Menu

Individual skill

verification-before-completion

0upvotes

Verify work actually meets its brief BEFORE declaring it done — a structured self-review pass that catches the gaps, unmet requirements, and untested claims that 'looks finished' hides. Use when about to hand over any deliverable (document, code, analysis, plan), when past work kept coming back with 'you missed…', or as the standing final step of any multi-step task. Produces the verified deliverable plus a short verification record: what was checked, what was found and fixed, what remains open.

skills/verification-before-completion/SKILL.md

Read pinned source

Source commit f7c90bc09ee05dc25cf257bdb1826f2c2552c2cb

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,539
Repository last updated
Nov 10, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Verification Before Completion Skill

"Done" is a claim, and most agents (and humans) declare it by *feeling* — the output looks complete, reads well, compiles. This skill replaces the feeling with a check: re-derive what was actually asked, audit the work against it, try to break it, and only then hand it over. The gap between looks-done and is-done is where rework lives.

## What This Skill Produces

- The deliverable, **after** fixes the verification pass surfaced
- A **verification record** (3-8 lines): checked against what, found and fixed what, still open what
- Honest **residuals**: anything not verified, stated rather than implied

## The Verification Pass

1. **Re-read the ORIGINAL ask — not your memory of it.** Requirements decay in working memory over a long task; the third instruction in the user's message is the classic casualty. List every explicit requirement and every implicit one (format, tone, length, audience) as a checklist. *Then* audit the work against the list, item by item.
2. **Check the claims, not just the presence.** A section existing isn't the section being right. For each substantive claim/number/behaviour in the deliverable: is it grounded (traceable to input, source, or test) or asserted? Every ungrounded assertion either gets grounded, gets labelled as an assumption, or gets cut.
Back to top