CtrlK
BlogDocsLog inGet started
Tessl Logo

wx-mp-engagement

微信公众号已发布作品数据抓取,写入 published-track的 pub_wx_mp 表。wx_mp session 登录。

53

Quality

60%

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 ./crews/main/skills/wx-mp-engagement/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 and well-structured with a concrete sequenced fetch workflow, explicit login validation, and a thorough pitfalls section; its main weakness is redundant restatement of the relogin/cookie-export constraints across multiple sections.

Suggestions

Consolidate the relogin flow and '不导出 cookie/UA/token' constraint into a single authoritative section and cross-reference it instead of restating verbatim in 前置条件, fetch流程, 约束, and Pitfalls.

Replace the '<innerText 解析 JS>' placeholder in step 6 with the actual eval JS or an explicit pointer to the function in scripts/fetch_engagement.py.

Add an explicit 'see scripts/fetch_engagement.py' link near the CLI section so the backing implementation is clearly signaled.

DimensionReasoningScore

Conciseness

Content is high-signal domain knowledge with no generic-concept padding, but the relogin flow and the '不导出 cookie/UA/token' constraint are restated verbatim across 前置条件, fetch流程, 约束, and two Pitfalls entries, which could be tightened.

3 / 5

Actionability

Provides copy-paste-ready CLI commands, exact camoufox-cli invocations with flags, full list-page URLs with token params, and a 9-step fetch sequence; the only gap is the innerText-parsing eval JS shown as a '<innerText 解析 JS>' placeholder rather than real code.

4 / 5

Workflow Clarity

The fetch flow is a clearly numbered 9-step sequence with an explicit login-state validation checkpoint (redirect URL → exit 2) and a relogin feedback loop; minor validation gaps remain in the batch fetch-all path beyond the pitfalls coverage.

4 / 5

Progressive Disclosure

Well-organized into clear sections (前置条件/CLI/工作流程/集成/约束/Pitfalls/Notes) with the 694-line implementation correctly kept in scripts/fetch_engagement.py and one-level-deep references to sibling published-track scripts; the body script itself is not explicitly linked by path.

4 / 5

Total

15

/

20

Passed

Description

53%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 concrete and clearly niche-scoped to WeChat official-account engagement scraping into a specific table, but it lacks any 'Use when' trigger guidance and omits the specific metric names a user would naturally invoke.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when fetching reads/likes/comments/shares/favorites for published WeChat official-account articles.'

Name the concrete metrics captured (阅读/点赞/评论/分享/收藏) so the trigger terms match what users actually say.

Mention the camoufox/browser-based mechanism briefly to distinguish from the pure-HTTP engagement skills (xhs/bilibili/douyin/kuaishou).

DimensionReasoningScore

Specificity

Names the domain and concrete actions ('已发布作品数据抓取', '写入 published-track的 pub_wx_mp 表', 'wx_mp session 登录') but is terse and omits which metrics (reads/likes/comments) are scraped, so coverage is not comprehensive.

3 / 5

Completeness

The 'what' is clear (scrape published-work data, write to pub_wx_mp) but there is no 'when'/'Use when' trigger guidance at all, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Contains relevant natural terms ('微信公众号', '已发布作品', '数据抓取') but misses the common variations a user would actually say (阅读/点赞/评论/互动数据) and any 'engagement' synonym.

3 / 5

Distinctiveness Conflict Risk

Narrowly scoped to the wx_mp platform and the pub_wx_mp table, making it mostly distinct from sibling engagement skills, though terse phrasing leaves minor overlap risk with the broader published-track family.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
TeamWiseFlow/xiaobei
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.