CtrlK
BlogDocsLog inGet started
Tessl Logo

feishu-create-doc

创建飞书云文档。从 Lark-flavored Markdown 内容创建新的飞书云文档,支持指定创建位置(文件夹/知识库/知识空间)。

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./nexu-skills/skills/feishu-create-doc/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The SKILL.md body is a tight, highly actionable reference for the create-doc tool: complete JSON examples for every parameter path, an exhaustive catalog of Lark-flavored Markdown block syntax with attributes and constraints, and explicit gotchas. It is well-organized and avoids concept padding.

DimensionReasoningScore

Conciseness

The body is a lean, dense reference catalog — every block type gets a tight executable code example with attributes and limits, with no padding explaining concepts Claude already knows (e.g. no 'what is Markdown/PDF'). The '场景速查' and '最佳实践' tables concisely distill guidance rather than narrate it.

3 / 3

Actionability

Provides six complete, copy-paste-ready JSON examples covering each parameter combination (folder, wiki_node, wiki_space, my_library) plus full XML tag examples with all attributes and concrete value enumerations (e.g. iframe type mappings, callout color palettes).

3 / 3

Workflow Clarity

This is a single-tool skill and the single action (call create-doc with the documented parameters) is unambiguous; parameter priority (wiki_node > wiki_space > folder_token) and key gotchas (禁止重复标题, long-doc append-mode guidance) are stated explicitly, which per the simple-skill note supports a top score.

3 / 3

Progressive Disclosure

Content is organized in one well-structured SKILL.md with clearly labeled sections (返回值/参数/示例/内容格式) and no nested multi-level references; no bundle files exist, so the single self-contained, well-organized file satisfies progressive disclosure.

3 / 3

Total

12

/

12

Passed

Description

57%

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 specific and distinct, clearly stating the tool creates Feishu cloud documents from Lark-flavored Markdown with configurable locations. Its main weakness is the absence of an explicit 'Use when...' trigger clause and limited natural-language keyword variations.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to create a Feishu/Lark document, write meeting notes or project plans into 飞书云文档, or create docs in a folder/知识库/知识空间.'

Broaden trigger term coverage with natural variations users would say (飞书文档, Lark 文档, 会议纪要, 项目计划, 知识库文档).

List a couple more concrete actions (e.g. 'fill structured content with callout/table/mermaid blocks') to push specificity to 3.

DimensionReasoningScore

Specificity

Names the domain (飞书云文档) and concrete actions ('从 Lark-flavored Markdown 内容创建', '支持指定创建位置(文件夹/知识库/知识空间)'), but does not list multiple distinct actions beyond create+locate, so it is not a full score-3 list of specific actions.

2 / 3

Completeness

Clearly answers 'what' (creates Feishu cloud docs from Lark-flavored Markdown with a chosen location), but the 'when' trigger is only implied; there is no explicit 'Use when...' clause, which caps completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Contains the natural phrase '创建飞书云文档' that a user might say, but offers limited keyword variations and no listing of common phrasings like '飞书文档', 'Lark 文档', or '会议纪要' to broaden coverage.

2 / 3

Distinctiveness Conflict Risk

The skill targets a clearly distinct niche (飞书/Lark cloud document creation from Lark-flavored Markdown) with specific parameters unlikely to overlap with other skills, so it is clearly distinguishable and low-conflict.

3 / 3

Total

9

/

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

skill_md_line_count

SKILL.md is long (731 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

13

/

16

Passed

Repository
nexu-io/nexu
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.