一键导入
sh-dod
Run the Definition of Done gate check before deployment. Verifies work is complete, tests pass, and task meets all exit criteria before committing.
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。
菜单
Run the Definition of Done gate check before deployment. Verifies work is complete, tests pass, and task meets all exit criteria before committing.
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
Multi-expert AI/ML specification review with scoring gate — model architecture, evaluation rigor, safety/alignment, and production readiness for AI systems and LLM apps
Multi-expert architecture review — boundaries, integration patterns, failure modes, evolvability
Multi-expert business analysis with advisory recommendations (no scoring gate)
Multi-expert intelligence pipeline review — discovery quality, ingestion resilience, scoring validity, platform compliance, taxonomy coherence, cost efficiency
Multi-expert mobile/native app specification review with scoring gate — Android, iOS, Swift, SwiftUI
Multi-expert personal-development review with scoring gate — learnability, adoption, human-centeredness, and capability impact for talent/learning/AI-augmentation designs
| name | sh-dod |
| description | Run the Definition of Done gate check before deployment. Verifies work is complete, tests pass, and task meets all exit criteria before committing. |
Gate: Must pass BEFORE deployment. An item that fails DOD cannot be deployed. The queue tail enforces this automatically.
Unknown: clausegit status clean after commit[x] in TODO-Today.md1. Analyze changed files (findings use FIPD classification)
2. Deep audit (M+ size tasks only -- security/perf/architecture)
3. Cleanup (fix Low findings, enforce coding standards)
4. Run tests with coverage (if new test files)
5. Atomic conventional commit
6. Deploy (project-specific)
If any step fails, autopilot pauses and reports the blocker.
The quality gate (quality_gate.run_stage1_dod) consumes this skill via
claude -p and reads the verdict from stdout, not the exit code. Therefore
the final line of your output MUST be exactly one of:
DOD-VERDICT: PASS
DOD-VERDICT: FAIL: <machine_reason>
PASS only when every applicable checklist item is satisfied.<machine_reason> naming the first
blocking item — e.g. tests_red, uncommitted_changes, audit_findings,
no_provenance, app_boot_failed, secrets_present.dod_no_verdict (inconclusive).