decompose-tech-spec
stepanenkoviktor0110-boop/ai-dev-methodology/skills/decompose-tech-spec/SKILL.md
Decompose approved tech-spec into tasks with validation
Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/decompose-tech-spec/SKILL.md
Decompose approved tech-spec into tasks with validation
stepanenkoviktor0110-boop/ai-dev-methodology/skills/documentation-writing/SKILL.md
Maintain project documentation in .claude/skills/project-knowledge/: audit, edit, check consistency, track status.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/do-feature/SKILL.md
Execute feature with team of agents — waves, reviews, commits.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/done/SKILL.md
Finalize work session: detect documentation drift from git changes, show drift items for review, update project knowledge, optionally archive feature.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/do-task/SKILL.md
Execute task from tasks/*.md with quality gates.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/feature-execution/SKILL.md
Orchestrate feature delivery as team lead: spawn agents by wave, manage review cycles (max 3 rounds), commit per wave.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/init-project-knowledge/SKILL.md
Первичное заполнение документации проекта
stepanenkoviktor0110-boop/ai-dev-methodology/skills/methodology/SKILL.md
AI-First development methodology: spec-driven pipeline, project structure, skills/agents ecosystem, quality gates.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/new-tech-spec/SKILL.md
Create technical specification and tasks (uses tech-spec-planning skill)
stepanenkoviktor0110-boop/ai-dev-methodology/skills/new-user-spec/SKILL.md
Create user specification through adaptive interview (uses user-spec-planning skill)
stepanenkoviktor0110-boop/ai-dev-methodology/skills/pause/SKILL.md
Stops current work on user request, captures full session state to project docs, and generates a resume prompt so the next session can continue without loss.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/pishi/SKILL.md
Редактирует русский текст по инфостилю Ильяхова («Пиши, сокращай»). Убирает стоп-слова, штампы, канцеляризмы, голословные утверждения. Заменяет конкретикой: фактами, цифрами, пользой. Адаптирует строгость под контекст: UI, лендинги, email, статьи, саппорт. Вызывай, когда нужно отредактировать, улучшить, вычистить или проверить русский текст. Also triggers on: edit Russian text, improve copy, review UX writing, fix marketing text, rewrite landing page, clean up email.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/post-deploy-qa/SKILL.md
Post-deploy verification: execute AVP from tech-spec on live environment, verify all acceptance criteria (user-spec + tech-spec), pick up deferred criteria from pre-deploy QA report. Uses MCP tools (Telegram MCP, Playwright, curl, bash).
stepanenkoviktor0110-boop/ai-dev-methodology/skills/pre-deploy-qa/SKILL.md
Pre-deploy acceptance testing methodology: run test suite (unit/integration/E2E), verify acceptance criteria from user-spec and tech-spec. Does not require live environment.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/prompt-master/SKILL.md
Guide for writing effective prompts for LLMs.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/quick-learning/SKILL.md
Owner of the unified methodology knowledge system: format, triad structure, similarity check, Seen counters, and Adapted tracking.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/recalibrate-all/SKILL.md
Autonomous one-shot cleanup and calibration of all skills in $AGENTS_HOME. Removes 16 obsolete design skills (keeps photo-crop, content-card), purges codex references from active skills and triads, calibrates remaining skills against Anthropic best practices and the 250-line SKILL.md soft limit. Runs end-to-end without user gates; risky items skipped to known-issues for post-run review rather than asked about mid-flight.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/security-auditor/SKILL.md
Comprehensive security analysis against OWASP Top 10 standards. Use after code-reviewer for code handling: authentication, user input, database queries, external APIs.
stepanenkoviktor0110-boop/ai-dev-methodology/skills/sketch/SKILL.md
Lightweight prototyping mode: collect requirements in 3–5 questions, write code directly without validators, then decide whether to develop further or archive.
Often used withtouchdesigner-mcp
stepanenkoviktor0110-boop/ai-dev-methodology/skills/skill-trainer/SKILL.md
Embeds accumulated triads from quick-learning into target skills as permanent instructions. Reads triads with Adapted=— from triad-index.md, analyzes each skill's existing logic, auto-applies new rules when no coverage exists, proposes refinements when partial coverage found. After embedding, updates Adapted field and cleans reasoning-patterns.md.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.