CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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。

Quality

79%

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

85%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 dense, well-sequenced operational skill with strong validation checkpoints, explicit templates, and lean token usage. Its one real weakness is bundle integrity: the two referenced companion documents are missing, which undermines both navigation and the ready-for-agent deliverable.

Suggestions

Ship AGENT-BRIEF.md and OUT-OF-SCOPE.md in the bundle (e.g. under references/) so the linked brief format and .out-of-scope/ knowledge-base mechanics are actually reachable.

Inline a minimal brief skeleton in SKILL.md as a fallback, so the ready-for-agent outcome is executable even if the reference file is absent.

Move the referenced documents into a clearly named references/ directory and update the links to point there, making the bundle structure self-describing.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout: roles/states are one-line definitions, the workflow steps are dense directives ('redundancy 按域名 concept 搜索...并报告你查找过的地方'), and the needs-info template is included only once. No section explains concepts Claude already knows; every token earns its place, matching anchor 5.

5 / 5

Actionability

Guidance is highly concrete: exact disclaimer text to prepend to every comment, a copy-paste needs-info template, precise verification steps ('checkout 它,运行相关 tests 或 commands'), named Skill invocations ('分别指定 grilling 和 domain-modeling'), and a fallback command ('/setup-matt-pocock-skills'). It stops short of anchor 5 because the key deliverable format — the agent brief — is delegated to AGENT-BRIEF.md, which is not present in the bundle, leaving the ready-for-agent outcome without an executable specification.

4 / 5

Workflow Clarity

The triage process is a clearly sequenced five-step workflow (Gather context → Recommend → Verify the claim → Grill → Apply the outcome) with explicit checkpoints: wait for maintainer instructions after recommending, report verification outcomes (confirmed / failed / insufficient detail → strong needs-info signal), ask before anomalous state transitions, and confirm before executing quick overrides. Feedback loops are present (needs-info → reporter replies → re-evaluate; resume-session section instructs re-reading prior notes), matching anchor 5.

5 / 5

Progressive Disclosure

References are clearly signaled and only one level deep ([AGENT-BRIEF.md](AGENT-BRIEF.md), [OUT-OF-SCOPE.md](OUT-OF-SCOPE.md)), and the ~110-line body is appropriately sized for a SKILL.md overview. However, neither referenced file exists in the bundle (no references/, scripts/, or assets/ directories), so the links are broken and the promised detail (brief format, .out-of-scope/ KB mechanics) is unreachable — navigation fails in practice, which anchors this at 3 rather than 4.

3 / 5

Total

17

/

20

Passed

Description

66%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 concrete, domain-specific description that names its actions clearly, but it omits any 'when to use' guidance, which caps its completeness. Adding an explicit trigger clause and a few natural synonyms would round it out.

Suggestions

Add an explicit 'Use when...' clause (e.g. 'Use when the maintainer asks to triage, label, categorize, or review open issues and external PRs').

Include natural trigger-term variations users would actually say: 'label issues', 'categorize issues', 'close stale issues', 'review incoming PRs'.

Mention the full set of outcomes (needs-info questions, closing as wontfix, ready-for-human vs ready-for-agent) so the 'what' coverage is comprehensive.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "通过一组 triage roles 状态机" (move through a triage roles state machine), "分类、验证、必要时 grilling,并写出 agent-ready briefs" (classify, verify, grill when needed, write agent-ready briefs) — with only minor coverage gaps (no mention of closing/wontfix outcomes or needs-info notes). It sits at anchor 4 rather than 5 because coverage of the full workflow outcomes is incomplete, and clearly above anchor 3's '1-2 concrete actions' since it names four to five distinct actions.

4 / 5

Completeness

The 'what' is clear (triage issues/PRs through a roles state machine to agent-ready briefs), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the skill is maintainer-invoked via /triage, and nothing in the description states when it applies. Per the judging guideline, a missing 'Use when' clause caps completeness at 3; it is above anchor 2 because the 'what' is fully explicit rather than vague.

3 / 5

Trigger Term Quality

Natural terms users would say are present: "issues", "external PRs", "triage", "agent-ready briefs". It is not a 5 because common variations a user might naturally say — e.g. "labels", "categorize", "close issues", "review requests" — are missing, but coverage goes beyond anchor 3's 'some relevant keywords with missing synonyms'.

4 / 5

Distinctiveness Conflict Risk

The triage state-machine niche (roles, states, agent-ready briefs) is quite distinct from generic issue-management skills, with only minor overlap risk with a general 'issue tracker' or 'labeling' skill. It falls short of anchor 5's 'clear niche with distinct triggers' because no explicit trigger phrases mark the niche, and above anchor 3 because the state-machine/agent-brief framing is specific.

4 / 5

Total

15

/

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.

Validation — 15 / 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

Path

skills/engineering/triage/SKILL.md

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.