メニュー
Post-implementation cleanup for recent changes using parallel reuse, quality, and efficiency reviewers. Use after building a feature or fix, before commit, PR, or submit.
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
| name | simplify |
| description | Post-implementation cleanup for recent changes using parallel reuse, quality, and efficiency reviewers. Use after building a feature or fix, before commit, PR, or submit. |
| version | 0.1.0 |
| author | George-RD |
| x-compatibility | jcode-primary, claude-code-adaptable, opencode-adaptable |
Use this skill after implementation and tests, before commit or submit.
Simplify is cleanup/pre-review hardening, not a substitute for correctness, security, acceptance, or submit review.
Core principle: tighten recent changes without expanding scope. Find duplication, code quality issues, and efficiency problems, then apply only high-signal fixes. Repeat simplify only when the latest fix cycle made medium or large changes.
git diff, git diff --staged, or the commit range the user gives.Read references only when needed:
references/reviewer-prompts.md: prompts for reuse, quality, and efficiency lenses when external reviewers are justified by scale.references/fix-policy.md: which simplify findings to apply or skip.assets/simplify-loop.mmd: Mermaid loop diagram template.scripts/validate.sh: behavioral contract checks for this skill.Primary review entrypoint for plans, diffs, commits, subagent results, and pre-submit checks. Selects quick, standard, or deep mode by scale and risk.
Planner-led repo improvement loops with subagents, review gates, Mermaid DAGs, and workflow-aware commits. Use for improve, refactor, audit, or continue-loop requests.
Triage and apply code review feedback with technical verification. Use when a human, reviewer subagent, CI, or adversarial reviewer returns findings or requested changes.
Heavy review mode normally invoked by request-code-review for risky checkpoints, pre-submit stacks, OpenSpec/cflx acceptance, security-sensitive work, or explicit deep review, audit, or red-team requests.
End-of-workflow learning loop for skill-guided work. Use at session/checkpoint closeout to classify GitHub/CodeRabbit/human/CI findings, log missed-review patterns, and propose skill improvements only when evidence justifies them.
Use this skill when working in a repo that uses Graphite (the `gt` CLI) for stacked PRs. Activates whenever the git common dir contains `.graphite_repo_config`, the project's CLAUDE.md mentions Graphite or `graphite-pr`, or the user mentions `gt`, stacked PRs, atomic commits, or splitting a change into reviewable pieces. Drives the daily commit → submit → review → merge loop and the rules for sizing atomic commits. To bootstrap Graphite in a new repo, read `references/setup.md` first.