メニュー
Design and build a generational improvement when the current approach is wrong or plateaued. Audit, choose a coherent architecture, implement, test, and hand off.
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
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.
| name | pursue |
| description | Design and build a generational improvement when the current approach is wrong or plateaued. Audit, choose a coherent architecture, implement, test, and hand off. |
Use this for architectural leaps, not parameter tuning. The output is a working generation with tests, not a proposal.
.evolve/ progress, prior pursuits, and current failures./hypothesize when one exists), argue them against each other, pick the winner by predicted leverage, and graft the best ideas from the runners-up. Then commit to one coherent change set; avoid unrelated cleanup.Use references/full-reference.md for the full pursuit template and verification details.
hypothesize before designing, when the architecture field is wide open — get a researched, ranked set of candidate designs to run the tournament on.evolve to tune a working generation.breakout when the generation lands but the ceiling still feels small — the honest next move is a higher target, not a better point under this one.polish when the generation works but quality gaps remain.autopsy if the generation result is null or suspicious.