CtrlK
BlogDocsLog inGet started
Tessl Logo

wechat-hotspot-publisher

自媒体创作者和运营专员在需要全网追热点分发时,使用此技能可自动采集热点并10分制筛选优质选题,AI一键生成适配公众号、小红书、B站的爆款图文与HTML排版,直接发布至各平台草稿箱,轻松完成多平台高质量内容分发。

56

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/wechat-hotspot-publisher/wechat-hotspot-publisher/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 highly actionable with concrete publish/filter/image commands and a sensible generate-then-publish flow, but it is padded with significant repetition, lacks validation/error-recovery loops for outward-facing publishing, and leaves half its reference bundle unlinked. Tightening duplication and wiring up the orphaned references would substantially improve it.

Suggestions

Remove duplicated blocks — keep 排版规范/颜色规范 in html-layout-guide.md only and reference it once; delete the redundant 默认模式 section and the second 推送后操作 block.

Add an explicit validation/feedback loop for publishing: check the returned draft ID, handle non-success responses, and retry or surface the error before declaring success.

Link the four orphaned reference files (bilibili/wechat/xiaohongshu api-guides, content-template) from the relevant script sections so the full bundle is navigable.

DimensionReasoningScore

Conciseness

Noticeably verbose with repeated sections: 排版规范/颜色规范/局部划线 appears in 阶段一 3.5, again in 注意事项→排版规范, and again in 默认模式; the 默认模式 block rehashes 阶段一; 推送后操作 and the publish commands are duplicated; this is padding rather than concept-explanation, so it lands at 2 rather than 1.

2 / 5

Actionability

Provides mostly executable, copy-paste-ready commands ('python scripts/publish_wechat.py --mode custom_api --title ... --content ... --cover ... --tags ...'), a concrete JSON file format, and specific filter/image-search invocations; held at 4 because some steps are delegated vaguely to '智能体根据...生成' without a script call and error/return-value handling is unspecified.

4 / 5

Workflow Clarity

A clear two-phase sequence exists (生成→预览调整→一键推送) with a human-confirm checkpoint and draft-box safety, but publishing to external platforms is an outward-facing/batch operation and the workflow lacks an explicit validate/recover loop (no 'verify returned draft ID', no error-handling/retry), so per the batch-operation cap it cannot exceed 3.

3 / 5

Progressive Disclosure

Some structure with one-level-deep, well-signaled references (viral-content-templates.md, html-layout-guide.md, sources-config.md each get a '何时读取' note), but 4 of 7 reference files (bilibili-api-guide.md, wechat-api-guide.md, xiaohongshu-api-guide.md, content-template.md) are never linked from the body, and HTML排版规范 is inlined despite a dedicated reference file existing.

3 / 5

Total

12

/

20

Passed

Description

78%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 specific, trigger-rich, and distinct, clearly conveying both capability and use scenario. Its main weaknesses are a second-person voice ('使用此技能') that costs a specificity point and a 'when' clause that is explicit but not as concretely enumerated as the top anchor.

Suggestions

Rewrite in third person ('采集热点、筛选选题、生成多平台图文与HTML排版并发布至草稿箱') to remove the second-person '使用此技能' voice penalty.

Expand the 'when' clause into concrete enumerated triggers, e.g. '当用户提到追热点、多平台发文、公众号/小红书/B站投稿或爆款图文时使用'.

Trim marketing fluff ('爆款', '轻松完成...高质量内容分发') to keep the description lean and avoid over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('自动采集热点并10分制筛选优质选题', 'AI一键生成...爆款图文与HTML排版', '直接发布至各平台草稿箱') with comprehensive coverage; held at 4 rather than 5 because the second-person imperative '使用此技能' ('use this skill') triggers the third-person-voice penalty, and trailing fluff ('轻松完成...高质量内容分发') pads rather than specifies.

4 / 5

Completeness

Answers both 'what' (采集→筛选→生成→排版→发布草稿箱) and 'when' via the explicit trigger clause '在需要全网追热点分发时', so it is not capped at 3; held at 4 because the 'when' names a scenario but lacks the concrete, enumerated trigger phrases of a 5-anchor example.

4 / 5

Trigger Term Quality

Strong natural keywords users would actually say — '全网追热点分发', '热点', '多平台', and the platform names '公众号、小红书、B站' (with B站 as a synonym for 哔哩哔哩) plus '草稿箱'; not a 5 because common phrasings like '发文/投稿' and file-format triggers are absent.

4 / 5

Distinctiveness Conflict Risk

Clear niche (multi-platform hotspot content publishing to draft boxes) with distinct, specific triggers (named platforms + 10-point topic scoring) and minimal overlap risk with other skills.

5 / 5

Total

17

/

20

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
anbeime/skill
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.