comet-runtime-diagnose

通过区分过期配置与源码缺陷，并执行真实打包 Runtime 路径，诊断 Comet Hook、安装、路由、平台、生成 Runtime 或生命周期行为。Hook 或安装报告可能涉及配置、生成资产漂移、不支持的平台或跨项目归属问题时使用。

Quality

68%

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-maintainer/comet-runtime-diagnose/SKILL.md

Quality

Content

68%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 exceptionally concise and well-structured with a clear phased workflow and one signaled external reference. Its weaknesses are actionability (no executable commands or paths) and workflow_clarity (no explicit validation/feedback loops, capped at 3 for a skill governing destructive changes).

Suggestions

Add at least one concrete executable command or file path per diagnostic action (e.g. the actual command to invoke the packaged Router/Runtime, or the path to the canonical platform registry) to lift actionability.

Insert an explicit validate-before-act checkpoint in the workflow (e.g. 'confirm reproduction before authorizing any fix; re-run the packaged Runtime and re-check the registry after rebuild') to satisfy the destructive-operation feedback-loop requirement.

Verify the referenced ../comet-github/references/maintainer-contract.md exists and render it as a markdown link so the external reference is clearly navigable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it gives classification buckets, concrete checks, and reporting requirements with no padding or explanation of concepts Claude already knows; every line earns its place.	5 / 5
Actionability	It gives concrete high-level direction (call the packaged Router/Runtime with the host cwd, cross-check against the canonical platform registry, compare source entry vs generated bundle vs Manifest vs installed copy) but provides no executable commands, file paths, or copy-paste examples — the guidance is specific but not directly executable.	3 / 5
Workflow Clarity	A rough three-phase sequence is present (确定问题边界 → 执行真实路径 → 报告诊断结果) with some concrete checkpoints, but it lacks explicit validation/feedback loops and the destructive/batch cap applies since the skill governs whether to modify source/install/assets yet has no validate-before-act checkpoint, capping it at 3.	3 / 5
Progressive Disclosure	Structure is good: a single clearly signaled one-level reference (../comet-github/references/maintainer-contract.md) plus well-organized sections, with the bulk of diagnostic guidance appropriately inline for a short skill; minor gap is that the external reference path is relative and its existence is not verified within the bundle.	4 / 5
	Total	15 / 20 Passed

Description

67%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 domain-specific and answers both what and when, with a clear niche and low conflict risk. Its main weakness is trigger-term naturalness — the phrasing is engineer-facing rather than user-facing, and the action list is more categorical than comprehensive.

Suggestions

Rewrite to lead with natural user-facing trigger phrases (e.g. 'Use when a Comet Hook or install report mentions...') so the 'when' clause reads as something a user would actually say.

Add concrete synonym/variation coverage (e.g. 安装失败、Hook 不生效、平台未注册、Runtime 生成错误) to improve trigger_term_quality.

Enumerate concrete diagnostic actions explicitly (检查 X、对比 Y、运行 Z) to lift specificity from categorical to comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain (Comet Hook/安装/路由/平台/生成 Runtime/生命周期) and several concrete actions (区分过期配置与源码缺陷、执行真实打包 Runtime 路径、诊断), but the actions are diagnostic categories rather than a comprehensive enumerated action list.	4 / 5
Completeness	It states clearly what the skill does (区分配置与源码缺陷并执行真实 Runtime 路径以诊断...) and gives an explicit 'when' clause ("...问题时使用"), satisfying both what and when, though the 'when' could be more specific with concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes some natural terms a user might say (Hook、安装、平台、配置), but they are embedded in technical phrasing and miss common user-facing variations and synonyms; it reads as engineer-jargon rather than natural trigger language.	3 / 5
Distinctiveness Conflict Risk	The Comet-specific terminology (Comet Hook、生成 Runtime、平台注册、生命周期契约) gives it a clear niche with minimal overlap risk against generic skills, with only minor overlap risk against sibling comet-* skills.	4 / 5
	Total	15 / 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-maintainer/comet-runtime-diagnose/SKILL.md
Commit: 899d1fb

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.