verification-before-completion

Review and validate completion claims. Use when you are about to say work is complete, fixed, passing, pushed, or ready for review.

Quality

73%

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/agent-ops/verification-before-completion/SKILL.md

Quality

Content

70%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.

A concise, well-sequenced instruction-only skill with strong validation feedback loops and clear workflow checkpoints. Its main weaknesses are the lack of concrete executable examples and a Progressive Disclosure section whose referenced paths don't match the real bundle files.

Suggestions

Add at least one concrete, copy-paste-ready example command or checklist template (e.g., a sample test-rerun invocation) to lift actionability above directive-only guidance.

Reconcile the Progressive Disclosure paths with the actual bundle: either point to references/contract.yaml, evals.yaml, and task-profile.json, or remove the stale Infrastructure/references/* pointers that have no matching files.

Remove the verbatim re-statement of the description in the body's opening line and tighten overlapping sections (Philosophy vs. When To Use vs. Avoid) to recover a few tokens.

Dimension	Reasoning	Score
Conciseness	Lean, bulleted, and free of explanations Claude already knows, but the body's first line repeats the description verbatim and several sections (Philosophy/When To Use/Avoid) slightly overlap, leaving minor trims, so not a 5.	4 / 5
Actionability	Guidance is concrete and directive ('Inspect 2-3 focused surfaces', 'Rerun the relevant validation after fixes') but offers no literal executable commands or copy-paste examples, matching the anchor for actionable-but-incomplete guidance.	3 / 5
Workflow Clarity	The numbered Workflow has explicit validation checkpoints and a validate->fix->rerun feedback loop (steps 4-5 plus the Validation section's fail-fast gate), fully matching the 5 anchor; the destructive/batch cap does not apply since the skill forbids destructive ops and includes loops.	5 / 5
Progressive Disclosure	A Progressive Disclosure section signals references, but the cited paths (Infrastructure/references/software-literature-*.md, deferred-skill-context/...) do not match the actual bundle files present (references/contract.yaml, evals.yaml, task-profile.json), so references are misaligned rather than clearly navigable.	3 / 5
	Total	15 / 20 Passed

Description

76%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 tight, well-structured description that clearly answers what the skill does and when to trigger it, with natural user-facing trigger phrases. It is held back from the top band only by narrow action coverage and minor overlap with adjacent review skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('completion claims') and two concrete actions ('Review and validate'), matching the anchor for 1-2 concrete actions without comprehensive coverage, so not a 4.	3 / 5
Completeness	Explicitly states both the 'what' ('Review and validate completion claims') and the 'when' ('Use when you are about to say work is complete, fixed, passing, pushed, or ready for review') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	'work is complete, fixed, passing, pushed, or ready for review' gives strong natural-phrase coverage with synonyms, but lacks file extensions and is domain-narrow, just short of comprehensive (5).	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (verifying completion claims) with distinct triggers, but 'verify work is done' lightly overlaps with general testing/PR-review skills, so not a 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Skills/agent-ops/verification-before-completion/SKILL.md
Commit: a3808a9

Reviewed: 18 minutes 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.