feishu-notify
Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Supports push-only (webhook) and interactive (bidirectional) modes. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.
71
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies its purpose, supported modes, and trigger conditions. It covers both bilingual trigger terms and programmatic use cases, making it easy for Claude to select appropriately. The description is concise yet comprehensive with no unnecessary fluff.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: send notifications, push-only webhook mode, interactive bidirectional mode. Also specifies it's an internal utility used by other skills and can be triggered manually via /feishu-notify. | 3 / 3 |
Completeness | Clearly answers both what ('Send notifications to Feishu/Lark, supports push-only and interactive modes') and when ('Use when user says "发飞书", "notify feishu", or other skills need to send status updates'), with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger terms in both Chinese ('发飞书') and English ('notify feishu'), plus mentions 'Feishu/Lark' covering both brand names. Also covers programmatic triggers ('other skills need to send status updates'). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific platform (Feishu/Lark) with specific trigger terms and a unique slash command (/feishu-notify). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 utility skill with strong actionability and clear workflow sequencing including proper fallback chains and error handling. Its main weakness is moderate verbosity — the 'zero-impact' guarantee and config-absent behavior are restated redundantly across multiple sections. The content could benefit from consolidation and potentially splitting the event catalog and card templates into separate reference files.
Suggestions
Remove redundant statements about config-absent behavior — state it once in Configuration and once in Key Rules, not in Overview, Helper Function, and elsewhere.
Consider extracting the Event Catalog and Card Templates tables into a separate reference file (e.g., EVENTS.md) to reduce the main skill's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity — the 'Zero-impact guarantee' explanation is repeated multiple times (config absent = no-op is stated at least 4 times), and the Helper Function section restates what's already clear. The Event Catalog table, while useful, adds significant length. | 2 / 3 |
Actionability | Provides fully executable curl commands for both push and interactive modes, concrete JSON config format, specific card templates with color codes, and clear bash commands for reading config. The guidance is copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Clear 4-step workflow with explicit sequencing (read config → push or interactive → verify delivery). Includes validation at Step 4, fallback behavior (interactive → push → silent skip), timeout handling, and explicit error recovery paths. The fail-open principle is clearly stated. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and tables, but it's all inline in a single file with no references to supporting documents. The Event Catalog and card templates could be split into separate reference files. However, no bundle files exist, so there's nothing to reference — the content is borderline monolithic at ~150 lines but not egregiously so. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
a425a71
- 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.