skills.rest
Ab0umar
Ab0umarCOMMUNITY
Explore all skills by this author →
GitHub

verification-before-completion

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

Updated Sep 19, 2026
Search Tags:#code quality#testing#tdd#verification#evidence#CI#completion claims
One-click install
npx skills add https://github.com/Ab0umar/selrs.cc.BU --skill verification-before-completion-ab0umar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: verification-before-completion
Source: https://github.com/Ab0umar/selrs.cc.BU/tree/main/.codex/plugins/cache/openai-curated/superpowers/dc902811/skills/verification-before-completion
Command: npx skills add https://github.com/Ab0umar/selrs.cc.BU --skill verification-before-completion-ab0umar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often declare tasks done, bugs fixed, or tests passing 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 - The Iron Law: Blocks any success claim unless the verification command was run in the current message and its output confirms the claim. - Gate Function Workflow: A five-step process (identify command, run it fully, read output and exit code, verify against the claim, then report) applied before commits, PRs, or task handoffs. - Rationalization Prevention: Tables of common excuses ("should work", "linter passed", "agent said success") mapped to the required evidence, plus red-green regression test verification. - Use Case: Before committing a bug fix, run the test suite, confirm 0 failures in the output, and only then state "all tests pass" with the evidence attached. ## Quick Start Before you claim this task is complete, apply the verification-before-completion gate: run the full test or build 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 your claim, run it fresh and in full, read the entire output including exit code, and confirm it matches the claim. Only then state the result, citing the evidence such as "34/34 tests pass".

What counts as evidence that tests pass?▼

Evidence is the actual output of the test command run in the current session showing zero failures. A previous run, a partial check, or confidence that it "should pass" does not qualify as verification.

Does a passing linter mean the build succeeds?▼

No, a linter does not check compilation. Build success requires running the build command and confirming exit code 0; linter output alone is insufficient evidence for a build claim.

How do I verify a regression test actually works?▼

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

Can I trust a sub-agent's report that a task succeeded?▼

No, agent success reports must be verified independently. Check the version control diff to confirm the changes exist and match the claimed work before reporting the actual state.

When should verification before completion not be skipped?▼

Never. The rule applies before any success claim, expression of satisfaction, commit, PR, task handoff, or delegation, including paraphrases and implications of completion. There are no exceptions for confidence or fatigue.

Related Skills

Explore More Software Engineering Skills→
nobelknobelk

tdd-bugfix

Reproduce bugs with failing tests and verify fixes via the full test suite.

Community
Advanced
caitengweicaitengwei
6

verification-before-completion

Require fresh command execution and evidence before reporting completion status.

Community
Basic
Devsoul2026Devsoul2026
150

requesting-code-review

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

Community
Advanced
sicambriasicambria

deploy

Runs verified deploys with healthchecks, event logging, and automatic rollback on failure.

Community
Advanced