CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-github-pr-review

以只读、证据优先的方式审阅 Comet 社区 PR,包括最新 diff、关联 Issue、review thread 状态、可合并性和 CI。用户要求审阅 PR、判断评论是否仍然有效,或准备简洁的合并阻塞评论时使用。

72

Quality

89%

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 read-only review workflow that respects token budget and gives specific, actionable direction. Slight room to add concrete command examples and an explicit validation feedback loop.

Suggestions

Add one or two concrete command examples for fetching PR state (e.g. a gh CLI snippet) to lift actionability from directive to copy-paste ready.

Make the verification checkpoint explicit as a validate→re-check loop, e.g. 'after refreshing head, re-confirm mergeability before concluding', to strengthen workflow clarity.

Optionally inline a one-line pointer to where the required issue-report fields are defined, so the report structure is unambiguously tied to a source.

DimensionReasoningScore

Conciseness

Lean and directive throughout — it assumes Claude's competence, never explains concepts Claude already knows, and every line earns its place (state refresh, implementation review, reporting scope, comment/fix boundaries).

5 / 5

Actionability

Concrete, specific guidance — exact PR metadata fields to fetch, the required per-issue structure (severity, title, file/line or runtime path, failure reason, fix direction, evidence state), and ready conclusion phrases — but as an instruction-only skill it lacks copy-paste commands/code examples.

4 / 5

Workflow Clarity

A clearly numbered state-refresh sequence (steps 1–4) plus a bulleted implementation-review sequence with implicit checkpoints (verify thread resolved/stale, base conclusions on current head, check if head already fixed); minor validation gaps but no explicit validate→fix→retry feedback loop, which is acceptable for a read-only skill.

4 / 5

Progressive Disclosure

Under 50 lines, single-purpose, and well-organized into clear sections; the one external reference (../comet-github/references/maintainer-contract.md) and delegations to sibling skills are one level deep and clearly signaled at the top.

5 / 5

Total

18

/

20

Passed

Description

92%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 strong, well-scoped description that clearly conveys both capability and trigger conditions in third person without fluff. Minor room only in trigger-term synonym coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions scoped to PR review — latest diff, related Issue, review thread status, mergeability, and CI — plus judging comment validity and preparing merge-blocking comments, giving comprehensive coverage of the domain.

5 / 5

Completeness

Explicitly states both what it does (read-only, evidence-first PR review covering diff/Issue/thread/mergeability/CI) and when to use it ('用户要求审阅 PR、判断评论是否仍然有效,或准备简洁的合并阻塞评论时使用') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like '审阅 PR', '判断评论是否仍然有效', and '准备简洁的合并阻塞评论' map well to what a user would say, though a few synonyms/common variations are absent.

4 / 5

Distinctiveness Conflict Risk

Scoped narrowly to 'Comet 社区 PR' with distinct triggers, giving it a clear niche and minimal conflict risk with unrelated skills.

5 / 5

Total

19

/

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.