feishu-doc
Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.
87
81%
Does it follow best practices?
Impact
100%
1.85xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
82%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 covers the basics well, with explicit trigger guidance and relevant keywords. Its main weakness is the lack of specific concrete actions beyond the generic 'read/write operations', and some trigger terms like 'cloud docs' and 'docx links' could cause overlap with other document skills.
Suggestions
Expand 'read/write operations' into specific actions, e.g., 'Read, create, edit, and format Feishu documents, insert blocks, and manage document permissions.'
Qualify the more generic trigger terms to reduce conflict risk, e.g., 'Feishu cloud docs' instead of just 'cloud docs', and specify 'Feishu docx links' or include URL patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Feishu documents) and mentions 'read/write operations' as actions, but does not list specific concrete actions like creating, editing, formatting, extracting content, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (Feishu document read/write operations) and 'when' (explicitly states 'Activate when user mentions Feishu docs, cloud docs, or docx links'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Feishu docs', 'cloud docs', 'docx links'. These are relevant variations that cover how users typically refer to Feishu documents. | 3 / 3 |
Distinctiveness Conflict Risk | 'Cloud docs' and 'docx links' could overlap with other document-related skills (e.g., Google Docs, general document processing). 'Feishu' is distinctive, but the other trigger terms introduce some conflict risk. | 2 / 3 |
Total | 10 / 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 strong, actionable API reference skill with excellent conciseness and fully executable JSON examples for every action. Its main weaknesses are the lack of write/mutation workflows with validation checkpoints (especially for destructive operations like replace-all and delete) and the absence of progressive disclosure structure for what is a fairly lengthy reference document.
Suggestions
Add a 'Writing Workflow' section with explicit validation steps, e.g., read → write → read-back to verify, especially for the destructive 'write' (replace all) action.
Add error handling guidance or a feedback loop for delete_block and write operations (e.g., what to check after a write, how to recover if content is lost).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Feishu is or how APIs work—it jumps straight into token extraction, action schemas, and concrete JSON examples. Every section earns its place with no filler. | 3 / 3 |
Actionability | Every action includes a complete, copy-paste-ready JSON payload with specific parameter names and example values. Limitations (e.g., markdown tables not supported) and important notes (e.g., owner_open_id for permissions) are clearly called out. | 3 / 3 |
Workflow Clarity | The 'Reading Workflow' section provides a clear 3-step sequence with a conditional check, which is good. However, there's no equivalent workflow for write operations (e.g., create doc → write content → create table → verify), and no validation/error-handling steps for destructive operations like write (replace all) or delete_block. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and a logical progression from simple to complex actions. However, with ~150 lines of action reference inline, some content (like the full table operations or image upload details) could benefit from being split into a separate reference file. No bundle files exist to offload to, but the skill is borderline monolithic for its length. | 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
- qsimeon/openclaw-engaging
- Commit
4467e04
- 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.