CtrlK
BlogDocsLog inGet started
Tessl Logo

triage

让 issues 和 external PRs 通过一组 triage roles 状态机——分类、验证、必要时 grilling,并写出 agent-ready briefs。

56

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/engineering/triage/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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-sequenced, mostly actionable triage workflow with explicit validation steps and a copy-paste template, keeping conciseness and actionability high. Its main weakness is progressive disclosure: the two referenced markdown files are missing from the bundle, leaving the offloaded detail unreachable.

Suggestions

Ship the referenced AGENT-BRIEF.md and OUT-OF-SCOPE.md files (or inline their essential guidance) so the one-level-deep references actually resolve.

Convert the narrative validation gates (e.g., 'verify the claim', '确认你即将做什么') into explicit hard-stop checkpoints to push workflow clarity toward 5.

Tighten the PR-as-issue framing and the redundancy/prior-rejection paragraphs to remove the remaining over-explanation.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no explanations of what issues/PRs/diffs are), uses brief bullets, and avoids padding; a few sections like the PR-as-issue framing and the redundancy/prior-rejection checks could be trimmed slightly.

4 / 5

Actionability

Guidance is concrete: canonical role/state names, a copy-paste needs-info template, explicit slash-command invocations (/grilling, /domain-modeling, /setup-matt-pocock-skills), and a defined gather-context checklist; minor gaps remain around tracker-specific mechanics.

4 / 5

Workflow Clarity

The 'Triage a specific issue or PR' section is a clear 5-step sequence (Gather → Recommend → Verify → Grill → Apply) with validation gates ('等待指示', verify-the-claim) and feedback loops (needs-info, re-triage), though some gates are described narratively rather than as hard stop-points.

4 / 5

Progressive Disclosure

Section structure is good and the two references (AGENT-BRIEF.md, OUT-OF-SCOPE.md) are clearly signaled inline and in a Reference docs section, but neither referenced file is present in the bundle, so the one-level-deep navigation points to content that does not exist.

3 / 5

Total

15

/

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 concretely states what the skill does across multiple actions but omits any explicit 'Use when...' trigger guidance, capping completeness and trigger quality at the midpoint. It is third-person and reasonably specific, but lacks the trigger phrases a user would naturally say to invoke it.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when triaging issues or external PRs, or when the maintainer asks to review what needs attention').

Include common synonyms/variations users might say (e.g., 'review backlog', 'categorize issues', 'prepare agent briefs') to lift trigger-term coverage.

Consider naming the closing/wontfix outcome in the description so the action coverage reads as fully comprehensive.

DimensionReasoningScore

Specificity

The description names the domain (issues, external PRs, triage) and several concrete actions — '分类' (categorize), '验证' (verify), 'grilling', and '写出 agent-ready briefs' (write agent-ready briefs) — placing it at 'several specific actions; minor gaps' rather than fully comprehensive.

4 / 5

Completeness

It gives a clear 'what' (route issues/PRs through a triage state machine and write briefs) but no explicit 'when/Use when' clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms like 'triage', 'issues', and 'PRs' appear, but there are no 'Use when...' phrases and no synonyms/variations, so coverage is partial rather than good.

3 / 5

Distinctiveness Conflict Risk

Issue/PR triage with role state machines and agent briefs is a fairly distinct niche with minor overlap risk against related issue-management skills, not a clear standalone niche with minimal conflict.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
vinvcn/mattpocock-skills-zh-CN
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.