CtrlK
BlogDocsLog inGet started
Tessl Logo

feishu-tools

Use the Feishu/Lark plugin MCP tools for Feishu documents, spreadsheets, knowledge content, and other matching workspace operations.

60

Quality

70%

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 ./plugins/feishu/skills/feishu-tools/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is a well-organized, appropriately concise instruction skill: it gives concrete routing rules, specific error-handling guidance, and an honest constraint that tool availability depends on the active preset rather than inventing tool names. Its main weaknesses are minor — a redundant instruction about not asking the user to classify the plugin, and the absence of a concrete Feishu URL/token example that would make the identifier-extraction rule fully executable.

DimensionReasoningScore

Conciseness

The body is efficient and behavioral-rule driven ('extract the relevant document, sheet, spreadsheet, or workspace identifier when the target tool expects an id or token'), with only minor redundancy — the intro's 'Do not ask the user to classify the plugin' overlaps with Required Behavior #3 about not asking how to call the plugin.

4 / 5

Actionability

For an instruction-only skill, the guidance is concrete: a specific auth-error remedy ('verify App ID, App Secret, brand, and preset'), specific routing name patterns ('docs, docx, wiki, or knowledge'; 'sheets, spreadsheets, tables, or bitable-like structures'), and a clear URL-handling rule. The minor gap is no example of what a Feishu URL or document token looks like.

4 / 5

Workflow Clarity

A simple single-purpose routing skill with clear When-To-Use triggers, ordered behavioral rules, and an explicit error-recovery path (auth/config error → check plugin settings). It falls short of 5 because the rules are parallel guidance rather than a sequenced flow, and there is no recovery guidance for failed write operations beyond ambiguity confirmation.

4 / 5

Progressive Disclosure

The body is under 50 lines, needs no external references (none exist in the bundle, and none are referenced), and is organized into well-labeled sections (When To Use, Required Behavior, Routing Hints, Important Constraint) — matching the rubric's simple-skill case for a 5.

5 / 5

Total

17

/

20

Passed

Description

61%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.

The description identifies a clear niche (Feishu/Lark) with good product-name synonym coverage, but it describes capabilities generically ('Use the ... tools for') and entirely lacks an explicit 'Use when...' trigger clause, which both limits completeness and weakens natural trigger-term matching. It is serviceable but below the rubric's good examples, which pair concrete action verbs with explicit trigger conditions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions Feishu, Lark, Feishu docs, sheets, bitable, wiki, or shares a feishu.cn/larksuite.com link.'

Replace the generic 'Use the ... tools for' framing with concrete action verbs: 'Read, create, update, and append to Feishu/Lark documents and spreadsheets; search knowledge content.'

Include natural user-facing synonyms and file/link tokens (wiki, bitable, base, sheet, feishu.cn) so the description matches how users actually phrase these requests.

DimensionReasoningScore

Specificity

Names the domain ('Feishu/Lark') and specific artifacts ('documents, spreadsheets, knowledge content'), but the action verb is generic — 'Use the ... plugin MCP tools for X' rather than concrete operations like read, create, update, or summarize.

3 / 5

Completeness

The 'what' is clear (use Feishu/Lark MCP tools for documents, spreadsheets, and knowledge content), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Good keyword coverage including both product-name synonyms ('Feishu', 'Lark') plus 'documents, spreadsheets, knowledge content', but natural variations users would actually say ('wiki', 'bitable', 'sheet', or the Chinese name) are missing.

4 / 5

Distinctiveness Conflict Risk

'Feishu/Lark' establishes a clear niche with minimal wrong-skill trigger risk, but the trailing 'and other matching workspace operations' is broad, and generic document/spreadsheet phrasing without the Feishu name could overlap with general doc/spreadsheet skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
ThinkInAIXYZ/deepchat
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.