Review Staged Changes
Use when the user wants a review of currently staged git changes before committing. Triggers on phrases like "review staged", "посмотри что я застейджил", "review before commit", "проверь изменения перед коммитом". Returns a structured findings list focused on correctness, security, and conventions — not style nitpicks.
Research Pipeline
Disciplined multi-source research pipeline that produces a verifiable, citation-backed report — orchestrated subagents, source-discipline, content-addressed snapshots, a deterministic→judge verification funnel, and a mandatory adversarial fact-check pass. Use when a deep-research document (best-practices canon, technology evaluation, claims that downstream code or decisions will lean on) must be…
Consulting Problem Solving Ru
**Русская версия Consulting Problem Solving Framework** — интерактивное решение бизнес- и организационных задач: ты ассоциат, пользователь — партнёр. 8 шагов с артефактами и явным утверждением: проблема, MECE-дерево, приоритизация, план работ, анализ, синтез, рекомендации, коммуникация по Strunk & White. Термины: стратегический консалтинг, дерево проблемы, issue tree, MECE, гипотезо-ориентированн…
Oss Product Selection
|
Demo Video Pipeline
End-to-end automated pipeline for recording polished 30-90s demo videos of React or HTML web apps. Universal keyboard-driven zoom hook with cinematic scenes → Playwright headless recording → Remotion overlay graphics (intro, callouts, count-up numbers, pulse highlights) → ElevenLabs voiceover with frame-perfect timings → final mp4 with audio mixing and ducking. Use whenever the user wants to reco…
Skill Graveyard
Audit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, hallucinated skill invocations, per-project skill stats, or token cost of installed skill metadata. Triggers on "what skills don't I use?", "clean up my skills", "why didn't this skill work?", "audit skills". Runs locally; reads ~/.claude session JSONL logs. No network calls.
Memory Graveyard
Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entries, broken pointers in MEMORY.md, orphan memory files, or surface entries that fall below the system-prompt truncation cutoff. Triggers on "audit MEMORY.md", "dead memory entries", "broken memory pointers", "memory hygiene", "unused memory", "memory truncation". Runs locally; re…
Mcp Graveyard
Audit which MCP server tools your Claude Code sessions actually invoke. Use when the user wants to find dead MCP servers (configured but never called), hallucinated MCP tool calls, or per-project MCP usage. Triggers on "which MCP servers don't I use?", "clean up MCP config", "remove unused MCP servers", "audit MCP tools". Runs locally; reads ~/.claude session JSONL logs and ~/.claude.json. No net…