ワンクリックで
evaluate-patterns
Evaluation patterns — sprint contract format, three-layer verification, scoring rubric references.
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。
メニュー
Evaluation patterns — sprint contract format, three-layer verification, scoring rubric references.
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
Switch model mid-session preserving thinking blocks. Used by /model command and by BRD §6.2 failover when the primary provider rate-limits or fails.
Six-phase ReAct loop (pre-check, thinking, self-critique, action, tool, post). Activates per-workflow via the thinking_level knob in config/workflows.yaml. Replaces standard ReAct for workflows where independent verification of the reasoning improves outcomes.
Mines completed sessions for repeating {tool sequence → outcome} tuples. Scores by frequency × success_rate × novelty. High-scoring tuples become "instincts" — candidate skill seeds — in instincts/pending/.
Walk-back algorithm for the Spec-Auditor subagent. Given a failure at phase N, identifies the earliest phase whose spec, if tightened, would have prevented the failure. Proposes a surgical amendment.
Sessions stored as trees (not lists). /fork creates a branch from any point; /tree navigates; /branch labels a path; /export produces HTML for review. All branches live in one session file under sessions/<project>/<session_id>.json.
Progressive context refinement for subagents. Don't dump everything; retrieve in passes. Start with a list of file paths and one-line abstracts; load full content only when the abstract proves insufficient.
| name | evaluate-patterns |
| description | Evaluation patterns — sprint contract format, three-layer verification, scoring rubric references. |
Reference skill for the evaluator agent. Points to authoritative sources for evaluation patterns.
Read .claude/skills/evaluate/SKILL.md for the complete three-layer verification workflow, execution steps, verdict format, and mode behavior.
| File | Contents |
|---|---|
references/contract-schema.json | Sprint contract JSON schema |
references/scoring-rubric.md | Design scoring rubric (4 criteria, weights, exemplars) |
references/scoring-examples.md | Calibration anchors (score 5, 7, 9) — read before scoring |
references/playwright-patterns.md | Selector patterns and assertion patterns for Layer 2 |
These rules are non-negotiable. Deviation invalidates the evaluation.
status: 200 and you get 201, that is a FAIL.