skills.rest
danieliudi
danieliudiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

verification-before-completion

Enforces running verification commands before claiming work is complete or passing.

Updated Aug 26, 2026
Search Tags:#code quality#testing#verification#evidence#regression testing#ci#completion claims
One-click install
npx skills add https://github.com/danieliudi/trackforge-os --skill verification-before-completion-danieliudi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/danieliudi/trackforge-os/tree/main/.cursor/skills/verification-before-completion
Command: npx skills add https://github.com/danieliudi/trackforge-os --skill verification-before-completion-danieliudi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It prevents premature or false completion claims by requiring fresh verification evidence—test output, build exit codes, linter results—before any success statement, commit, or PR is made. ## Core Features & Use Cases - Evidence Gate: Defines a five-step gate (identify, run, read, verify, claim) that must be completed before asserting any status. - Failure Pattern Catalog: Maps common claims (tests pass, build succeeds, bug fixed) to the exact evidence each requires and what is not sufficient. - Rationalization Blocking: Lists red flags and excuse patterns like "should work" or "agent said success" that signal unverified claims. - Use Case: Before committing a bug fix, run the original failing test, confirm it passes, then state the fix is verified with the actual output as evidence. ## Quick Start Ask the assistant to verify the fix by running the full test suite and only claim completion after confirming zero failures in the output.

Frequently Asked Questions about verification-before-completion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify code changes before committing?▼

Identify the command that proves your claim, run it fresh and completely, read the full output including exit code, and only then state the result. For example, run the test suite and confirm zero failures before claiming tests pass.

What counts as evidence that a bug is fixed?▼

A bug is fixed only when a test reproducing the original symptom passes after the change. Code edits alone, assumptions, or a previous successful run do not count as evidence.

How do I verify a regression test actually works?▼

Use the red-green cycle: write the test, confirm it passes with the fix, revert the fix and confirm it fails, then restore the fix and confirm it passes again. A test that only passes once is not verified.

Can I trust a linter passing as proof the build works?▼

No. A linter passing does not prove compilation succeeds. You must run the actual build command and confirm exit code 0 before claiming the build passes.

Should I trust an agent's report that a task succeeded?▼

No. Independently verify agent claims by checking the version control diff and confirming the changes exist and work. Agent success reports are not evidence.

Related Skills

Explore More Software Engineering Skills→
jnyrossjnyross

tdd

Writes a failing regression test before fixing a bug with a clear test path.

Community
Intermediate
compozycompozy
2.7k

cy-final-verify

Enforces fresh verification evidence before completion claims, commits, and PR creation.

Official
Advanced
Devsoul2026Devsoul2026
150

requesting-code-review

Automate pre-commit verification with static analysis, tests, and lint checks.

Community
Advanced
hotriluanhotriluan
3

code-review

Request code reviews via a dedicated subagent enforcing verification gates before completion claims.

Community
Basic