CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-github

将 Comet GitHub 维护请求路由到基于证据的 PR 审阅、Issue 分诊、本地想法收集、CI 诊断或 Issue 实施流程。用户提到 Comet GitHub Issue/PR 但未指定流程,或询问下一步如何处理时使用。

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured routing skill: concise overview, concrete intent-to-flow mapping, sequenced safety rules with read-only defaults and authorization gates, and a single clearly signaled reference. The main gap is the absence of an explicit error-recovery feedback loop and executable commands, which is acceptable for an instruction-only routing skill.

DimensionReasoningScore

Conciseness

The body is lean and efficient with no padding and no explanation of concepts Claude already knows — every line is actionable routing or safety guidance, matching the level-5 'every token earns its place' anchor.

5 / 5

Actionability

The intent→skill routing table ('审阅 PR / 看这个 PR' → comet-github-pr-review) and the concrete routing rules give specific, actionable guidance, but as an instruction-only routing skill it provides no executable commands, placing it at mostly-executable (4) rather than fully-executable (5).

4 / 5

Workflow Clarity

The '共享路由规则' is a clear five-step sequenced checklist with validation checkpoints (refresh live state before trusting stale data, explicitly report uncertainty, default read-only with authorization for writes), but there is no explicit validate→fix→retry feedback loop, so it sits at 4 rather than 5.

4 / 5

Progressive Disclosure

Under 50 lines with well-organized sections and one clearly signaled one-level-deep reference ('路由前先读取[共享维护者契约](references/maintainer-contract.md)') that resolves to a real file, matching the level-5 anchor for a simple skill.

5 / 5

Total

18

/

20

Passed

Description

88%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 well-constructed routing description that clearly states what it does, when to use it, and the five concrete destinations, with good natural trigger phrasing. The only soft spot is minor overlap risk with its sibling comet-github sub-skills.

DimensionReasoningScore

Specificity

Lists multiple concrete routing targets — '基于证据的 PR 审阅、Issue 分诊、本地想法收集、CI 诊断或 Issue 实施流程' — giving comprehensive coverage of the skill's routing scope, matching the level-5 anchor rather than the minor-gaps level-4 anchor.

5 / 5

Completeness

It explicitly answers both what (routes Comet GitHub maintenance requests to five evidence-based flows) and when (the '用户提到...时使用' trigger clause), matching the level-5 anchor for both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural triggers are present ('用户提到 Comet GitHub Issue/PR 但未指定流程,或询问下一步如何处理时使用') giving good keyword coverage, but it lacks synonyms and file extensions so it does not reach the comprehensive level-5 anchor.

4 / 5

Distinctiveness Conflict Risk

The 'Comet GitHub' namespace carves a clear niche with distinct triggers, but the description overlaps with its five sibling comet-github sub-skills, so it sits at mostly-distinct (4) rather than minimal-conflict (5).

4 / 5

Total

18

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.