メニュー
Measured codebase cleanup: dead code, dependency cycles, weak types, duplicate logic, deprecated paths, test debt, and complexity, using real tools and before/after proof.
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。
Raise the ceiling, don't climb toward it. When a target is nearly hit or a metric has plateaued, question the target itself: name the binding constraint, separate the physics floor from the assumed floor, design the regime change that makes 10x reachable, commit through the valley. Triggers: 'breakout', '10x this', 'raise the ceiling', 'why are we capped', 'think way bigger', 'this metric is a cage'.
Prove that a merged change is actually live and production behavior is measured against the deployed artifact. Use after merge, before claiming deployed/live/validated, for Cloudflare Pages/Workers deploys, cache claims, perf claims, and release closeout.
Diagnose and improve eval harnesses built on @tangle-network/agent-eval or similar trace-first systems. Use when success/failure rates, scorecard deltas, judge outputs, promotion gates, benchmark rows, or improvement campaigns may be contaminated by harness bugs, evaluator drift, routing/auth failures, missing traces, or invalid baselines.
Goal-pursuit loop: measure, diagnose, experiment, verify, compare, and iterate against a measurable target. Triggers: evolve, optimize, make this better, push to target.
Split one messy experiment branch into N clean, independent branches — one logical change each, built from the merge-base, disjoint change-sets, each an isolated reviewable PR. Triggers: 'finalize', 'split this branch', 'atomize this', 'make reviewable PRs', 'decompose this mess'.
Read repo/session state and choose the single next skill: exploit (evolve/polish), explore (pursue/meta-harness/breakout), bootstrap (eval-agent), diagnose (diagnose/eval-harness-diagnose), or step back (reflect). One dispatch, then exit.
SOC 職業分類に基づく
| name | deep-clean |
| description | Measured codebase cleanup: dead code, dependency cycles, weak types, duplicate logic, deprecated paths, test debt, and complexity, using real tools and before/after proof. |
Use this for broad cleanup after big changes, migrations, or obvious codebase drift. It is not a substitute for feature work or security validation.
Run the repo's relevant static tools before editing: dead-code scan, dependency graph, typecheck, duplicate scan, lint, tests, and build where available. Record the exact command and baseline counts.
Do not parallelize across those phases; each phase changes what the next phase sees.
Use references/full-reference.md for tool commands, phase details, and reporting templates.
harden for security-sensitive surfaces discovered during cleanup.converge if cleanup leaves CI red.polish for a narrower final quality pass.