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

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/verification-before-completion/SKILL.md

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers an actionable, validation-gated workflow well suited to an instruction-only discipline skill. Its main weakness is conciseness: three sections redundantly hammer the same evidence-before-claims message and could be merged.

Suggestions

Merge 'Red Flags - STOP' and 'Rationalization Prevention' into a single table — they restate the same no-claims-without-evidence message and inflate the body without adding new guidance.

Replace placeholder command templates in Key Patterns (e.g. '[Run test command]') with one or two concrete example invocations so the ✅ cases are copy-paste-ready rather than schematic.

Consolidate 'Common Failures' and 'Key Patterns' so each claim-type appears once with its required evidence, eliminating the duplicated Tests/Build/Requirements rows.

Dimension	Reasoning	Score
Conciseness	Style is terse, but the same core idea (no claims without evidence) is reinforced across three overlapping sections — 'Common Failures', 'Red Flags - STOP', and 'Rationalization Prevention' — so the body could be tightened; not a 4 because the redundancy is noticeable padding rather than a single stray explanation.	3 / 5
Actionability	Provides concrete executable guidance: the five-step Gate Function (IDENTIFY/RUN/READ/VERIFY/ONLY THEN) and ✅/❌ Key Patterns with literal command templates like '[Run test command] [See: 34/34 pass]'; not a 5 because several examples remain template placeholders rather than fully copy-paste-ready commands.	4 / 5
Workflow Clarity	The Gate Function is a clearly sequenced workflow with an explicit validation checkpoint (step 4 VERIFY) and a feedback branch ('If NO: State actual status with evidence'), plus the regression red-green cycle — exactly the validation-gated pattern the rubric rewards.	5 / 5
Progressive Disclosure	Single self-contained file with clear section headers and no need for external references, so structure is good; not a 5 because the body exceeds 50 lines and carries redundant sections that would be better consolidated than split, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, trigger-rich description that explicitly covers both what the skill does and when to apply it, with concrete actions and natural synonyms. Minor gains are possible by adding a few more colloquial completion terms ('done', 'shipped', 'green').

Dimension	Reasoning	Score
Specificity	Names concrete actions ('running verification commands and confirming output', 'before committing or creating PRs', 'before making any success claims') with only minor gaps in coverage; not a 5 because it lists procedure steps rather than a comprehensive catalog of distinct capabilities.	4 / 5
Completeness	Explicitly answers both: 'when' ('Use when about to claim work is complete, fixed, or passing, before committing or creating PRs') and 'what' ('requires running verification commands and confirming output before making any success claims'), with concrete trigger phrases throughout.	5 / 5
Trigger Term Quality	Covers natural trigger terms and synonyms ('complete, fixed, or passing', 'committing', 'creating PRs', 'verification'); a few natural variations (e.g. 'done', 'shipped', 'tests green') are missing, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (evidence-before-claims discipline tied to completion/commit/PR moments) with minimal conflict risk; not a 5 because the broad notion of 'verification' could lightly overlap with general testing/linting skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: obra/superpowers
Path: skills/verification-before-completion/SKILL.md
Commit: b36e082

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.