skills.rest
cbrostrom
cbrostromCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

verification-before-completion

Requires running verification commands and reading output before claiming work is complete.

Updated Nov 25, 2024
Search Tags:#code quality#testing#verification#test-driven development#evidence#agent discipline#completion claims
One-click install
npx skills add https://github.com/cbrostrom/dotfiles --skill verification-before-completion-cbrostrom
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/cbrostrom/dotfiles/tree/main/stow/agents/.agents/skills/verification-before-completion
Command: npx skills add https://github.com/cbrostrom/dotfiles --skill verification-before-completion-cbrostrom

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim work is done, tests pass, or bugs are fixed without actually running the verification commands, leading to broken code, lost trust, and wasted rework. This Skill enforces an evidence-first discipline so no completion claim is made without fresh command output. ## Core Features & Use Cases - Verification Gate: A five-step gate function (identify, run, read, verify, claim) that must be completed before any success statement. - Claim-to-Evidence Mapping: A table defining what proof each claim requires, such as test output with zero failures or a build exiting with code 0. - Rationalization Blocking: Explicit counters for common excuses like "should work", "linter passed", or "agent said success". - Use Case: Before committing a bug fix, the agent runs the full test suite, confirms zero failures in the output, and only then reports the fix as verified with the evidence attached. ## Quick Start Before you claim this task is complete, run the full verification command, read the output, and report the result with evidence.

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 work is complete before committing code?▼

Identify the command that proves the claim, run it fresh and in full, read the entire output including exit code and failure counts, then state the claim only with that evidence attached. Skipping any step counts as an unverified claim.

What evidence is required before claiming tests pass?▼

Claiming tests pass requires the actual test command output showing zero failures from a fresh run. Previous runs, partial checks, or assumptions that the code should pass are not sufficient evidence.

Does a passing linter mean the build succeeds?▼

No, a passing linter does not prove the build succeeds because linters do not check compilation. You must run the actual build command and confirm it exits with code 0 before claiming the build passes.

How do I verify a regression test actually works?▼

Verify a regression test with a 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 unverified.

Can I trust an agent's success report without checking?▼

No, agent success reports must be independently verified by inspecting the version control diff and confirming the actual changes match the claimed work. Trusting the report alone is listed as a common failure mode.

Related Skills

Explore More Software Engineering Skills→
dwbdwb

test-driven-development

Guide writing a failing test before implementing code to pass it.

Community
Basic
basicmachines-cobasicmachines-co
4.0k

pr-create

Creates or updates Basic Memory pull requests and runs the Codex review loop.

Official
Intermediate
Rawgrowth-ConsultingRawgrowth-Consulting

requesting-code-review

Verify code changes with static security scans and quality gates before git commits.

Official
Advanced
mahg-esmahg-es
3

cicd-quality

Design and enforce CI/CD quality gates for code, tests, security, build, E2E, and performance.

Official
Advanced