kaizen

Delegate deep domain analysis, architecture planning, or complex decisions to your own scope's expert agent (claude-opus). Ensures the expert is running for YOUR scope. Use for architectural decisions, multi-step planning, tradeoff evaluation, domain modeling. Never borrows agents from other scopes.

Full feature development cycle with herdr-managed agent panes. Ensures an ai-workers tab exists with coder, researcher, and critic panes, then orchestrates implement-review loop via pi-link. Use when you want a persistent multi-agent workspace managed by herdr.

Delegate a research task to your own scope's researcher agent. Ensures ai-workers panes are running for YOUR scope, then sends the request to <scope>@researcher. Use for codebase exploration, external references, pattern lookup. Never borrows agents from other scopes.

Delegate a code review to your own scope's critic agent. Ensures ai-workers panes are running for YOUR scope, then sends the request to <scope>@critic. Use for code review, diff review, quality checks. Never borrows agents from other scopes.

Analyze colleague feedback for relevance, objectivity, and practical value. Use when evaluating code review comments, architectural feedback, or any critique from a peer before deciding what to act on.

Full feature development cycle with multi-agent collaboration — researcher, coder, and reviewer. Use when implementing a non-trivial feature that benefits from research, iterative coding, and independent review.

Delegate a task to the most suitable connected agent via link_prompt and return the result to the user. Use when you want to route a request to a specialist colleague on the pi-link network.

Request a code review from an independent reviewer agent via link_prompt, then analyze and act on the findings. Use when you want an external perspective on recent changes before committing or merging.

Coordinate a local multi-agent coding team via pi-link. Use when the user wants a real team lead who decomposes work, assigns roles (researcher, coder, reviewer), manages execution order, or asks to orchestrate multiple agents safely.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Write high-signal code comments for humans and coding agents. Use when adding inline comments, docstrings, API comments, or local rationale near code. Triggers on: "write better comments", "comment this", "document why", "agent-friendly comments", "explain this code with comments", "docstring".

Maintain i18n JSON dictionary files manually and safely. Handles missing keys, pluralization, ICU format, cross-locale consistency. Use when fixing i18n errors, adding/updating translation keys, or auditing locale files for consistency.

**REQUIRED** - ALways activate FIRST on any git/VCS operations (commit, status, branch, push, etc.), especially when HEAD is detached. If `.jj/` exists -> this is a Jujutsu (jj) repo - git commands will corrupt data. Essential git safety instructions inside. DO NOT IGNORE.

Review English text edits in org-mode files from a git diff. Checks grammar, style, translation quality (RU→EN), and produces a clean patch. Use when reviewing org-mode writing, checking English quality of documentation edits, or auditing translation naturalness.

Fetch unresolved GitHub PR review comments, analyze each for relevance, present categorized summary, ask which to fix, then apply minimal code changes. Trigger - any GitHub PR URL or request to review/fix PR comments.

Fetch open GitHub PR data (diff, files, CI, metadata), perform AI code review using strict KISS/DRY/SOLID rules, save results locally, and present categorized findings. Trigger - any GitHub PR URL or request to "review PR", "check PR", "review open PR".

Plan and write Vitest tests for changed code. Analyses git diff, checks existing tests, produces a concrete test plan using flat test structure (no describe/it blocks). Use when adding tests for new/changed code, improving Vitest coverage, or asking what to test after a change.