.config

Проведение ревью и анализ результата через независимого агента...

Describe the current jj revision with a proper commit message. Use when the user wants to create a commit message, describe changes, write a commit summary, prepare a commit description, or says "describe this revision", "what should I commit", "create commit message".

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.

Helps describe changes clearly, follow conventional commit style, keep jj revisions focused, and apply agent/skill creation best practices. Use whenever the user asks how to name a change, write a commit or revision description, decide whether to reuse the current jj revision, create or modify an agent or skill, or wants cleaner change hygiene before editing files.

Reviews uncommitted changes or an explicitly requested diff with a strict KISS/DRY/SOLID rubric. Use when the user asks for a code review, diff review, pre-commit validation, or a quality pass on recent changes.

Runs an independent multi-model review of the current diff, stores per-model reports, merges duplicates, and produces a skeptical consolidated verdict in Russian. Use when one reviewer is not enough and the user wants crowd wisdom.

Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page snapshot", "browser snapshot", "DOM structure", "inspect page", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output that may exceed 20 lines. Subagent routing is handled automatically via PreToolUse hook.

Show how much context window context-mode saved this session. Displays token consumption, context savings ratio, and per-tool breakdown. Trigger: /context-mode:ctx-stats

Produces a deep implementation plan with clarifications, multiple solution variants, and adversarial critique. Use when the user asks for architecture, a serious implementation plan, design options, or a high-confidence roadmap before coding.

Builds a rigorous test strategy with multiple test-suite variants and critical review. Use when the user asks what to test, wants adversarial coverage, or needs a stronger test plan before or after implementation.

Reviews a Jujutsu (jj) revision range using the canonical KISS/DRY/SOLID rubric. Use when the user asks to review jj revisions, review a jj diff range, check quality of a jj commit stack, or do a pre-push review of jj changes. Triggers on "review my jj changes", "review this revision", "review commits from A to B", "jj code review", "review before push", "review jj range", "check jj diff quality".

Use Jujutsu (jj) for version control instead of git. Always check current revision before making changes — if the task semantically differs from the current revision's description, create a new revision first.

Non-interactively split a jj revision into atomic, focused commits via CLI. Triggers on "split revision", "split commit", "jj split", "разделить коммит", "split changes", "make commits atomic", "refactor commits into smaller ones".

**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.

Build, debug, and package pi coding-agent extensions. Use when the user wants to create or modify a pi extension, register custom tools or commands, handle lifecycle events, or package extensions for sharing.

Reviews CSS/SCSS changes in the current branch for over-specificity, missed reuse opportunities, and over-engineered abstractions. Produces analysis findings and uses pm7y-ralph-planner to generate TASKS.md for autonomous execution. Use when reviewing CSS changes before commit or PR, or to audit existing styles. Supports @file syntax to target specific files.

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".

Refactor existing code to improve quality, readability, architecture, consistency, simplicity, and idiomatic style — without changing observable behavior. Use this skill whenever the user says "refactor", "clean up this code", "this is messy", "too complex", "hard to read", "too much duplication", "improve code quality", or shares code with obvious structural problems. Also trigger proactively when you notice significant code smells while working on another task. Default mode is execution (make the changes); switch to plan-only if the user explicitly asks for a refactoring plan without executing changes.

Analyzes pi skills — both remote (URL/GitHub) and local (installed on disk). Fetches the skill, runs a security audit, summarizes what it does and which problems it solves, then polls multiple AI models for a multi-model consensus rating. Use this skill whenever the user shares a link to a skill and wants to know if it's safe and worth installing, asks to review or evaluate a skill from GitHub, asks to audit an already installed local skill, says something like 'check this skill', 'review my skills', 'should I install this', 'audit this skill', or wants a second opinion on a skill's quality. Also triggers on 'проанализируй скилл', 'проверь скилл по ссылке', 'оцени скилл', 'проверь локальный скилл' — works in both English and Russian.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Searches YouTrack from natural language or native query syntax and returns a concise report with the most relevant issues. Use when the user wants to find issues, triage work, or translate a plain-language query into YouTrack search.

Analyzes a YouTrack issue, reviews comments and attachments, and proposes or creates actionable subtasks. Use when the user gives a YouTrack issue ID and wants synthesis, decomposition, or follow-up tasks.

Fetch YouTrack task + comments via MCP, critically analyze relevance and requirements, produce concise summary of what to implement, and build an implementation plan mapped to codebase. Trigger - YouTrack issue ID or request to "analyze task", "plan task", "break down YT issue".