openspec-verify-change

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/openspec-verify-change/SKILL.md

Quality

Content

65%

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 thorough, actionable verification workflow with executable commands and sensible degradation handling. Its main weaknesses are repetitive boilerplate that could be tightened and the reliance on inference-based verification rather than hard checkpoints.

Suggestions

Compress the repeated 'Recommendation:' boilerplate into a single format reference to cut length.

Replace fuzzy 'assess if implementation likely exists' checks with a deterministic verification step or explicit acceptance criteria.

Move the report templates and issue-priority structure into a referenced file to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Direct and imperative with no concept-explaining fluff, but the ~170-line body carries repetitive 'Recommendation:' boilerplate and verbose issue-list structures that could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands (openspec list/status/instructions with --json), exact checkbox-parsing rules, and a defined report format rather than vague direction.	3 / 3
Workflow Clarity	Eight well-sequenced steps with graceful-degradation branches, but the core verification relies on fuzzy keyword inference ('assess if implementation likely exists') rather than deterministic validation checkpoints, leaving the key check implicit.	2 / 3
Progressive Disclosure	Well-organized with clear section headers and no nested references, but everything is inline in SKILL.md with no bundle files; reusable report templates and heuristics could be split out.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 cleanly answers both what the skill does and when to use it with an explicit trigger clause and a distinct niche. It could be sharper by listing more concrete verification actions and using more natural, user-spoken phrasings.

Suggestions

List concrete verification actions explicitly (e.g., 'check tasks, audit spec requirements, verify scenario coverage') rather than abstract dimensions.

Add more natural user phrasings to the trigger (e.g., 'Use when the user asks to check their work is done or ready before archiving').

Dimension	Reasoning	Score
Specificity	Names the domain ('Verify implementation matches change artifacts') and three verification dimensions (complete, correct, coherent), but treats them as facets of one action rather than enumerating multiple distinct concrete operations.	2 / 3
Completeness	Clearly states what it does and provides an explicit 'Use when the user wants to validate...' trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	Includes relevant natural terms ('validate', 'complete', 'correct', 'before archiving') but they are fairly abstract and miss common casual phrasings a user might actually say.	2 / 3
Distinctiveness Conflict Risk	Tied to a niche (openspec change artifacts, archiving) with triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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: Fission-AI/OpenSpec
Path: skills/openspec-verify-change/SKILL.md
Commit: 19d4171

Reviewed: 5 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.