CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-matt-pocock-skills

为此仓库配置 engineering skills——设置其 issue tracker、triage labels 词汇与 domain docs 布局。在首次使用其他 engineering skills 前运行一次。

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

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 well-crafted interactive setup skill: concrete commands and file paths, a copy-paste output template, explicit conditional branching, and user-confirmation checkpoints at every write. Its weaknesses are minor — a duplicated file-selection rule in step 4 and template references that could not be verified against the (absent) bundle files.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (raw commands like "git remote -v" with no explanation of git or GitHub), but step 4 states the CLAUDE.md/AGENTS.md file-selection rule twice ("如果 CLAUDE.md 存在,编辑它…" then "当 CLAUDE.md 已存在时,绝不创建 AGENTS.md…始终编辑已经存在的那个"), which is trimmable redundancy. Not 3 because padding is minor, not pervasive.

4 / 5

Actionability

Guidance is fully concrete throughout: exact files to inspect (.git/config, AGENTS.md, pnpm-workspace.yaml), exact default label strings (needs-triage through wontfix), a copy-paste markdown block template, exact output paths (docs/agents/issue-tracker.md, domain.md), and explicit per-case handling for GitHub/GitLab/local/other trackers and installed/missing triage. Anchor 5 for an instruction-only skill; not 4 because the common cases are all covered with executable specifics.

5 / 5

Workflow Clarity

A clear five-step sequence (Explore → Present → Confirm → Write → Done) with explicit branching rules (skip Section B without triage, skip C without monorepo signals) and explicit validation checkpoints: one section and one answer at a time, drafts shown with "写入前允许用户修改", and error-avoidance rules (update an existing ## Agent skills block in place, never overwrite surrounding user edits). Not 4 because checkpoints are explicit user-confirmation loops, not implicit.

5 / 5

Progressive Disclosure

The body keeps bulk seed-template content out of SKILL.md and points to five one-level-deep, individually labeled references (issue-tracker-github.md, issue-tracker-gitlab.md, issue-tracker-local.md, triage-labels.md, domain.md) exactly at the point of use (step 4). However, no bundle files were provided alongside SKILL.md, so the referenced files' existence and content cannot be verified — a minor organization gap that keeps this below anchor 5.

4 / 5

Total

18

/

20

Passed

Description

87%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 description: third-person, concise, names three concrete configuration targets, and includes an explicit run-once trigger condition tied to first use of the skill suite. The only gap is that it does not mention the concrete artifacts it writes (docs/agents/ files, the ## Agent skills block in CLAUDE.md/AGENTS.md).

DimensionReasoningScore

Specificity

"设置其 issue tracker、triage labels 词汇与 domain docs 布局" names three concrete configuration targets, matching the 'several specific actions, minor gaps' anchor; it stops short of anchor 5 because it omits the concrete outputs the skill actually performs (writing docs/agents/*.md files, editing CLAUDE.md/AGENTS.md).

4 / 5

Completeness

The description explicitly answers both what ("为此仓库配置 engineering skills——设置其 issue tracker、triage labels 词汇与 domain docs 布局") and when ("在首次使用其他 engineering skills 前运行一次") with a concrete trigger condition, matching the top anchor; it is not 4 because the when-clause is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

Terms like "issue tracker", "triage labels", "domain docs", and "engineering skills" are natural phrases users of this suite would say, giving good keyword coverage; not anchor 5 because common synonyms and concrete file names (e.g. CONTEXT.md, ADRs) are absent from the description.

4 / 5

Distinctiveness Conflict Risk

"在首次使用其他 engineering skills 前运行一次" carves out a clear per-repo setup niche that no sibling skill (triage, to-tickets, to-spec) would claim, giving minimal conflict risk; not 4 because there is no meaningful overlap with closely related skills.

5 / 5

Total

18

/

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: 5 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.