verification-before-completion skill
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 always
- GitHub stars
- 7
- Files
- 1
- Last commit
- Oct 4, 2026
- License
- MIT
- Allowed tools
- —
What does the verification-before-completion skill do?
verification-before-completion uses 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 always.
How to install the verification-before-completion skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the verification-before-completion skill in Plugin
/plugin marketplace add pickleshell/next-level-agent /plugin install superpowers@superpowers-dev
Install the verification-before-completion skill in Claude Code
~/.claude/skills/verification-before-completion/SKILL.md
$ npx degit pickleshell/next-level-agent/skills/verification-before-completion ~/.claude/skills/verification-before-completionInstall the verification-before-completion skill in Claude Code (project)
.claude/skills/verification-before-completion/SKILL.md
$ npx degit pickleshell/next-level-agent/skills/verification-before-completion .claude/skills/verification-before-completionInstall the verification-before-completion skill in Codex
~/.agents/skills/verification-before-completion/SKILL.md
$ npx degit pickleshell/next-level-agent/skills/verification-before-completion ~/.agents/skills/verification-before-completionInstall the verification-before-completion skill in Gemini CLI
~/.gemini/skills/verification-before-completion/SKILL.md
$ npx degit pickleshell/next-level-agent/skills/verification-before-completion ~/.gemini/skills/verification-before-completionInstall the verification-before-completion skill in Claude.ai
npx degit pickleshell/next-level-agent/skills/verification-before-completion verification-before-completion && zip -r verification-before-completion.zip verification-before-completion # claude.ai → Customize → Skills → + → Create skill → Upload a skill → verification-before-completion.zip
SKILL.md
View on GitHubVerification 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
Files in this skill
1verification-before-completion skill questions
How do I install the verification-before-completion skill in Claude Code?
Run npx degit pickleshell/next-level-agent/skills/verification-before-completion ~/.claude/skills/verification-before-completion. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the verification-before-completion skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.