feishu-wiki
Feishu knowledge base navigation. Activate when user mentions knowledge base, wiki, or wiki links.
76
63%
Does it follow best practices?
Impact
100%
2.00xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./extensions/feishu/skills/feishu-wiki/SKILL.mdQuality
Discovery
40%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 too vague about what the skill actually does—'navigation' is not a concrete action. While it includes a 'when' clause with some trigger terms, the lack of specific capabilities (e.g., search, retrieve, browse, link resolution) makes it hard for Claude to know exactly what this skill offers versus other documentation or wiki skills.
Suggestions
Replace 'navigation' with specific concrete actions such as 'Search Feishu knowledge base articles, retrieve wiki page content, resolve wiki links, and browse knowledge base structure'.
Expand trigger terms to include variations like 'Feishu wiki', 'Feishu docs', 'KB', 'knowledge article', 'wiki page', and any relevant Chinese terms users might use.
Strengthen the 'Use when' clause to be more explicit, e.g., 'Use when the user asks to find, read, or link to content in a Feishu knowledge base or wiki, or when wiki URLs or knowledge base references appear in the conversation.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'knowledge base navigation' which is vague. It does not list any concrete actions like 'search articles', 'retrieve documents', 'browse wiki pages', or 'extract content from knowledge base entries'. | 1 / 3 |
Completeness | It has a weak 'what' (navigation) and does include a 'when' clause ('Activate when user mentions knowledge base, wiki, or wiki links'), but the 'what' is too vague to be considered clearly answered. The 'when' clause is present but the 'what' is insufficient for a score of 3. | 2 / 3 |
Trigger Term Quality | Includes some relevant trigger terms ('knowledge base', 'wiki', 'wiki links') but misses common variations like 'Feishu docs', 'Feishu wiki', 'knowledge article', 'KB', or Chinese equivalents. The term 'Feishu' itself is a useful distinguishing keyword. | 2 / 3 |
Distinctiveness Conflict Risk | 'Feishu' provides some distinctiveness, but 'knowledge base navigation' and 'wiki' are generic terms that could overlap with other wiki or documentation skills. The Feishu-specific context helps somewhat but the actions are too vague to clearly carve out a niche. | 2 / 3 |
Total | 7 / 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-crafted, concise skill that provides highly actionable JSON examples for every wiki operation. Its main weakness is the lack of validation/error-handling guidance in the workflow section, particularly for destructive operations like move and create. The structure and token efficiency are excellent for a tool-reference skill.
Suggestions
Add a validation step to the Wiki-Doc Workflow (e.g., verify obj_token is not null before proceeding to feishu_doc calls)
Add brief error handling guidance for move/create operations (e.g., what to check if a move fails or a node already exists)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what a wiki is or how APIs work. Token extraction is shown by example, actions are shown as concrete JSON payloads with minimal prose. | 3 / 3 |
Actionability | All actions are shown as copy-paste-ready JSON payloads with concrete parameter examples. The wiki-doc workflow provides exact tool calls with specific parameter names. Every action variant is demonstrated with real examples. | 3 / 3 |
Workflow Clarity | The Wiki-Doc Workflow section provides a clear 3-step sequence for the most common multi-step operation. However, there are no validation checkpoints or error handling guidance—e.g., what if the node doesn't exist, or if obj_token is null. For operations like move/create that could be destructive, no verification steps are mentioned. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~80 lines) with no bundle files, the content is well-organized into logical sections (Token Extraction, Actions, Workflow, Configuration, Permissions). Each section is appropriately scoped and easy to navigate via headers. | 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
- 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.