菜单
Use when authoring or editing a skill that enforces a rule an agent could rationalize past — a discipline skill — or when a shipped discipline skill is being skipped, ignored, or only partially followed. Also use when reviewing a discipline skill before release.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
When --quality-locked is active, loop review/revise at each Quality Gate until findings reach a clean bar (no Critical, no Major, only cosmetic Minor) or the iteration cap (10) is reached. Uses a deterministic Python checker for classification and decision logic; agent runs the actual review and revision steps.
Use after implementation passes the quality gates, when a change needs an independent pass over the code before it ships, or when the user asks to "QA this", "check the implementation", or "verify it matches the spec". Applies to Standard and Comprehensive scopes with the Task tool available; Lightweight tasks skip.
Use when the user picks [A] Review at a spec/plan/ADR/root-cause/fix-plan checkpoint, or asks for an independent review before implementation begins. Applies to Standard and Comprehensive scopes with the Task tool available; Lightweight tasks skip.
Use as the code-quality gate after spec-compliance and constitution checks pass, or when the user says "review my code", "quality check", "security review", or "is this code good". Runs as an independent sub-agent when the Task tool is available.
Adversarial review verifying implementation matches its specification — checks completeness (nothing missing) and precision (nothing extra). Distrusts the implementer's self-report. Use after implementation, or when the user says "check against spec", "does this match requirements", or "verify the implementation".
Configure Sage preset and project settings. Switch between base, startup, enterprise, or opensource constitution presets. Use when the user says "configure sage", "change preset", or "sage settings".
| name | testing-skills |
| description | Use when authoring or editing a skill that enforces a rule an agent could rationalize past — a discipline skill — or when a shipped discipline skill is being skipped, ignored, or only partially followed. Also use when reviewing a discipline skill before release. |
| version | 1.0.0 |
| modes | ["build","architect","fix"] |
| skill_type | methodology |
| compliance_marker | ⚡ RED baseline first |
Behavioral proof for discipline skills — those that enforce a rule an agent could rationalize past. Structure is not compliance. This proves the skill holds under pressure, deterministically.
Use for a discipline skill: one whose value is that it runs even when the agent is tempted to skip it (mandatory reviews, quality gates, process steps). Signs: it says MUST/ALWAYS, lists "blocked rationalizations", or gates a phase.
Do not use for technique or reference skills — ones that inform but enforce nothing. Those are covered by the structural scorecard; they have no skip to prove.
No discipline skill ships without a failing behavioral test first. Applies to
new skills and edits. When you catch a discipline skill about to ship or change
without a RED→GREEN run, announce ⚡ RED baseline first and run it. If you
cannot point at that run, you are not done.
references/pressure-scenarios.md.Every discipline skill MUST carry all four (enforced by
validate-discipline-skill.sh):
compliance_marker — an exact string the real code path emits when
followed. Not a test-only echo.TESTS.md beside SKILL.md, latest green_verdict: PASS.## Rationalization table — observed excuses + counters
(references/rationalization-table.md).description — triggering conditions only, no workflow summary
(references/cso.md).develop/skill-tests/run-skill-test.sh <skill-dir> --both dispatches the
scenario with the skill withheld (RED) then present (GREEN). RED passes when the
marker is absent; GREEN when present. Off-platform it exits 2 with a manual-mode
instruction — a dev tool, never a runtime dependency.