メニュー
Visible Harness analyze entry. Use after experiment runs to turn results into interpretation, decisions, and next-run or writing guidance.
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
Internal Harness instruction source for auto-iterate-goal. Route through visible Harness aliases or hook contracts instead of invoking directly.
Internal Harness instruction source for auto-paper. Route through visible Harness aliases or hook contracts instead of invoking directly.
Internal Harness instruction source for evaluate. Route through visible Harness aliases or hook contracts instead of invoking directly.
Internal Harness instruction source for iterate. Route through visible Harness aliases or hook contracts instead of invoking directly.
Internal Harness instruction source for orchestrator. Route through visible Harness aliases or hook contracts instead of invoking directly.
Visible Harness write entry. Use for manuscript writing, citation-supported paper work, final documentation, README hardening, and GitHub Pages preparation.
| name | analyze |
| description | Visible Harness analyze entry. Use after experiment runs to turn results into interpretation, decisions, and next-run or writing guidance. |
Use $analyze as the human-facing alias for result analysis. This is not a
separate Skill Contract.
Read and follow:
../../../.agents/skills/evaluate/SKILL.md../../../.agents/references/workflow-guide.md../../../AGENTS.md../../../CLAUDE.mdAnalyze current run artifacts and iteration logs, then produce decision-ready
insights that guide the next $run, a $grill pivot, or $write.
After updating completed run evidence, refresh
docs/30_evidence/Experiment_Evidence_Index.{json,md} using
tooling/evidence/build_experiment_evidence_index.py so $write can consume
experiment results without treating iteration_log.json as the sole source of
truth. If not run, report NOT_RUN with the reason.