菜单
AI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when completing any task, fixing a bug, finishing a phase, running tests, building, deploying, or making any "it works" claim.
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
AI DevKit · Design phase guidance for reviewing feature design against requirements. Use when the user wants to validate architecture, review design docs, resolve design trade-offs, or run dev-lifecycle phase 3.
AI DevKit · Implementation phase guidance for executing feature plans and checking implementation against design. Use when the user wants to implement planned tasks, update implementation docs, verify code matches design, or run dev-lifecycle phases 5 and 7.
AI DevKit · Orchestrator for structured SDLC phase skills. Use when the user wants to run the full lifecycle or choose the next phase across requirements, design, planning, implementation, testing, and review.
AI DevKit · Planning phase guidance for creating and reconciling feature task plans. Use when the user wants to create an implementation plan, update planning docs, mark task progress, capture blockers or new tasks, or run dev-lifecycle planning work.
AI DevKit · Requirements phase guidance for starting features and reviewing requirements. Use when the user wants to capture a new requirement, clarify product scope, initialize feature docs, review requirements, or run dev-lifecycle phases 1-2.
AI DevKit · Final code review phase guidance for holistic pre-push review. Use when the user wants code review, final lifecycle review, design alignment checks, integration risk review, or dev-lifecycle phase 9.
| name | verify |
| description | AI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when completing any task, fixing a bug, finishing a phase, running tests, building, deploying, or making any "it works" claim. |
Prove it works before saying it works.
Every completion claim must pass all 5 steps in order:
If any step fails, stop. Fix the issue and restart from step 1.
If no verification command exists (e.g., no test suite), tell the user and ask them how to verify before claiming done.
| Claim | Required Evidence | Not Sufficient |
|---|---|---|
| Tests pass | Test output: 0 failures, exit 0 | Previous run, "should pass now" |
| Build succeeds | Build output: exit 0 | Linter passing, partial build |
| Bug is fixed | Reproduce symptom → now passes | "Changed code, should be fixed" |
| Linter clean | Linter output: 0 errors | Single file check |
| Phase complete | Each criterion verified individually | "Tests pass, so done" |
| Feature works | E2E test or manual walkthrough | Unit tests alone |
For bug fixes, a single pass is not enough:
If step 4 passes, the test is wrong. Rewrite it.
| Rationalization | Why It's Wrong | Do Instead |
|---|---|---|
| "This change is trivial" | Trivial changes break things constantly | Run the check |
| "I ran it earlier" | Code changed since then | Run it again now |
| "The test is flaky" | Flaky ≠ ignorable | Fix the flake first |
| "It compiles, so it works" | Compilation ≠ correctness | Run the tests |
| "The CI will catch it" | CI is a safety net, not a substitute | Verify locally first |
| "The agent said it's done" | Agent claims need verification too | Check diff and run tests |
After a failed verification, store the failure pattern: npx ai-devkit@latest memory store --title "<failure pattern>" --content "<what failed and how to avoid>" --tags "verify,failure-pattern"
If a task name is known and tracing is usable, record task evidence after
the verification report per task. If tracing was not probed, run the real read
probe first. If probe or evidence recording fails, report the failed task command
and continue verification; never block verification on optional task logging.
