Use before claiming any work is complete, fixed, passing, or expressing satisfaction. Required before committing, creating PRs, moving to next task, or delegating to agents. Prevents claims without fresh verification evidence. Critical when tired or under pressure.
Mandatory verification protocol requiring fresh evidence before any completion claims. Triggers on "done", "fixed", "passes", or any success statement—forcing you to run verification commands and show output before claiming work is complete.
/plugin marketplace add astrosteveo/harness-mp/plugin install harness@harness-mpThis skill inherits all available tools. When active, it can use any tool Claude has access to.
This is the failure mode: "Tests pass" → user runs tests → tests fail → trust broken.
The fix: Run tests → see output → "Tests pass: 34/34" with evidence shown. </THE-RULE>
Claiming work is complete without verification is dishonesty, not efficiency.
Core principle: Evidence before claims, always.
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
| 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 |
| Work is committed | git status shows clean | "I committed earlier" |
| Docs are current | CLAUDE.md reflects changes | Assumed unchanged |
| Roadmap aligned | Phase marked if completing feature | Tests pass, moving on |
| Backlog aligned | Completed items marked | Assumed no matches |
| 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 |
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
Git worktree clean:
✅ [Run git status] [See: "nothing to commit, working tree clean"] "All changes committed"
❌ "I committed everything" (without checking)
CLAUDE.md current:
✅ Review changes made → Check if new patterns/conventions/frameworks → Update CLAUDE.md if needed
❌ Assume CLAUDE.md doesn't need updates
Roadmap alignment:
✅ Check ROADMAP.md → Mark phase complete if finishing feature → Update current marker
❌ Complete feature without checking roadmap
Backlog alignment:
✅ Scan BACKLOG.md → Mark matching items complete with commit SHA
❌ Assume no backlog items relate to this work
Silent failures - Did you actually do everything?
✅ Re-read task list → Check each item → Verify completion evidence for each
❌ "I did all the things" (without checking)
Before claiming completion, verify EACH claimed action:
| You Said | Verify By |
|---|---|
| "Created file X" | ls -la path/to/X - file exists |
| "Added function Y" | grep "function Y" file - function exists |
| "Tests pass" | Run tests NOW - see output |
| "Committed changes" | git log -1 - see commit |
| "Updated config" | Read config file - see change |
| "Installed dependency" | Check package.json/lock file |
| "Fixed the bug" | Reproduce original steps - bug gone |
Red flags for silent failures:
The pattern:
❌ "I created the file, added the function, and updated the tests."
✅ "I created the file:" [shows ls output]
"Added the function:" [shows grep output]
"Tests pass:" [shows test output]
From 24 failure memories:
ALWAYS before:
Rule applies to:
No shortcuts for verification.
Run the command. Read the output. THEN claim the result.
This is non-negotiable.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.