting incidents.

DevOps patterns: containerization, CI/CD, deployment strategies, monitoring. Use when containerizing apps, setting up pipelines, or deploying services.

Code exploration strategies for understanding unfamiliar codebases. Use when exploring unknown code, debugging, or analyzing architecture.

Frontend patterns: component design, state management, performance, accessibility. Use when building web frontends, components, or client-side apps.

Git version control best practices: branching, commits, merging, conflict resolution, PR workflows. Use when managing branches, creating commits, merging code, or resolving conflicts.

Extracts reusable patterns from sessions. Use at session end to capture debugging insights and project-specific knowledge.

Native app development strategies including iOS/macOS (Apple platforms), Tauri desktop apps. Use when developing native mobile or desktop applications.

Code quality assurance strategies. Parent skill for quality-related skills: security (security review) and debug (systematic debugging).

Research-before-coding workflow: systematically search existing solutions before custom implementation. Use when introducing new libraries, tools, or solving unfamiliar problems.

Cross-validate code, architecture or design decisions using a second model. Use for critical decisions, complex refactoring, security reviews.

Session lifecycle management. Parent skill for session-related skills: learning (pattern extraction) and compact (context compression).

Testing strategies and methodologies including TDD and E2E testing. Use when writing tests, implementing TDD workflow, or setting up E2E test infrastructure.

Use when brainstorming a product or feature where multiple valid technology choices exist and the wrong one is costly, when the user asks for 'objectively best' or 'highest quality', or when the domain has tools/frameworks where marketing or popularity biases could mislead research agents. Also use when starting architecture decisions, evaluating tech stacks, or when the user mentions bias, vendor lock-in, hallucinated benchmarks, or wants research-backed decisions rather than default recommendations.

Use when creating or editing documents (DOCX, PDF, XLSX, PPTX) that need professional output. Adds visual verification, typography hygiene, and formula patterns.

Advanced python-docx patterns for nested tables, complex cells, and content extraction beyond .text property. Techniques for forms, checklists, and complex layouts.

Fill DOCX template forms preserving 100% original structure - logos, footers, styles, metadata. Zero-artifact insertion. Output indistinguishable from manual entry.

Use when adding/editing/querying content in an existing Obsidian vault, configuring plugins, integrating Claude Code with Obsidian via Local REST API or CLI, automating ongoing capture/organization/retrieval, designing a personal knowledge management workflow, OR building academic study vaults (course prep, exam-ready, mock-exam content — the durable academic-study patterns from a deprecated companion skill have been folded into this one).

Extract PDFs to text and images before reading

>-

Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.

>-

Translate DOCX to RTL languages (Arabic, Hebrew, Urdu) preserving exact formatting, tables, colors, layouts. Handles quote normalization and multi-pass matching.

Provides the complete content of 'The Swift Programming Language (6.3)' book by Apple. Use this skill when you need to verify Swift syntax, look up language features, understand concurrency, resolve compiler errors, or consult the formal language reference.

>

Audit and improve an existing Quickstop plugin's quality against Claude Code plugin spec

Scaffold a new Quickstop plugin with correct structure and conventions

Full multi-phase audit of Claude Code configuration (dispatches research + audit subagents, edits files, may open a PR). Run only when the user explicitly asks to audit or optimize their Claude Code setup.

Retrieve claudit knowledge cache domains (ecosystem, core-config, optimization). Checks freshness and auto-refreshes stale domains.

Force-refresh claudit's cached Claude Code docs by re-fetching Anthropic documentation (spawns web-research agents, overwrites the local cache). Run only when the user explicitly asks to refresh the claudit cache.

Show claudit knowledge cache status — freshness, TTL, and domain coverage

|

>

Professional frontend standards for building, scaffolding, extending, or reviewing any UI or frontend project — new or existing — even when standards aren't explicitly asked for. Keeps generated code consistent, reusable, secure, and production-quality. Framework-agnostic: React, Vue, Angular, Svelte, plain JS.