feishu-doc
Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.
78
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./extensions/feishu/skills/feishu-doc/SKILL.mdQuality
Discovery
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 functional and includes explicit trigger guidance, which is a strength. However, it lacks specificity in the actions it performs (just 'read/write operations') and some trigger terms like 'cloud docs' and 'docx links' are generic enough to cause conflicts with other document-related skills. Adding more concrete actions and Feishu-specific terminology would improve it.
Suggestions
Replace 'read/write operations' with specific actions like 'create, read, update, and format Feishu documents, insert blocks, manage content'.
Add more Feishu-specific trigger terms such as 'Lark docs', 'feishu.cn links', '飞书文档' to improve distinctiveness and reduce conflict with generic document skills.
Clarify or narrow 'cloud docs' and 'docx links' to be Feishu-specific (e.g., 'Feishu cloud documents' or 'Feishu docx links') to reduce overlap with other document tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Feishu documents) and mentions 'read/write operations' as actions, but does not list specific concrete actions like 'create documents, update content, extract text, manage permissions'. | 2 / 3 |
Completeness | Explicitly answers both 'what' (Feishu document read/write operations) and 'when' ('Activate when user mentions Feishu docs, cloud docs, or docx links'), with clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Feishu docs', 'cloud docs', and 'docx links', but misses common variations such as 'Lark docs', '飞书', 'Feishu document links', or specific URL patterns that users might reference. | 2 / 3 |
Distinctiveness Conflict Risk | 'Cloud docs' and 'docx links' are somewhat generic and could overlap with Google Docs, Microsoft Word, or other cloud document skills. 'Feishu' is distinctive, but the other trigger terms introduce conflict risk. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that provides immediately actionable JSON examples for all Feishu document operations. Its main weakness is the lack of validation/verification steps for destructive operations like 'write' (which replaces entire document content) and 'delete_block', and no error handling guidance. The reading workflow is well-sequenced but write workflows deserve similar treatment.
Suggestions
Add a write workflow with validation steps, especially since 'write' replaces the entire document - suggest reading first to confirm the target, and verifying after writing.
Add error handling guidance or common failure modes (e.g., invalid doc_token, permission errors, what happens when writing to a wiki page directly).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what Feishu is or how APIs work. Token extraction, actions, and configuration are all presented with minimal prose and maximum information density. | 3 / 3 |
Actionability | Each action includes a complete, copy-paste-ready JSON payload with concrete parameter examples. The token extraction from URL is specific and immediately usable. Limitations (no markdown tables) are clearly called out. | 3 / 3 |
Workflow Clarity | The 'Reading Workflow' section provides a clear 3-step sequence with a conditional branch, which is good. However, there are no validation/verification steps for write operations (write replaces entire document - a destructive operation) and no error recovery guidance for any action. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but everything is in a single file with no references to supporting documents. For a skill with 8 distinct actions plus configuration and permissions, some content (e.g., detailed block type reference, permission setup) could benefit from being split out. However, the current length is manageable. | 2 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- 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.