verification-before-completion

Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready. Requires fresh verification output before success claims. Do not use for root-cause debugging, TDD implementation, test-report packaging, or review-feedback triage.

Quality

81%

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

Quality

Content

81%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 is a tightly written, highly actionable verification gate with explicit validation and feedback loops. Its only real weakness is moderate cross-section redundancy that could be consolidated to save tokens without losing clarity.

Suggestions

Consolidate the overlapping message of 'Red Flags', 'Rationalization Prevention', 'Common Failures', and 'Key Patterns' — they each restate 'no claim without fresh evidence'; merging Red Flags into Rationalization Prevention would cut ~15 lines.

The 'When To Apply' section largely restates the description's trigger list; consider trimming it to the single novel note (paraphrases/synonyms/implications also count) to avoid duplication.

Dimension	Reasoning	Score
Conciseness	Terse, imperative, and free of concepts Claude already knows; the main cost is thematic redundancy across Red Flags, Rationalization Prevention, Common Failures, and Key Patterns, each restating 'no claim without evidence' from a slightly different angle.	4 / 5
Actionability	The Gate Function gives concrete sequenced instructions (IDENTIFY/RUN/READ/VERIFY) and the Common Failures table maps each claim to required evidence with explicit ✅/❌ examples, though the 'commands' are abstract ('run the test command') rather than specific invocations, which fits a meta-skill.	4 / 5
Workflow Clarity	The Gate Function is a clear 5-step sequence with an explicit validation checkpoint (step 4 VERIFY) and a feedback loop (If NO → state actual status; If YES → claim with evidence), supported by checklists in Common Failures and Key Patterns.	5 / 5
Progressive Disclosure	Single-file skill with no bundle references (references/, scripts/, assets/ are empty) and well-organized section headers; all content is appropriately inline for a behavioral guardrail, with no nested references to evaluate.	4 / 5
	Total	17 / 20 Passed

Description

82%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.

The description is well-crafted: third-person, explicit what-and-when, concrete trigger phrases, and a sharp disambiguation boundary against related skills. Its only weakness is modest action breadth, which fits a single-purpose guardrail skill.

Dimension	Reasoning	Score
Specificity	Names the domain ('Completion-evidence route') and a concrete action ('Requires fresh verification output before success claims'), but does not enumerate a comprehensive set of distinct actions — it is a single-purpose guardrail rather than a multi-capability tool.	3 / 5
Completeness	Explicitly answers both what ('Completion-evidence route... Requires fresh verification output before success claims') and when ('used before claiming work is complete, fixed, passing, committed, or PR-ready') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural completion-state phrases users and Claude would say ('complete, fixed, passing, committed, or PR-ready') with good keyword coverage, though a few common synonyms (e.g. 'done', 'shipped', 'green') are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche with an explicit 'Do not use for root-cause debugging, TDD implementation, test-report packaging, or review-feedback triage' boundary, minimizing overlap with adjacent skills.	5 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/verification-before-completion/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.