comet-verify

Comet Classic 阶段 4 —— 验证 change、记录证据并驱动修复循环。

Quality

70%

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 ./assets/skills-zh/comet-verify/SKILL.md

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 well-engineered verify workflow: clearly sequenced, rich in concrete CLI commands, and reinforced with explicit checklists and a bounded fix-loop. Its main weakness is conciseness and that detail is offloaded to external references rather than an in-bundle progressive-disclosure structure.

Suggestions

Tighten the repeated decision-point and dirty-worktree policy prose, which restates the same protocol several times across steps.

Add one concrete worked end-to-end example (real change name + real report path) to reduce placeholder-only actionability gaps.

Consider moving the long attribution/exception-decision rules into a short in-bundle reference file so the main flow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational — commands, conditions, and rules — and mostly avoids explaining concepts Claude already knows, though some policy prose (dirty-worktree attribution, repeated decision-point protocol) could be tightened.	4 / 5
Actionability	Concrete executable `comet` CLI commands appear throughout (state select/check/scale/transition/set, guard --apply, next), but pervasive `<change-name>` placeholders and heavy deferral to external references and skills leave minor gaps.	4 / 5
Workflow Clarity	A clearly sequenced 0a→3 process with explicit validation checkpoints, a 6-item light checklist, a 7-item full checklist, and a verify-fail→build feedback loop with attempt limits and decision points — matching the feedback-loop anchor for batch/destructive operations.	5 / 5
Progressive Disclosure	No in-bundle files exist, but the body is well-sectioned and clearly signals one-level-deep external references (comet-classic/reference/*.md) via backticks; at ~210 lines some inlined policy could live in reference files, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

58%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 clearly identifies a niche phase and names three concrete actions, but it omits any 'Use when...' trigger guidance and reads more as a phase label than a natural trigger phrase. It is competent but stops short of being a strong standalone trigger description.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke this skill (e.g. 'Use when the Comet Classic change has finished build and needs final verification and evidence capture').

Include natural user-facing trigger terms and synonyms beyond the phase label (e.g. 'verify', 'validation report', 'failed checks', 'fix loop') so users can discover it by intent.

Lead with the action ('Verifies a Comet Classic change, records validation evidence, and drives the build→verify fix loop') before the phase identifier to strengthen the 'what'.

Dimension	Reasoning	Score
Specificity	Names the domain ('Comet Classic 阶段 4') and three concrete actions — '验证 change', '记录证据', '驱动修复循环' — giving several specific actions with minor coverage gaps.	4 / 5
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent trigger guidance, so 'when' is only weakly implied by the phase number — capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant keywords (验证, 证据, 修复循环) are present, but the phrasing reads as a workflow-phase descriptor rather than natural terms a user would say, and it lacks common synonyms or variations.	3 / 5
Distinctiveness Conflict Risk	The 'Comet Classic 阶段 4' qualifier carves a clear niche with mostly distinct triggers; only minor overlap risk with generic verification skills.	4 / 5
	Total	14 / 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: rpamis/comet
Path: assets/skills-zh/comet-verify/SKILL.md
Commit: a23a251

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.