工具

Use when user requests automated documentation generation from requirements file. Triggers include: - Korean: "문서 작성해줘", "write-docs 실행해줘", "자동 문서 생성" - English: "write documentation", "run write-docs", "generate from requirements" - Context: User has run prepare-docs and has docs/doc-requirements.md file ready This skill focuses on Step 2 of automated workflow: Reading requirements file and generating documentation automatically with per-sentence accuracy tracking and rationale for low-confidence statements (< 70%).

Comprehensive Docker containerization workflow covering multi-stage builds, docker-compose orchestration, image optimization, debugging, and production best practices. Use when containerizing applications, setting up development environments, or deploying with Docker.

Standardize Figma-to-code workflow using Figma MCP - always get_design_context first, then screenshot, use project tokens not hardcoded values, validate 1:1 parity

Эксперт по переговорам. Используй для sales negotiation, objection handling и deal closing.

Default testing standard for all implementation work - ensures code actually works through mandatory execution validation before confirming to user. Applies automatically whenever writing, modifying, debugging, or implementing any code (scripts, APIs, UI, configs, data operations, logic changes). This is the baseline expectation, not an optional extra - every implementation must be verified through actual execution, not assumed correct.

Generate a skeleton template for a new Claude Code Skill.

Sync markdown projects to Confluence using the markdown_confluence tool. Use for publishing, crawling, and managing Confluence pages from local markdown files.

Use when creating or pricing energy consulting proposals including ASHRAE Level 1/2/3 audits, benchmarking services, commissioning, compliance pathway consulting, and performance target analysis. Provides pricing models, cost estimation, scope templates, service definitions, labor hour estimates, and proposal generation. Use when the user mentions proposal writing, pricing services, scoping work, energy audit costs, consulting rates, or needs to generate professional proposals for energy projects.

Use this skill when developing Next.js/React frontend code for Brokle. Includes components, pages, hooks, API clients, stores, or any frontend features.

Technical content writer for marketing pages, blogs, documentation, and video scripts. Use when asked to create marketing content, landing pages, blog posts, technical documentation, video scripts, or any content that requires deep understanding of the codebase and task history.

Execute Preflight phase for /itp workflow - create ADR (MADR 4.0), design spec from global plan, verify checkpoint. Use when creating ADRs, design specs, or when /itp invokes Preflight phase. Triggers - ADR creation, design spec, MADR format, preflight verification.

Generate a .gitignore file for any project using the gitignore.io command-line tool (gi) or API.

Codex CLI를 sub-agent로 활용하여 실제 구현 작업을 수행합니다. Claude가 작업을 분석/분해하고, Codex가 코드 작성/수정/리팩토링을 담당합니다. "Codex로 구현", "구현해줘", "코드 작성해줘", "병렬 구현" 요청 시 활성화됩니다.

Comprehensive Playwright automation testing skill with E2E testing standards, test generation workflows, and browser automation best practices. Use when writing automated browser tests, testing user flows, or performing web application QA.

Generate comprehensive dbt test suites following FF Analytics data quality standards and dbt 1.10+ syntax. This skill should be used when creating tests for new dbt models, adding tests to existing models, standardizing test coverage, or implementing data quality gates. Covers grain uniqueness, FK relationships, enum validation, and freshness tests.

Extract video transcripts and captions from YouTube. Use when user wants to get text content from YouTube videos, analyze video content, create summaries, or extract quotes.

Remove a git worktree after agent completes work. Use this after merging a sub-issue PR or on failure to cleanup all associated resources including Docker containers, volumes, and git metadata.

Provides three production-ready ML training examples (sentiment classification, text generation, RedAI trade classifier) with complete training scripts, deployment configs, and datasets. Use when user needs example projects, reference implementations, starter templates, or wants to see working code for sentiment analysis, text generation, or financial trade classification.

Critical review and gap analysis skill that can be invoked at any workflow stage. Use to challenge decisions, identify missing specifications, verify coherence, and surface unaddressed questions in CDC, findings, plans, or any deliverable. Acts as a devil's advocate by deeply analyzing codebase, project documentation ([DOC]-* folders), and context.

Deterministically compare wf_cycle runs as a Proof of Invariance step: compute metrics, score the double-run, and write canonical compare artifacts for the result_core outputs.