メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.
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"call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output".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.
| name | consensus-review |
| description | 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 this skill when the user wants several independent review opinions and one consolidated report.
Before starting, load:
references/code-reviewer.mdUse that rubric as the common review contract for every model.
Review only uncommitted changes unless the user specifies a different range.
git diff HEAD --name-only
If there is no diff, report that and stop.
Write results to:
plans/review/qwen-cli-review.mdplans/review/codex-5.1-review.mdplans/review/gemini-2.5pro-review.mdplans/review/deepseek-3.2pro-review.mdplans/review/overview.mdCreate plans/review/ if needed.
references/code-reviewer.md.plans/review/overview.md with:
The final user-facing answer must include: