CtrlK
BlogDocsLog inGet started
Tessl Logo

complete-example

当用户明确要求"填充示例内容""生成示例""补充 LaTeX 示例"时使用。AI 增强版 LaTeX 示例智能生成器,实现 AI 与硬编码的有机融合:AI 做"语义理解"(分析章节主题、推理资源相关性、生成连贯叙述),硬编码做"结构保护"(格式验证、哈希校验、访问控制)。

67

Quality

82%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and token-efficient with concrete rules and parameters, but it stops short of executable guidance and does not explicitly navigate to the provided scripts/ and references/ bundle. Validation exists but the feedback loop is left implicit.

Suggestions

Add a concrete invocation example — e.g. the command/entry point to run scripts/skill_controller.py with sample arguments — so the body is copy-paste actionable instead of deferring all detail to config.yaml.

Make the validation feedback loop explicit in the workflow (e.g. 'if format validation fails, fix and re-validate; only write back to the project when validation passes') rather than a single terse validate step.

Add explicit navigation to the bundle: link references/README.md and name the entry-point script (scripts/skill_controller.py) in the body so the scripts/ files are discoverable.

DimensionReasoningScore

Conciseness

The body is lean — short definitional lists and rules with no explanation of concepts Claude already knows (no 'what is LaTeX' filler), and every line earns its place.

3 / 3

Actionability

It gives concrete specifics (input enums like content_density=minimal/moderate/comprehensive, output_mode=preview/apply/report, blacklisted file paths, allowed \section levels) but contains no executable command or entry-point invocation, deferring most detail to config.yaml — 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

The 7-step workflow is clearly sequenced and step 7 plus output_mode=preview provide validation, but the validate→fix→retry feedback loop is not spelled out and there is no explicit 'only proceed when valid' gate, leaving checkpoints implicit.

2 / 3

Progressive Disclosure

The body is a well-sectioned overview and clearly signals config.yaml for detail, but it never links references/README.md or names the entry-point script in scripts/, so the substantial bundle is not navigated from the overview.

2 / 3

Total

9

/

12

Passed

Description

100%

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 is strong: it pairs an explicit 'use when' trigger clause with a concrete, action-oriented statement of what the skill does and a well-scoped niche. Voice is appropriately third-person with no over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions on both sides of the AI/hard-code split — '分析章节主题、推理资源相关性、生成连贯叙述' and '格式验证、哈希校验、访问控制' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' (AI-enhanced LaTeX example generator with semantic understanding + structure protection) and 'when' ('当用户明确要求…时使用'), satisfying the explicit-trigger requirement.

3 / 3

Trigger Term Quality

Includes natural user-facing phrases ('填充示例内容', '生成示例', '补充 LaTeX 示例') that a user would actually say, giving good coverage of trigger variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (filling example content into existing LaTeX projects for NSFC/thesis/paper) with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
huangwb8/ChineseResearchLaTeX
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.