It requires the execution and review of verification commands before marking any task as complete.
Install
mkdir -p .claude/skills/verification-before-completion && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/631" && unzip -o skill.zip -d .claude/skills/verification-before-completion && rm skill.zipInstalls to .claude/skills/verification-before-completion
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysKey capabilities
- →Execute verification commands
- →Validate exit codes and output
- →Confirm test pass results
- →Verify bug fix success
How it works
It mandates running a fresh verification command and confirming the output before any completion claim can be made.
Inputs & outputs
When to use verification-before-completion
- →Verifying test pass results
- →Checking linting output
- →Confirming bug fix success
About this skill
Verification Before Completion
Overview
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
The Gate Function
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence
5. ONLY THEN: Make the claim
Skip any step = lying, not verifying
Common Failures
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |
Red Flags - STOP
- Using "should", "probably", "seems to"
- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
- About to commit/push/PR without verification
- Trusting agent success reports
- Relying on partial verification
- Thinking "just this once"
- Tired and wanting work over
- ANY wording implying success without having run verification
Rationalization Prevention
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler |
| "Agent said success" | Verify independently |
| "I'm tired" | Exhaustion ≠ excuse |
| "Partial check is enough" | Partial proves nothing |
| "Different words so rule doesn't apply" | Spirit over letter |
Key Patterns
Tests:
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"
Regression tests (TDD Red-Green):
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
Build:
✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)
Requirements:
✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"
Agent delegation:
✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report
When To Apply
ALWAYS before:
- ANY variation of success/completion claims
- ANY expression of satisfaction
- ANY positive statement about work state
- Committing, PR creation, task completion
- Moving to next task
- Delegating to agents
Rule applies to:
- Exact phrases
- Paraphrases and synonyms
- Implications of success
- ANY communication suggesting completion/correctness
When not to use it
- →When skipping verification steps
Limitations
- →Requires manual execution of verification
- →Cannot automate the verification logic itself
How it compares
It enforces a strict gate function requiring evidence before assertions, preventing premature success claims.
Compared to similar skills
verification-before-completion side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| verification-before-completion (this skill) | 9 | 10mo | No flags | Beginner |
| mutation-testing | 5 | 5mo | Review | Advanced |
| workflow-patterns | 1 | 2mo | No flags | Intermediate |
| tdd-workflows-tdd-refactor | 1 | 4mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by obra
View all by obra →You might also like
mutation-testing
metabase
Run mutation testing on a Clojure namespace, generate tests to kill surviving mutations, and open draft PRs with Linear issue tracking.
workflow-patterns
wshobson
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
tdd-workflows-tdd-refactor
sickn33
Use when working with tdd workflows tdd refactor
customaize-agent:create-hook
LAI-YEN-CHUN
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
qa
gmaiarviana
> **📌 Carregado por:** Claude Code Web após Dev marcar tasks como concluídas. > **📌 Documentação:** ver [README.md](README.md) para visão geral.
qc
macro-inc
Quality gate. 5 parallel agents review changes. All must pass.