home / skills / ed3dai / ed3d-plugins / verification-before-completion

This skill enforces verification before claiming completion by running exact commands and presenting fresh evidence to support success claims.

This is most likely a fork of the verification-before-completion skill from obra
npx playbooks add skill ed3dai/ed3d-plugins --skill verification-before-completion

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
4.1 KB
---
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
user-invocable: false
---

# Verification Before Completion

## Overview

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.**

## 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
```

## Why This Matters

From 24 failure memories:
- your human partner said "I don't believe you" - trust broken
- Undefined functions shipped - would crash
- Missing requirements shipped - incomplete features
- Time wasted on false completion → redirect → rework
- Violates: "Honesty is a core value. If you lie, you'll be replaced."

## 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

## The Bottom Line

**No shortcuts for verification.**

Run the command. Read the output. THEN claim the result.

This is non-negotiable.

Overview

This skill enforces a strict verification-before-completion habit: never claim work is complete, fixed, or passing without fresh, executable evidence. It embeds a simple gate function you must follow before committing, creating PRs, or asserting success. The goal is concrete proof over confidence to prevent regressions and broken releases.

How this skill works

Before any positive statement about status, the skill guides you to identify the exact verification command, run it fully, and inspect the full output and exit code. If the output confirms the claim, include that evidence when you state completion; if it does not, report the real status with the failing evidence. The process blocks or flags any claim made without following these steps.

When to use it

  • Before committing code or opening a pull request
  • Before stating tests, lint, or builds pass
  • Before marking bugs as fixed or tasks as done
  • Before moving to the next task or milestone
  • Whenever delegating work to agents or automated tools

Best practices

  • Always run the exact verification command live in your environment (no remembered results)
  • Capture full command output and exit codes as evidence when claiming success
  • Use red-green verification for regressions: show failing before fix and passing after
  • Avoid language like "should", "probably", or "seems" when reporting status
  • Treat agent-reported success as a prompt to independently verify changes

Example use cases

  • Run the test suite and include the "0 failures" output line before saying "all tests pass"
  • Execute the build command and show exit 0 plus logs before merging a release branch
  • Reproduce a bug failing test, apply a fix, run the failing test to pass, and include both results in the PR
  • Run a linter and include exact error/warning counts before claiming the code is clean
  • Ask an agent to apply a change, then show the VCS diff and run verification commands before approving

FAQ

What counts as acceptable evidence?

Complete command output and exit code demonstrating the claimed state (e.g., test summary, build exit 0). Partial logs or agent messages are not sufficient.

Can I rely on previous verification runs?

No. You must run fresh verification where you are about to claim success; past runs can be referenced but not replace current evidence.