CtrlK
BlogDocsLog inGet started
Tessl Logo

feishu-im-read

飞书 IM 消息读取工具使用指南,覆盖会话消息获取、话题回复读取、跨会话消息搜索、图片/文件资源下载。 **当以下情况时使用此 Skill**: (1) 需要获取群聊或单聊的历史消息 (2) 需要读取话题(thread)内的回复消息 (3) 需要跨会话搜索消息(按关键词、发送者、时间等条件) (4) 消息中包含图片、文件、音频、视频,需要下载 (5) 用户提到"聊天记录"、"消息"、"群里说了什么"、"话题回复"、"搜索消息"、"图片"、"文件下载" (6) 需要按时间范围过滤消息、分页获取更多消息

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

The body is dense, actionable, and well-structured: it pairs an intent-to-tool index with concrete parameter formats, sequenced scenario walkthroughs, and a troubleshooting table. It respects Claude's intelligence (no concept padding) and gives copy-paste-ready examples. Main room for improvement is tightening a few prose passages and, optionally, splitting the larger reference tables into a referenced file.

Suggestions

Tighten the prose in section 1 (time-range inference) and section 3 into terser rules so the body stays table/pointer-driven throughout.

Consider moving the detailed resource-marker and search-parameter tables into a referenced reference file, keeping SKILL.md as a lean overview with one-level-deep pointers.

Add an explicit validation checkpoint after fetch_resource and after multi-page retrieval (e.g., 'confirm result count matches expectation before reporting to user') to elevate workflow_clarity.

DimensionReasoningScore

Conciseness

Largely lean and table-driven with no padding about what Feishu/IM is; a few prose passages (e.g., section 1's inference guidance) could be tightened but every section earns its place. Not a 5 because section intros are slightly more explanatory than strictly necessary.

4 / 5

Actionability

Fully concrete: names exact tools, parameter formats (oc_xxx, omt_xxx, file_key img_xxx/file_xxx, type values), and copy-paste-ready JSON examples with realistic field shapes covering the common cases.

5 / 5

Workflow Clarity

Clear sequencing via '执行前必读', an intent→tool index, step-numbered scenarios, and a '常见错误与排查' error-recovery table. The pagination loop (has_more/page_token) acts as a checkpoint; minor gap is the absence of an explicit post-fetch validation step, so not a 5.

4 / 5

Progressive Disclosure

Single-file skill with no bundle files, well-organized into clearly headed sections and tables with a quick-index for navigation. Good structure; scored 4 rather than 5 because it exceeds the 'under 50 lines' simple-skill exception and a couple of dense reference tables could conceptually live in a separate reference file, though inlining is reasonable for this scope.

4 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 well-crafted: it states the skill's scope, enumerates concrete capabilities, and provides an explicit, naturally-phrased 'Use when...' trigger list. No padding or over-claims. Note: the description uses second-person-free third-person phrasing in the body triggers, satisfying the voice requirement.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '会话消息获取', '话题回复读取', '跨会话消息搜索', '图片/文件资源下载' — with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (tool usage guide covering four operations) and 'when' via the numbered '当以下情况时使用此 Skill' trigger list.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers users would actually say: '聊天记录', '消息', '群里说了什么', '话题回复', '搜索消息', '图片', '文件下载'.

5 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (Feishu IM message reading) with distinct triggers unlikely to conflict with unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

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.