General

verification-before-completion - Claude MCP 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

SEO Guide: Enhance your AI agent with the verification-before-completion tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to use when about to claim work is complete, fixed, or passing, before committing or creating prs - req... Download and configure this skill to unlock new capabilities for your AI workflow.

🌟20737 stars • 27678 forks
šŸ“„0 downloads

Documentation

SKILL.md
# 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:**
```
āœ… [Run test command] [See: 34/34 pass] "All tests pass"
āŒ "Should pass now" / "Looks correct"
```

**Regression tests (TDD Red-Green):**
```
āœ… Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
āŒ "I've written a regression test" (without red-green verification)
```

**Build:**
```
āœ… [Run build] [See: exit 0] "Build passes"
āŒ "Linter passed" (linter doesn't check compilation)
```

**Requirements:**
```
āœ… Re-read plan → Create checklist → Verify each → Report gaps or completion
āŒ "Tests pass, phase complete"
```

**Agent delegation:**
```
āœ… Agent reports success → Check VCS diff → Verify changes → Report actual state
āŒ 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

Signals

Avg rating⭐ 0.0
Reviews0
Favorites0

Information

Repository
obra/superpowers
Author
obra
Last Sync
11/2/2026
Repo Updated
11/2/2026
Created
1/12/2026

Reviews (0)

No reviews yet. Be the first to review this skill!

Related Skills

CLAUDE

Claude-Mem: AI Development Instructions

⭐ 55307

firecrawl-build-onboarding

Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser auth flow, so it does not depend on the website onboarding skill.

⭐ 39577

firecrawl-build

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.

⭐ 39577

firecrawl-build-scrape

Integrate Firecrawl `/scrape` into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.

⭐ 39577

Related Guides