CtrlK
BlogDocsLog inGet started
Tessl Logo

scaffold-exercises

创建包含章节、题目、答案和讲解的练习目录结构,并确保通过 linting。适用于用户想 scaffold exercises、创建 exercise stubs,或设置新的课程章节时。

70

Quality

86%

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.

The body is highly actionable and workflow-focused: exact commands, a validation feedback loop, and a complete worked example make it copy-paste ready. Its only weaknesses are mild duplication between the 'Required files' and 'Lint rules summary' sections and a workflow that omits the git commit step mentioned in the intro.

Suggestions

Consolidate the overlapping requirements between 'Required files' and 'Lint rules summary' (non-empty readme.md, main.ts rule, broken links) into a single authoritative checklist to trim redundant tokens.

Add the `git commit` step (mentioned in the intro as "然后用 git commit 提交") to the end of the numbered Workflow so the sequence covers the full task lifecycle.

DimensionReasoningScore

Conciseness

The body is lean and imperative with no padding of concepts Claude already knows ("每个 exercise 至少需要这些 subfolders 中的一个", direct lint rule bullets). However, the "Lint rules summary" section repeats requirements already stated in "Required files" (non-empty readme.md, main.ts requirement, no broken links), which is duplication that could be trimmed — matching anchor 4 rather than 5.

4 / 5

Actionability

Guidance is fully executable: the exact lint command (`pnpm ai-hero-cli internal lint`), copy-paste `mkdir -p` brace-expansion commands, a `git mv` example, a concrete readme stub template, and a complete worked end-to-end example for stubbing from a plan. This matches anchor 5's copy-paste-ready commands covering common cases, not anchor 4's 'minor gaps'.

5 / 5

Workflow Clarity

The Workflow section gives a clear 5-step sequence with an explicit validation step ("Run lint — 执行 pnpm ai-hero-cli internal lint 验证") and an explicit feedback loop ("Fix any errors — 迭代直到 lint 通过" / iterate until lint passes), and the moving/renaming section also requires re-running lint after moves. This matches anchor 5 (explicit validation, error-recovery loop), not anchor 4.

5 / 5

Progressive Disclosure

Sections are well-organized with clear headers, no dead references, and all content sits appropriately in one file (no references/, scripts/, or assets/ exist, and none are needed). However, at ~107 lines it exceeds the under-50-line simple-skill exception, and the duplicative lint-rule summary is content that could be consolidated, matching anchor 4's 'minor organization gaps' rather than 5.

4 / 5

Total

18

/

20

Passed

Description

83%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 that clearly states what the skill does and when to use it, with an explicit use-when clause and natural trigger phrases. Its main gaps are modest: slightly incomplete coverage of the skill's full capabilities and a few missing trigger variations.

DimensionReasoningScore

Specificity

The description names concrete actions — "创建包含章节、题目、答案和讲解的练习目录结构" (create exercise directory structures with sections, problems, solutions, and explainers) plus "并确保通过 linting" (ensure passing linting). It lists several specific components and actions but omits parts of the skill's actual scope (renumbering/moving exercises, git commit), matching anchor 4 rather than 5.

4 / 5

Completeness

It explicitly answers both questions: what it does ("创建...练习目录结构,并确保通过 linting") and when to use it ("适用于用户想 scaffold exercises、创建 exercise stubs,或设置新的课程章节时" — an explicit use-when clause with concrete trigger phrases). This matches the anchor-5 example structure and is clearly above anchor 4, where the 'when' would be less explicit.

5 / 5

Trigger Term Quality

"scaffold exercises", "创建 exercise stubs" (create exercise stubs), and "设置新的课程章节" (set up new course sections) are phrases users would naturally say. Coverage is good but misses common variations such as "add a new exercise" or "new chapter", matching anchor 4 rather than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The niche (course exercise scaffolding with lint validation) is mostly distinct with specific trigger terms, but it could minorly overlap with generic project-scaffolding or directory-creation skills, matching anchor 4 rather than 5's minimal-conflict clear niche.

4 / 5

Total

17

/

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
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.