feishu-perm
Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.
87
81%
Does it follow best practices?
Impact
96%
1.26xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
Discovery
75%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 establishes a clear niche (Feishu permission management) and includes explicit trigger guidance, which are strengths. However, it lacks specificity in the concrete actions it performs and could benefit from more natural trigger term variations to improve discoverability.
Suggestions
Add specific concrete actions such as 'grant access, revoke permissions, list collaborators, change permission levels' to improve specificity.
Expand trigger terms to include common variations like 'access control', 'invite', 'share a doc', 'read-only', 'edit access' for better keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Feishu permission management) and mentions documents/files, but doesn't list specific concrete actions like granting access, revoking permissions, listing collaborators, or changing permission levels. | 2 / 3 |
Completeness | Answers both 'what' (Feishu permission management for documents and files) and 'when' (Activate when user mentions sharing, permissions, collaborators) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some natural keywords ('sharing', 'permissions', 'collaborators') but misses common variations like 'access control', 'share a doc', 'invite', 'read-only', 'edit access', or 'Feishu docs'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Feishu' and 'permission management' creates a clear niche that is unlikely to conflict with other skills, as it targets a specific platform and a specific function. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
87%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 clear, actionable JSON examples for each permission operation. The reference tables for token types, member types, and permission levels are excellent. The main weakness is the lack of validation/verification steps for these sensitive permission operations (e.g., confirming a collaborator was added, listing before removing).
Suggestions
Add a recommended workflow sequence for destructive operations, e.g., 'Before removing a collaborator, list current collaborators to verify the member_id, then remove, then list again to confirm removal.'
Include brief error handling guidance or expected error responses for common failure cases (e.g., invalid token, insufficient permissions, member not found).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what permissions are or how Feishu works. Tables are compact reference material, and examples are minimal but complete. | 3 / 3 |
Actionability | Provides fully concrete, copy-paste-ready JSON payloads for each action (list, add, remove). Parameter values, types, and permission levels are all explicitly enumerated in reference tables. | 3 / 3 |
Workflow Clarity | The three actions are clearly documented individually, but there's no guidance on sequencing (e.g., list before remove to verify member_id), no validation/verification steps after add/remove operations, and no error handling guidance. Permission management is a sensitive/destructive operation that warrants feedback loops. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~80 lines), the content is well-organized with clear sections: actions, reference tables, examples, and configuration. No need for external files, and the structure supports easy scanning. | 3 / 3 |
Total | 11 / 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
- Hung-Reo/hungreo-openclaw
- Commit
e893157
- 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.