verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
80
72%
Does it follow best practices?
Impact
92%
1.22xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/verification-before-completion/SKILL.mdEvaluation results
90%
51%Math Utilities Module Debugging
Verification evidence in reports
Test runner output present
13%
100%
Before-fix failure evidence
20%
33%
After-fix passing evidence
26%
100%
Test command cited
0%
100%
No weasel words in success claim
100%
100%
Claim backed by evidence
40%
100%
No satisfaction without evidence
80%
100%
Test count specificity
50%
100%
98%
1%Statistics Module: Median Bug and Regression Test
Regression test red-green cycle
Red phase documented
100%
95%
Green phase documented
100%
100%
Revert step present
100%
100%
Actual command output
80%
93%
No weasel words in test validation claim
100%
100%
Test counts present
100%
100%
No premature completion claim
100%
100%
90%
UserProfile Module Review
Requirements line-by-line checklist verification
Per-requirement checklist
100%
100%
All requirements addressed
100%
100%
Evidence per item
100%
100%
Gap REQ-003 identified
100%
100%
Gap REQ-004 identified
100%
100%
Gap REQ-005 identified
100%
100%
No weasel words in verdicts
100%
100%
Code executed or tested
0%
0%
- Repository
- roman01la/skills-agents
- Commit
45417f2
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.