KS
Killer-Skills

verification-before-completion — how to use verification-before-completion how to use verification-before-completion, verification-before-completion setup guide, what is verification-before-completion, verification-before-completion alternative, verification-before-completion vs testing, verification-before-completion install, verification-before-completion best practices

Verified
v1.0.0
GitHub

About this Skill

Essential for Code Review and QA Agents requiring evidence-based completion validation. Verification-before-completion is a core principle that mandates running verification commands and confirming output before claiming work is complete or passing

Features

Requires running verification commands before claiming completion
Mandates confirmation of output before making success claims
Enforces the Iron Law of no completion claims without fresh verification evidence
Supports gate function for expressing satisfaction only after verification
Ensures evidence-based assertions always

# Core Topics

obra obra
[71.9k]
[5546]
Updated: 3/6/2026

Quality Score

Top 5%
74
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add obra/superpowers/verification-before-completion

Agent Capability Analysis

The verification-before-completion MCP Server by obra is an open-source Categories.official integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use verification-before-completion, verification-before-completion setup guide, what is verification-before-completion.

Ideal Agent Persona

Essential for Code Review and QA Agents requiring evidence-based completion validation.

Core Value

Enforces rigorous verification protocols before claiming completion status, requiring fresh command execution and output confirmation to prevent premature success assertions. It provides a gate function against dishonesty by mandating evidence before claims.

Capabilities Granted for verification-before-completion MCP Server

Running verification commands before PR creation
Confirming test suite output before deployment
Validating fix completion before status reporting
Executing fresh verification in current context before claims

! Prerequisites & Limits

  • Requires access to command execution environment
  • Needs output analysis capabilities
  • Depends on available verification commands in context
Project
SKILL.md
3.8 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

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

ClaimRequiresNot Sufficient
Tests passTest command output: 0 failuresPrevious run, "should pass"
Linter cleanLinter output: 0 errorsPartial check, extrapolation
Build succeedsBuild command: exit 0Linter passing, logs look good
Bug fixedTest original symptom: passesCode changed, assumed fixed
Regression test worksRed-green cycle verifiedTest passes once
Agent completedVCS diff shows changesAgent reports "success"
Requirements metLine-by-line checklistTests 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

ExcuseReality
"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.

Related Skills

Looking for an alternative to verification-before-completion or building a Categories.official AI Agent? Explore these related open-source MCP Servers.

View All

flags

Logo of facebook
facebook

flags is a feature flag management system that enables developers to check flag states, compare channels, and debug feature behavior differences across release channels.

243.6k
0
Design

extract-errors

Logo of facebook
facebook

extract-errors is a skill that assists in extracting and managing error codes in React applications using yarn extract-errors command.

243.6k
0
Design

fix

Logo of facebook
facebook

fix is a technical skill that resolves lint errors, formatting issues, and ensures code quality in declarative, frontend, and UI projects

243.6k
0
Design

flow

Logo of facebook
facebook

Flow is a type checking system for JavaScript, used to validate React code and ensure consistency across applications

243.6k
0
Design