Verify
This is the skill that stops Claude from saying "I've fixed the bug" when it hasn't actually run the tests. It enforces a five-step gate before any completion claim: identify the proof command, run it fresh in this session, read the full output including exit codes, confirm it proves the claim, then report with evidence. No "should work" or "probably fixed" allowed. It includes a regression verification protocol for bug fixes that requires the test to fail without the fix and pass with it, proving the test actually catches the issue. The forbidden words list alone (should, probably, seems to, likely) is worth internalizing. If you've ever merged code based on an AI's confident assertion only to find it broken, this enforces the discipline you wished you'd had.
- GitHub stars
- 1.3K
- last updated
- Jun 11, 2026
Install
$ npx -y skills add codeaholicguy/ai-devkit --skill verify --agent claude-codeInstalls into .claude/skills of the current project.
Files
Verify
Prove it works before saying it works.
Hard Rules
- Do not claim completion without fresh terminal evidence from this session.
- Forbidden words in completion claims: "should", "probably", "seems to", "likely", "I believe", "I think it works". These signal unverified assertions.
- Cached, remembered, or previous-session output is not evidence. Run it again.
- A change that alters anything a user or caller sees requires a
dev-smokerun, whatever the claim is called.
Gate Function
Every completion claim must pass all steps in order:
- Classify — Does the change alter anything a user or caller sees (CLI output, API response, UI, displayed status or state, file formats)? If yes,
dev-smokeis required evidence alongside tests. - Identify — What command proves this claim? If multiple commands are needed, run the gate once per command.
- Run — Execute the full command now. No partial runs, no skipping.
- Read — Read complete output. Check exit code. Count pass/fail.
- Confirm — Does the output prove the exact claim?
- Report — State the result in the Report Format below.
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/codeaholicguy/ai-devkit
- Categories
- AI & Agent Building, Debugging
- First seen
- Jun 11, 2026
More from codeaholicguy/ai-devkit
All 12Recommended
More AI & Agent Building
Accessibility Engineerdaffy0208/ai-dev-standardsImplement accessibility (a11y) best practices to make applications usable by everyone. Use when building UIs, conducting accessibility audits, or ensuring WCAG 0skills.sh installsAsset Managerdaffy0208/ai-dev-standardsOrganize design assets, optimize images and fonts, maintain brand asset libraries, implement version control for assets, and enforce naming conventions. Keep de0skills.sh installsBMAD Methoddaffy0208/ai-dev-standardsBusiness Model and Architecture Design methodology for aligning technical architecture with business model sustainability and scalability0skills.sh installsdesign-system-architectdaffy0208/ai-dev-standardsBuild scalable, maintainable design systems that unify product experiences. Use when creating component libraries, design tokens, or establishing design standar0skills.sh installsFigma Developerdaffy0208/ai-dev-standardsExtract components from Figma, convert designs to React components, sync design tokens, and generate code from designs. Bridge the gap between design and code w0skills.sh installsFocus Session Managerdaffy0208/ai-dev-standardsAutomatically manage focus sessions, breaks, and hyperfocus protection. Uses ADHD-optimized Pomodoro technique with flexible timers, health reminders, and gentl0skills.sh installs