CtrlK
BlogDocsLog inGet started
Tessl Logo

feishu-update-doc

更新飞书云文档。支持 7 种更新模式:追加、覆盖、定位替换、全文替换、前/后插入、删除。

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./资料/feishu-openclaw-plugin/package/skills/feishu-update-doc/SKILL.md
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 highly actionable with concrete JSON examples and return formats for all seven modes, and it avoids explaining concepts Claude already knows. Its weaknesses are some redundancy across examples, missing verification checkpoints on destructive paths, and a monolithic structure with no progressive disclosure to reference files.

Suggestions

Add an explicit post-update verification checkpoint for destructive/batch modes (e.g. after overwrite/delete_range/replace_all, fetch the document or check the returned warnings before considering the operation complete).

Move the per-mode example catalog and detailed return-value/error reference into a separate reference file (e.g. references/examples.md) and link to it from the body, keeping SKILL.md as a lean overview.

Factor out the repeated doc_id+mode+markdown JSON skeleton into one shared example, then show only the differing fields per mode to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is mostly purposeful and Feishu-specific with no generic concept filler, but repeats the same doc_id+mode+markdown JSON skeleton across modes and restates the overwrite caution in multiple places, so it could be tightened.

2 / 3

Actionability

Every mode has a concrete, copy-paste-ready JSON request payload, plus complete success/async/error return-value formats — fully executable guidance matching the top anchor.

3 / 3

Workflow Clarity

The whiteboard-fix section is a clear 4-step sequence with a resubmit-validation loop, but the core destructive/batch paths (overwrite, delete_range, replace_all) lack an explicit post-update verification checkpoint, which caps workflow clarity at 2.

2 / 3

Progressive Disclosure

Content is well-organized into clear sections but is entirely monolithic in one ~150-line SKILL.md with no bundle files or one-level-deep references, so reference material that could be split stays inline.

2 / 3

Total

9

/

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 distinctive, clearly naming the platform and seven concrete update actions in third person. Its main weakness is the absence of explicit 'when to use' trigger guidance and natural-term variations beyond the single core phrase.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger scenarios, e.g. 'Use when updating, editing, or modifying Feishu cloud documents or when the user asks to append, replace, insert, or delete document content.'

Include common natural-language variations of the core trigger (编辑文档/修改飞书文档/添加内容) so it matches phrasings users actually say.

DimensionReasoningScore

Specificity

Names the domain (飞书云文档) and lists multiple concrete actions — 追加、覆盖、定位替换、全文替换、前/后插入、删除 — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

The core phrase '更新飞书云文档' is a natural trigger, but it lacks common variations a user might say (编辑/修改/添加内容) and the seven mode names read as technical labels rather than user vocabulary.

2 / 3

Distinctiveness Conflict Risk

'更新飞书云文档' is a clear niche tied to a specific platform and the update operation, unlikely to trigger for unrelated skills.

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.