This skill should be used when claiming a task is "done", "complete", "finished", "fixed", "passing", or before committing. Requires running verification commands before making success claims.
Enforces evidence-based claims by requiring fresh verification command execution before any completion statements. Automatically triggers when you're about to claim success, finish tasks, or commit changes.
/plugin marketplace add pproenca/dot-claude/plugin install dev-workflow@pproencaThis skill is limited to using the following tools:
Announce at start: "I'm using the verification-before-completion skill to verify this work."
Claiming work is complete without verification is dishonesty, not efficiency.
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
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
ALWAYS before:
Rule applies to:
CRITICAL: Do not trust agent success reports.
Agent reports "success" → Verify independently
1. Check VCS diff: git diff HEAD~1
2. Verify changes exist and match expectations
3. Run verification commands yourself
4. THEN report actual state
Agents may:
Always verify, never trust.
| 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 |
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ tests ≠ build |
| "Agent said success" | Verify independently |
| "Partial check is enough" | Partial proves nothing |
✅ [Run npm test] [See: 34/34 pass] "All tests pass"
❌ "Should pass now"
✅ [Run build] [See: exit 0] "Build succeeds"
❌ "Linter passed" (linter doesn't verify build)
✅ Re-read plan → Checklist each item → "Requirements met"
❌ "Tests pass, phase complete" (tests ≠ requirements)
From real failure patterns:
Violates: "Honesty is a core value. If you lie, you'll be replaced."
| Approach | Outcome |
|---|---|
| Claim without verification | 60% rework rate, broken trust |
| Verify then claim | 5% rework rate, high confidence |
| Time to verify | 30 seconds |
| Time to fix false claims | Hours of debugging + trust repair |
The math is clear: 30 seconds verification beats hours of rework.
No shortcuts for verification.
Run the command. Read the output. THEN claim the result.
This is non-negotiable.
This principle applies at every claim point:
Triggers independently when making claims outside formal workflows.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.