claudenv

Trigger when a task naturally decomposes into many independent sub-tasks that benefit from deterministic multi-agent orchestration: reviewing or migrating across many files, research over many sources, multi-dimension audits, generate-N-then-judge, or "find all X" with verification. Use the Workflow tool (agent()/parallel()/pipeline()). Also triggers on the word "workflow"/"workflows" or an explicit ask to fan out / orchestrate subagents. Do NOT trigger for single-file edits, strictly sequential work, or anything one or two Agent calls already cover.

Trigger when the current task would be done far better with a capability you don't yet have — a missing skill, connector, MCP server, browser automation, or memory you should be using. Also triggers on "/harness", "подбери инструменты", "what can you use here", "set yourself up for X", or when you notice you're about to do by hand something a dedicated skill exists for. The skill makes Claude self-aware of the claudenv harness and lets it EXTEND itself: introspect (`claudenv capabilities`), find the right tool (`claudenv skills search`), equip it (`claudenv skills add`), wire connectors / MCP / memory, and bootstrap the kimi-webbridge browser. Do NOT trigger for trivial edits that the current toolset already covers.

Trigger when the user wants to connect to a data source that has no ready MCP server - internal SQL/DWH behind VPN, corporate wiki (Confluence), Redash, YouTrack, a custom REST API - or says "добавь источник", "подключись к <система>", "/add-source". The skill interviews the user, generates a working connector script, stores credentials in .env.local (gitignored, never in memory), and caches connector knowledge (params + provenance) in the ACTIVE workspace memory, isolated from other workspaces. Do NOT trigger for sources that already have an MCP server (prefer MCP), or for trivial local file reads.

Trigger before writing code that involves a non-trivial technical choice (library, algorithm, data structure, architecture pattern, sync vs async, correctness vs performance). Output a brief overview with concrete trade-offs and 1-2 alternatives, then log the decision. Two modes: auto-log (no pauses) inside `claudenv loop`, pause-and-ask in interactive Claude Code. Also triggers on: "почему X?", "X vs Y?", "/why", "/deeper", "/decisions", "alternatives?", "trade-offs?". Do NOT trigger for trivial syntax, naming, or formatting choices.

Generates and updates project documentation including CLAUDE.md, rules, and hooks. Use when the user asks about documentation, project setup, CLAUDE.md, or when detecting that documentation is missing or outdated.