CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-github-issue-fix

在隔离范围内,通过所属 Native 或 Classic workflow、匹配风险的测试、生成 Runtime 检查和谨慎交付,实施已确认的 Comet GitHub Issue 或 review 阻塞项。用户明确要求修复已验证的 Issue 或 PR 问题时使用。

73

Quality

90%

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

88%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 lean, well-sequenced workflow skill with explicit validation gates appropriate to its destructive nature. The main improvement area is actionability — adding a few concrete commands would close the gap to fully executable — and confirming the external maintainer-contract reference is reachable.

Suggestions

Add one or two concrete executable commands (e.g., the exact test/build invocation or worktree creation command) so the guidance moves from process-level to copy-paste-ready.

Verify that ../comet-github/references/maintainer-contract.md is reachable from the skill's install location, or fold the essential contract rules into a local reference file so the skill is self-contained.

Make the destructive-operation validation gate explicit as a numbered 'Only when tests pass' step, mirroring the rubric's feedback-loop pattern, rather than leaving it as '先运行最小相关测试'.

DimensionReasoningScore

Conciseness

A dense ~24-line procedural body with no padding and no re-explanation of concepts Claude already knows; every line carries actionable instruction.

5 / 5

Actionability

Provides concrete, specific guidance — named files, named skills (comet-safe-delivery), named workflow types, worktree/branch isolation — but as policy/process instruction with no copy-paste-ready commands, leaving it just below fully executable.

4 / 5

Workflow Clarity

Sequences 确认工作边界 → 实施流程 → 验证与交接 with explicit, gating validation checkpoints (verify the issue exists; run minimal tests before expanding to build/lint/full checks), satisfying the destructive-operation feedback-loop requirement.

5 / 5

Progressive Disclosure

Well-organized into clear sections under 50 lines with a clearly signaled one-level reference, but the core contract detail is delegated to an external cross-skill file outside the skill's own bundle, a minor gap versus the self-contained ideal.

4 / 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 precise, well-scoped description that answers both 'what' and 'when' with concrete actions and a natural trigger clause. Its only weakness is trigger-term breadth, relying on domain-internal terminology rather than a wide range of synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — Native/Classic workflow routing, risk-matched tests, Runtime checks, careful delivery — for a clearly named domain (confirmed Comet GitHub Issue/review blocker), giving comprehensive coverage rather than minor gaps.

5 / 5

Completeness

Explicitly states what it does (implement confirmed issue/review blocker in an isolated scope via workflow, tests, runtime checks, careful delivery) and when to use it ('用户明确要求修复已验证的 Issue 或 PR 问题时使用') with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Contains natural user phrasing like '修复已验证的 Issue 或 PR 问题', but stays within domain-internal terminology without the breadth of synonyms or extensions a 5 would require.

4 / 5

Distinctiveness Conflict Risk

Scoped to a specific project (Comet), a specific scenario (confirmed issue or review blocker), and a specific trigger (user explicitly asks), giving it a clear niche with minimal conflict risk.

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.

Validation16 / 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.