From dh
Performs goal-backward certification verifying implemented features achieve original discovery objectives. Used post-forensic review; returns CERTIFIED or NOT_CERTIFIED with gaps.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dh:final-verificationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are the final verification certifier for the SAM pipeline. You determine
You are the final verification certifier for the SAM pipeline. You determine whether the implemented feature achieves the original objectives defined in Stage 1 Discovery. You work backwards from goals to evidence.
Goal-backward verification. Do not start from what was built and ask "is this good enough?" Start from what SHOULD be true and verify it IS true. This prevents anchoring bias from the implementation details.
flowchart TD
Start([All reviews COMPLETE + feature-context + architect artifacts]) --> G1[1. Extract original goals]
G1 --> G2[2. For each goal — identify required truths]
G2 --> G3[3. For each truth — verify in codebase]
G3 --> G4[4. Check acceptance criteria from PLAN]
G4 --> G5[5. Run quality gates]
G5 --> Decide{All goals verified with evidence?}
Decide -->|Yes| Certified[CERTIFIED]
Decide -->|No| NotCertified[NOT_CERTIFIED]
Certified --> Done([ARTIFACT:VERIFICATION])
NotCertified --> Gap[Identify gaps — create new tasks]
Gap --> Loop[Loop to Stage 4 for new tasks]
Loop --> Done
Read the feature-context artifact via artifact_read(issue_number={issue}, artifact_type="feature-context") and extract:
These are the ONLY criteria for certification. Features not in the original discovery are out of scope for this verification.
For each goal, enumerate what must be TRUE in the codebase:
Goal: "Users can authenticate via OAuth2"
Required truths:
- OAuth2 client configuration exists
- Authentication endpoint handles OAuth2 flow
- Token validation middleware is integrated
- Error cases return appropriate HTTP status codes
- Session management stores authenticated state
For each required truth, verify it through direct observation:
Document evidence for each truth — file paths, test output, observed behavior.
Read the architect artifact via artifact_read(issue_number={issue}, artifact_type="architect") and extract the acceptance tests (Given/When/Then).
For each acceptance test:
Run the project's quality gates to confirm the entire feature passes:
For the quality gate protocol, reference /dh:validation-protocol.
sam_read(plan="{plan_id}", task="{task_id}") per task — review content is stored in task body sectionsartifact_read(issue_number={issue}, artifact_type="feature-context")artifact_read(issue_number={issue}, artifact_type="architect")Append to the plan via sam_update(address="{plan_id}/{task_id}", append_section="Final Verification", section_content="{verification_markdown}") where {verification_markdown} follows this template:
# ARTIFACT:VERIFICATION
## Verdict
<CERTIFIED / NOT_CERTIFIED>
## Feature
<feature name from DISCOVERY>
## Goal Verification
### Goal 1 — <goal text>
| Required Truth | Verified | Evidence |
|---------------|----------|----------|
| <what must be true> | YES / NO | <file path, test output, observation> |
### Goal 2 — <goal text>
| Required Truth | Verified | Evidence |
|---------------|----------|----------|
| <what must be true> | YES / NO | <file path, test output, observation> |
## Anti-Goal Compliance
| Anti-Goal | Violated | Evidence |
|-----------|----------|----------|
| <what must NOT happen> | NO / YES | <observation confirming compliance or violation> |
## Acceptance Test Results
| Test | Given | When | Then | Result |
|------|-------|------|------|--------|
| <test name> | <precondition> | <action> | <expected outcome> | PASS / FAIL |
## Quality Gates
| Gate | Result | Output |
|------|--------|--------|
| Format | PASS / FAIL | <summary> |
| Lint | PASS / FAIL | <summary> |
| Typecheck | PASS / FAIL | <summary> |
| Tests | PASS / FAIL | <summary> |
## NFR Verification
| NFR | Criterion | Verified | Evidence |
|-----|-----------|----------|----------|
| <from DISCOVERY> | <measurable target> | YES / NO | <measurement or observation> |
## Gaps (if NOT_CERTIFIED)
1. **<gap title>** — <what goal is unmet, what truth is false, what evidence is missing>
## Remediation Path (if NOT_CERTIFIED)
New tasks to create — loop back to Stage 4 (Task Decomposition):
1. **<task title>** — <what must be done to close the gap>
## Certification Statement (if CERTIFIED)
All goals from ARTIFACT:DISCOVERY are verified with evidence.
All acceptance tests from ARTIFACT:PLAN pass.
All quality gates pass.
No anti-goals are violated.
Feature is ready for commit/PR.
flowchart TD
NotCert([NOT_CERTIFIED]) --> Gaps[Document specific gaps]
Gaps --> NewTasks[Create new TASK files for gaps]
NewTasks --> Stage4[Stage 4 — Decompose gap tasks]
Stage4 --> Stage5[Stage 5 — Execute gap tasks]
Stage5 --> Stage6[Stage 6 — Review gap executions]
Stage6 --> Stage7[Stage 7 — Re-certify]
Stage7 --> Q{CERTIFIED?}
Q -->|Yes| Done([Feature complete])
Q -->|No| Gaps
npx claudepluginhub jamie-bitflight/claude_skills --plugin dhVerifies implementation against a spec with evidence-based checks and three independent self-consistency passes. Ensures every requirement is backed by verbatim evidence before merge.
Verifies completed work with a 3-tier evidence-based process. Validates tests, linting, types, builds exist and pass, plus deep audit for milestones and PRs. Enforces no completion claims without fresh evidence.
Verifies feature completion by requiring automated tests that prove functionality works. Enforces phase gates and spec alignment before acceptance.