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

76%

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 ./.agent/skills/openspec-verify-change/SKILL.md

Quality

Content

75%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 thorough, well-structured verification workflow with concrete commands, a clear report schema, and sensible degradation rules. Its main gaps are vague heuristic search steps and the absence of explicit re-validation feedback loops, plus some inline content that could be externalized.

Suggestions

Make the spec/scenario search steps executable by specifying a concrete approach (e.g., `grep -r "<keyword>" --include="*.ts"` or a defined ripgrep pattern) instead of "search codebase for keywords".

Add an explicit re-validation loop: after the user addresses CRITICAL/WARNING issues, re-run `openspec status` and re-check before issuing the final archive-ready assessment.

Consider moving the full report template and Verification Heuristics into a referenced file to reduce inline length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is task-oriented and mostly efficient, with concrete commands and report structure rather than concept explanations. Not a 5 because some sections (Graceful Degradation, Verification Heuristics) restate logic already implied by the numbered steps; not a 3 because there is no significant padding of concepts Claude already knows.	4 / 5
Actionability	Provides executable CLI commands (`openspec list --json`, `openspec status --change "<name>" --json`), a concrete report structure, and specific issue/recommendation templates. Not a 5 because several heuristic steps are vague ("search codebase for keywords", "assess if implementation likely exists") without a concrete search command or method.	4 / 5
Workflow Clarity	Clear 8-step numbered sequence with graceful-degradation handling and false-positive guidance providing implicit checkpoints. Not a 5 because there are no explicit validation/re-verification feedback loops (e.g., re-run status after fixes); the destructive/batch cap does not apply since this is a read-only verification workflow.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections (Input, Steps, Heuristics, Graceful Degradation, Output Format) with no nested references, and no bundle files are needed. Not a 5 because at ~170 lines it exceeds the simple-skill threshold and some content (the detailed report template, heuristics) could be split into reference files rather than kept fully inline.	4 / 5
	Total	16 / 20 Passed

Description

78%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 clear, well-structured description that answers both what the skill does and when to invoke it, with concrete trigger phrasing. It is slightly thin on enumerating multiple specific actions and could use a few more natural synonyms.

Suggestions

Add 1-2 more concrete verification actions (e.g., "check task completion, map requirements to code, validate scenario coverage") to lift specificity from a single action to a list.

Include common synonyms users might say ("check implementation", "review a change", "validate before archive") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("change artifacts") and one concrete action ("Verify implementation matches"), but offers only a single high-level action rather than multiple specific capabilities. Not a 4 because no list of several distinct actions; not a 2 because the action is concrete, not generic.	3 / 5
Completeness	Explicitly answers both "what" ("Verify implementation matches change artifacts") and "when" ("Use when the user wants to validate that implementation is complete, correct, and coherent before archiving") with a concrete trigger phrase. Clearly matches the top anchor.	5 / 5
Trigger Term Quality	Includes natural user-facing phrases like "validate that implementation is complete", "correct", "coherent", and "before archiving". Not a 5 because it lacks synonyms/variants (e.g. "check implementation", "review change") and file-extension-style triggers; not a 3 because coverage is solid rather than partial.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (verifying implementation against change artifacts before archiving) with distinct triggers and low overlap risk. Not a 5 because "verify implementation" is somewhat broad and could brush against general review skills.	4 / 5
	Total	16 / 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: Draculabo/AntigravityManager
Path: .agent/skills/openspec-verify-change/SKILL.md
Commit: e29cfdc

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.