speckit-validate
Verify spec-to-task traceability and check that completed tasks produced expected files
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Verify spec-to-task traceability and check that completed tasks produced expected files
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Archive a merged SpecKit spec and clean active workflow residue after the implementation PR has merged. Use after confirming merge provenance, when the user asks for post-merge SpecKit archive hygiene, cleanup hygiene, or removal of completed specs from active specs.
Autonomous SpecKit workflow executor. Reads a populated workflow file and executes all 7 SDD phases (specify → clarify → plan → checklist → tasks → analyze → implement) with programmatic gate validation, multi-agent consensus resolution, and auto-commits. Use when the user says "run autopilot", "execute workflow", "autonomous speckit", or has a workflow file ready for execution.
Archive a merged SpecKit spec, remove completed active specs, refresh roadmap and project-memory state, and prepare the cleanup PR after merge.
Autonomous SpecKit workflow executor. Reads a populated workflow file and runs all 7 SDD phases (specify → clarify → plan → checklist → tasks → analyze → implement) with programmatic gate validation, multi-agent consensus resolution, and auto-commits. Use when the user says "run autopilot", "execute workflow", "autonomous speckit", "autonomous execution", "kick off autopilot", "start the autonomous pipeline", "drive it through all the SDD phases", "run the whole thing autonomously", "full end-to-end speckit run", or hands over a populated SPEC-NNN-workflow.md file for end-to-end execution. Requires SpecKit CLI installed, constitution created, and a populated workflow file. Not for SDD methodology questions ($speckit-coach), pre-spec scoping ($grill-me), new-spec setup ($speckit-scaffold-spec), status checks ($speckit-status), or PR comment resolution ($speckit-resolve-pr).
Autonomous SpecKit workflow executor. Reads a populated workflow file and runs all 7 SDD phases (specify → clarify → plan → checklist → tasks → analyze → implement) with programmatic gate validation, multi-agent consensus resolution, and auto-commits. Use when the user says "run autopilot", "execute workflow", "autonomous speckit", "autonomous execution", "kick off autopilot", "start the autonomous pipeline", "drive it through all the SDD phases", "run the whole thing autonomously", "full end-to-end speckit run", or hands over a populated SPEC-NNN-workflow.md file for end-to-end execution. Requires SpecKit CLI installed, constitution created, and a populated workflow file. Not for SDD methodology questions ($speckit-coach), pre-spec scoping ($grill-me), new-spec setup ($speckit-scaffold-spec), status checks ($speckit-status), or PR comment resolution ($speckit-resolve-pr).
Archive a merged SpecKit spec and clean active workflow residue after the implementation PR has merged. Use after confirming merge provenance, when the user asks for post-merge SpecKit archive hygiene, cleanup hygiene, or removal of completed specs from active specs.
| name | speckit-validate |
| description | Verify spec-to-task traceability and check that completed tasks produced expected files |
| compatibility | Requires spec-kit project structure with .specify/ directory |
| metadata | {"author":"github-spec-kit","source":"speckit-utils:commands/validate.md"} |
$ARGUMENTS
Deterministically verify that the implementation matches the specification by checking task completion, file existence, and requirement traceability.
If $ARGUMENTS specifies a feature name or number, use that. Otherwise, find the most recently modified feature in specs/.
If no features exist, error: "No features found in specs/. Run /speckit.specify first."
Read tasks.md from the feature directory. Parse each checkbox line:
- [x] or - [ ])auth/login.py), snake_case names (user_auth), CamelCase names (UserAuth), dotted names (config.yaml)If no tasks.md exists, error: "No tasks.md found. Run /speckit.tasks first."
For each completed task that references file paths:
Skip verification for:
Read spec.md from the feature directory. Extract items from the "Functional Requirements" section (bulleted list items under that heading).
If no requirements section found, skip to Step 6.
For each requirement, search task descriptions for matching keywords:
Report:
Output a validation report:
Validation Report: 001-auth
============================
Task Completion: 3/5 (60%)
[x] Task 1: Create auth/login.py -> auth/login.py FOUND
[x] Task 2: Add password hashing -> (no file reference)
[x] Task 3: Write auth tests -> tests/test_auth.py FOUND
[ ] Task 4: Add rate limiting -> (not yet implemented)
[ ] Task 5: Update API docs -> (not yet implemented)
Requirement Traceability: 3/3
"Users can log in with email" -> Task 1 (PASS)
"Passwords are stored securely" -> Task 2 (PASS)
"Users can reset password via email" -> (no matching task - WARN)
Summary: 2 PASS, 1 WARN, 0 FAIL
If $ARGUMENTS includes --strict, treat any WARN as FAIL and report a non-zero exit status.