skills.rest
dallascrilley
dallascrilleyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

Verification Before Completion

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

Updated Dec 4, 2025
Search Tags:#code quality#testing#debugging#verification#evidence#ci#completion claims
One-click install
npx skills add https://github.com/dallascrilley/dowser --skill verification-before-completion-dallascrilley
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Verification Before Completion
Source: https://github.com/dallascrilley/dowser/tree/main/skills/verification-before-completion
Command: npx skills add https://github.com/dallascrilley/dowser --skill verification-before-completion-dallascrilley

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers often claim tasks are done, tests pass, or bugs are fixed without actually running the verification command, leading to broken code, lost trust, and wasted rework. This Skill blocks any completion claim until fresh command output proves it. ## Core Features & Use Cases - The Iron Law: No completion claims without fresh verification evidence from a command run in the current message. - The Gate Function: A five-step checklist (identify, run, read, verify, claim) applied before any success statement, commit, or PR. - Rationalization Prevention: A table of common excuses ("should work", "linter passed", "agent said success") mapped to why each is invalid. - Use Case: Before telling your team a bug fix is done, run the failing test, confirm it passes, verify the regression test fails without the fix, and only then report completion with the evidence. ## Quick Start Ask the agent to verify all tests, builds, and linters pass with fresh command output before claiming the current task is complete.

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 before claiming a task is complete?▼

Identify the command that proves the claim, run it fresh and in full, read the complete output including exit codes, and only then state the claim with that evidence. Skipping any step means the claim is unverified.

How to 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 the test fails, then restore the fix and confirm it passes again. A test that never fails proves nothing.

Does a passing linter mean the build succeeds?▼

No. A linter checks style and static issues but does not verify compilation. You must run the actual build command and confirm exit code 0 before claiming the build succeeds.

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

No. Agent success reports must be independently verified by inspecting the VCS diff and confirming the changes exist and work. Trusting the report alone is listed as a common failure mode.

When should verification be skipped for small changes?▼

Never. The skill explicitly rejects exceptions like "just this once" or partial checks, stating that skipping verification steps is equivalent to making an unverified claim regardless of change size.

Related Skills

Explore More Software Engineering Skills→
adschilladschill

tdd-development

Enforces test-first workflow for code changes with focused failing tests and verification.

Community
Intermediate
SeanChenRSeanChenR

verification-before-completion

Require fresh verification commands and output inspection before completion claims.

Community
Intermediate
hoanghd218hoanghd218

debug

Trace bugs to root causes using systematic debugging phases and validation.

Community
Advanced
autoclaw-ccautoclaw-cc
1.7k

xhs-auth

Automate Xiaohongshu login status checks and QR or phone verification via CLI.

Official
Intermediate