メニュー
Final integrity check before declaring work complete: compile, test, placeholder scan, spec coverage. Use when: code changes appear complete and need final compile, test, and integrity verification.
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
Read-only cross-artifact consistency analysis after planning and before approval. Verifies that spec.md, requirements.json, plan.md, tasks/Tn.md, traceability.json are mutually consistent: no duplicate/ambiguous requirements, every behavior mapped to a task, no orphan tasks, no coverage gaps, no contradictions. Outputs artifact-analysis.json with coverage% and severity. CRITICAL/HIGH findings block the approval gate. Use when: planning produced plan.md + tasks + traceability.json, before the user approves the plan.
Explore 2-3 implementation options with trade-offs when the user describes a new feature or requirement. Use when: the user asks for a new feature design, implementation options, or technical trade-off analysis.
After implementation and before final verification, compare current code/tests against the intent inventory (requirements.json + traceability.json). Classify each requirement/behavior as covered, missing, partial, contradicts, or unrequested. Append missing/partial/contradicts as new tasks back to executing. Repeat until converged: zero blocker findings. Outputs convergence-report.json. Use when: executing produced test-report.md but before loom-verification-before-completion.
Expand each requirement into verifiable Behavior Obligations across 15 fixed dimensions (happy-path, boundary, invalid-input, authorization, state-transition, idempotency, concurrency, atomicity, external-failure, compatibility, security, performance, observability, recovery, forbidden-behavior) before planning. Use when: brainstorming produced requirements.json and spec is approved, but behaviors are still placeholders or only happy-path; before loom-writing-plans.
Read-only adversarial reviewer that looks for what SHOULD exist but doesn't, by cross-checking Behavior Obligations against code, tests, expected side effects, forbidden side effects, failure scenarios, and public API changes. Focuses on negative space: events that should not repeat, permissions that should not be bypassed, partial writes that should not happen, old APIs that should not change, swallowed exceptions, leaked secrets. Outputs findings.json. Use when: executing or converge needs an independent omission sweep.
Analyze user request + collect signals (file scope, keywords, worktree state, spec existence), then select pipeline steps via rule short-circuit / AI fallback / rule-based fallback. Select steps first, expose the choice to the user, and persist selected dynamic_steps only after explicit user confirmation; pipeline-plan.md is optional for manual review. Use when: user is unsure which pipeline type to pick, or wants AI to choose steps automatically.
| name | loom-verification-before-completion |
| description | Final integrity check before declaring work complete: compile, test, placeholder scan, spec coverage. Use when: code changes appear complete and need final compile, test, and integrity verification. |
| when_to_use | Run final compile, test, placeholder, and spec coverage checks before declaring work complete. |
| argument-hint | <spec_dir or verification scope> |
| user-invocable | true |
specs/<date+feature>/test-report.md、reviewer 判定等前置报告也算证据，但必须读取并引用。本阶段的 specDir 是 specs/<date+feature>/。所有验证产物都必须写入该目录内；禁止在项目根目录写 verify-report.md、progress.md 或 handoffs/。
做状态声明前：识别证据 → 运行命令或读取报告 → 验证输出确实支持断言 → 再声明。
进入人工判断前运行：
node <skill-dir>/scripts/verify-artifacts.mjs --spec-dir specs/<date+feature>
脚本通过只代表产物齐全且没有明显机械性缺陷；脚本失败时，先修复或补齐证据。
specs/<date+feature>/test-report.md 和 combined-reviewer 报告，确认最终通过。.loom/rules/constitution.md 中的 BUILD_CMD、VET_CMD 并执行；TEST_CMD 已由 test-reporter 执行时不重复。TBD、TODO、implement later、fill in details。specs/<date+feature>/verify-report.md。specs/<date+feature>/handoffs/verification.json，摘要说明验证结论、证据命令、关键产物和剩余风险。构建/检查的长输出保存到 specs/<date+feature>/evidence/verification.log；报告只保留 command、exit code、相对路径和 SHA-256。这样可验证且不占用后续上下文 token。
报告模板见：
assets/verify-report-template.mdassets/fix-instructions-template.md以下措辞意味着未验证就声称：应该通过了、probably passes、似乎没问题、seems fine、我觉得可以。发现后立即停止，补证据再声明。
构建/检查/测试命令
读取 .loom/rules/constitution.md 中的 BUILD_CMD/VET_CMD/TEST_CMD 并执行验证。
验证通过时完成 specs/<date+feature>/verify-report.md 和 specs/<date+feature>/handoffs/verification.json；验证失败时标记失败，输出修复指令，禁止全量重跑 Step 4。阶段结束后压缩验证过程中的长日志和中间排查，只保留报告、progress 和 handoff。