CtrlK
BlogDocsLog inGet started
Tessl Logo

feishu-fetch-doc

获取飞书云文档内容。返回文档的 Markdown 内容,支持处理文档中的图片、文件和画板(需配合 feishu_doc_media 工具)。

69

Quality

83%

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

100%

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

The body is lean, highly actionable, and well-structured: it provides executable JSON payloads, exact media tag formats, and a clear wiki-routing workflow with branching and a worked example. It is a strong, compact skill body with no concept-fluff or reference indirection.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it gives concrete HTML tag formats, JSON payloads, and decision tables without explaining what Feishu or Markdown are. Only minor redundancy exists (the final 工具组合 table restates tools already introduced inline), which does not push it down to the 'mostly efficient but includes some unnecessary explanation' anchor.

3 / 3

Actionability

Provides fully executable, copy-paste-ready guidance: exact media HTML tags, a complete feishu_doc_media download JSON payload, a wiki-node query payload, and an obj_type → tool → parameter decision table with a worked example. This matches the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

The Wiki URL workflow is clearly sequenced (query feishu_wiki_space_node → read obj_type/obj_token → route to the matching tool) with explicit branching including an 'unsupported type' fallback and a worked example. Since this is a read-only fetch operation, the destructive/batch feedback-loop cap does not apply, and the obj_type routing serves as an explicit checkpoint.

3 / 3

Progressive Disclosure

The skill is under 50 lines, single-purpose, and has no external bundle files (references/scripts/assets are absent). Per the rubric's simple-skills note, well-organized sections alone justify a 3 here, and the sections (媒体处理, 参数, Wiki 处理策略, 工具组合) are clearly organized.

3 / 3

Total

12

/

12

Passed

Description

67%

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 clearly scoped to a distinct Feishu-doc niche, but it lacks an explicit 'Use when...' trigger clause and uses tool-oriented phrasing rather than natural user terms, which caps trigger quality and completeness at 2.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke the skill, e.g. 'Use when the user asks to read or fetch a Feishu/Lark cloud document, or mentions 飞书文档, 云文档, or a feishu.cn/wiki or /docx URL.'

Incorporate natural trigger variations a user would actually say (飞书文档, 云文档, Lark doc, 飞书链接) alongside the current tool-function wording to lift trigger-term quality toward 3.

DimensionReasoningScore

Specificity

Names the domain (Feishu cloud docs) and lists multiple concrete actions — '获取飞书云文档内容', '返回文档的 Markdown 内容', '支持处理文档中的图片、文件和画板'. This matches the 'lists multiple specific concrete actions' anchor rather than score 2's partial coverage.

3 / 3

Completeness

Clearly states what the skill does, but the 'when' is only implied — there is no 'Use when...' clause. Per the rubric guideline, a missing explicit trigger clause caps completeness at 2.

2 / 3

Trigger Term Quality

Contains relevant domain keywords ('飞书云文档', '文档', '图片/文件/画板') but reads as tool-function jargon rather than natural user phrasing and lacks common variations. Not score 1 (it has real domain keywords) nor score 3 (no broad coverage of terms users would naturally say).

2 / 3

Distinctiveness Conflict Risk

Targets a specific niche (Feishu cloud documents and their media handling) with distinct triggers unlikely to overlap with other skills. Not score 2, which would describe a more generic 'works with document files' scope.

3 / 3

Total

10

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
op7418/CodePilot
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.