verification-before-completion
/verification-before-completion
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
- Author
- cloudfieldcz ↗
- Repository
- cf-powers ↗
- Licence
- MIT
- Last repository change
- 15.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 15.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
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
Original author description
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
How it works
- Overview
- The Iron Law
- The Gate Function
- Common Failures
- Verify the Outcome on Representative Data
- Seeing Is a Verification Command
- Red Flags - STOP
- Rationalization Prevention
- Key Patterns
- When To Apply
SKILL.md preview
---
name: verification-before-completion
description: 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
---
# 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 |
| UI change works | The affected screen opened in the running app and looked at (screenshot) | Component tests pass, testids assert |
| Feature is done | Every screen it touches seen running | Green suite, green build |
## Verify the Outcome on Representative Data
For changed user workflows or data transformations, run a representative
end-to-end scenario against a known expected result. Use realistic data structure
and relevant volume. Synthetic unit fixtures alone do not prove domain correctness.
Use authorized test data or anonymized equivalents. When the environment or data
is not available, report that verification gap explicitly.
## Seeing Is a Verification Command
Every row above except the last two is something a terminal prints. None of them can see a screen. For any change that alters a rendered surface, the verification step is: **open the app on that screen and look at it**, or capture a screenshot — via the built-in `run` skill, or Playwright (`browser_take_screenshot`) when it is available.
**Why:** a passing render test proves an element is in the DOM. It proves nothing about whether it has the shape a user recognises as a button. One branch shipped 4 234 lines of green tests, a green build and five review rounds, and its admin page rendered five of seven controls as bare text — the irreversible "reset" action was a scrap of red text. A person opened the page the next morning and saw it in one second. No command on this page could have.
## 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 |
| "Component tests pass, the UI is fine" | A testid in the DOM is not a button on a screen. Open it. |
## 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"
```
**Rendered surface:**
```
✅ [Open screen / screenshot] [See: controls render as buttons] "Page verified"
❌ "Render tests pass" (they assert presence, not appearance)
```
**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
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · cloudfieldcz/cf-powers | 100 | MIT |
| jjuraszek/pi-gauntlet | 100 | MIT |
| GanyuanRan/Aegis | 100 | MIT |
| mvschwarz/openrig | 100 | Apache-2.0 |
| nikospavlopoulos/devops-mutant-powers | 100 | MIT |
| FrancoStino/opencode-skills-collection | 100 | MIT |
| foryourhealth111-pixel/Vibe-Skills | 100 | Apache-2.0 |
| rootcastleco/rei-skills | 100 | MIT |
| Montinou/triqual | 100 | MIT |
Database snapshot: 13.11.2026 · package version 4cdd93680098 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100verify
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. - 100verifying-before-completion
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 - 100sr-verification-before-completion
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 - 100verify
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 - 100ferrox-verification-before-completion
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 - 90sp-verify
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