Verification Before Completion
This is a guard rail that forces you to actually run verification commands before claiming anything is done. It blocks the "looks good, tests should pass" reflex and requires fresh evidence for every completion claim. The five step pattern is simple: identify the verification command, run it completely, read the full output, verify it matches your claim, then and only then say you're done. The skill cites real numbers showing unverified work costs 60x more to fix than just running the test upfront. It's blunt about the core issue: claiming success without proof isn't efficiency, it's dishonesty. Use it as a pre-commit gate or whenever you're about to mark something complete.
- skills.sh installs
- 401
- GitHub stars
- 79
- last updated
- Aug 21, 2026
Install
$ npx -y skills add bobmatnyc/claude-mpm-skills --skill verification-before-completion --agent claude-codeInstalls into .claude/skills of the current project.
Files
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.
This skill enforces mandatory verification before ANY completion claim, preventing false positives, broken builds, and trust violations.
When to Use This Skill
Activate ALWAYS before claiming:
- Success, completion, or satisfaction ("Done!", "Fixed!", "Great!")
- Tests pass, linter clean, build succeeds
- Committing, pushing, creating PRs
- Marking tasks complete or delegating to agents
Use this ESPECIALLY when:
- Under time pressure or tired
- "Quick fix" seems obvious or confidence is high
- Agent reports success or tests "should" pass
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
Without running the verification command in this message, claiming success is not allowed.
Core Principles
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/bobmatnyc/claude-mpm-skills
- First seen
- Jun 3, 2026
More from bobmatnyc/claude-mpm-skills
All 158- Test Driven Development400
- Better Auth Authentication398
- Kysely398
- Kubernetes397
- Json Data Handling394
- Systematic Debugging391
- Vue390
- Api Documentation389
- Screenshot389
- Software Patterns382
- Nextjs V16380
- Vercel Deployments Builds378
- Security Scanning377
- Test Quality Inspector376
- Svelte5 Runes Static373
- Stacked Prs371
- Better Auth Core368
- Homebrew Formula Maintenance366
- Better Auth Integrations363
- Reporting Pipelines363
- Better Auth Plugins362
- Git Worktrees360
- Nextjs Core357
- Fastapi Local Dev356
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs