CtrlK
BlogDocsLog inGet started
Tessl Logo

feishu-troubleshoot

飞书插件问题排查工具。包含常见问题 FAQ 和深度诊断命令(/feishu_doctor)。 常见问题可随时查阅。诊断命令用于排查复杂问题(多次授权仍失败、自动授权无法解决等), 会检查账户配置、API 连通性、应用权限、用户授权状态,并生成详细的诊断报告和解决方案。

65

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./资料/feishu-openclaw-plugin/package/skills/feishu-troubleshoot/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, actionable, and well-organized for a compact instruction-only skill, with concrete fix steps and a clear diagnostic command. The main gap is the absence of an explicit verification step in the fix workflow.

Suggestions

Add a validation checkpoint to the FAQ workflow, e.g. a final step "重新点击卡片按钮验证是否恢复正常" (re-test the card button to confirm it works).

Reconcile the diagnostic command name — the description uses "/feishu_doctor" while the body uses "/feishu doctor"; pick one consistent form.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — it skips generic concept explanations and gives only domain-specific material (exact config steps, the /feishu doctor command, the diagnostic output structure), so every token earns its place per the level-3 anchor.

3 / 3

Actionability

Provides concrete, copy-ready guidance: a numbered platform-navigation fix with a real URL (https://open.feishu.cn/app) and an exact command ("/feishu doctor"); for an instruction-only skill the guidance is specific and actionable, matching the level-3 anchor.

3 / 3

Workflow Clarity

The FAQ fix is a clear numbered sequence (1–4: login → select app → change subscription → publish), but there is no validation/verification checkpoint (e.g. "re-test the card button after publishing"), so checkpoints are implicit per the level-2 anchor.

2 / 3

Progressive Disclosure

No bundle files exist and the content is under 50 lines, organized into two well-signaled sections (FAQ + diagnostic command) with clear headers; per the simple-skills note this satisfies progressive disclosure at level 3.

3 / 3

Total

11

/

12

Passed

Description

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 specific and distinct within the Feishu-plugin niche, but lacks an explicit "Use when..." trigger clause and has incomplete coverage of natural user phrasings, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause such as "Use when the user reports Feishu/Lark plugin errors, card buttons not responding, or repeated authorization failures."

Broaden trigger terms with common user phrasings (e.g. "飞书报错", "卡片点击没反应", "权限不足", "授权过期") alongside the existing technical terms.

DimensionReasoningScore

Specificity

Names multiple concrete actions: "包含常见问题 FAQ 和深度诊断命令", "会检查账户配置、API 连通性、应用权限、用户授权状态,并生成详细的诊断报告和解决方案" — a specific enumerated capability list, matching the level-3 anchor.

3 / 3

Completeness

"What" is clearly answered, and there is partial when-guidance ("诊断命令用于排查复杂问题(多次授权仍失败...)"), but there is no explicit top-level "Use when..." clause telling Claude when to invoke the skill overall, so per the guideline completeness is capped at 2.

2 / 3

Trigger Term Quality

Relevant natural terms appear ("问题排查", "授权失败", "诊断"), but coverage of variations a user might actually say (e.g. "飞书报错", "卡片没反应", "权限不足") is incomplete, matching the level-2 anchor of some keywords but missing common variations.

2 / 3

Distinctiveness Conflict Risk

"飞书插件问题排查工具" carves out a clear, narrow niche (Feishu plugin troubleshooting) with distinct triggers unlikely to collide with other skills, matching the level-3 anchor.

3 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
op7418/CodePilot
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.