CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

douyin-engagement

通过 HTTP 接口获取本人已发布视频和图文的基础、深度指标,复用发布 profile 登录态并回填发布记录。

Quality

76%

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/expert-douyin/tools/douyin-engagement/SKILL.md
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.

A lean, highly actionable CLI skill: executable commands for every subcommand, concrete error taxonomy with exit codes and recovery loops, and strict data-integrity rules. The main gaps are the missing post-write validation checkpoint and weakly signaled navigation to the three bundle scripts in scripts/.

DimensionReasoningScore

Conciseness

The body is dense operational text with no filler and no explanation of concepts Claude already knows ('脚本临时从 Camoufox 持久化 session douyin 的 profile 读取 cookie 和 UA…凭据只保留在进程内存'). Only the cold-start browser-session mechanics paragraph describes script internals rather than instructions to Claude, so it falls just short of the 'every token earns its place' anchor.

4 / 5

Actionability

The bash block gives copy-paste-ready commands covering all four subcommands ('douyin-engagement check / list / fetch --row-id 12 / daily') with an argument example, plus the exact recovery flow ('执行 douyin-publish login…完成后重跑 check') and concrete exit codes (SESSION_EXPIRED exit 2, PROFILE_SESSION_UNAVAILABLE exit 1). This matches the 'fully executable, covers the common cases' anchor.

5 / 5

Workflow Clarity

The flow is clear with a real feedback loop (check → login → re-check on SESSION_EXPIRED) and enumerated failure conditions with handling rules ('未找到作品、游标异常、接口空体、风控即报告原因'). It falls short of anchor 5 because there is no explicit post-write verification step after 'published-track update-metrics 写库', and the sequence is spread across prose rather than an ordered list.

4 / 5

Progressive Disclosure

For a ~25-line skill, inline content is appropriately sized, and the one named bundle file ('fetch-retro-data.ts') exists in scripts/. Minor gaps keep it below anchor 5: no section headers, the script reference is not path-linked, and the other two bundle scripts (douyin-web.ts, douyin_engagement.py) are never referenced, so navigation to the bundle is weakly signaled.

4 / 5

Total

17

/

20

Passed

Description

58%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 communicates concrete, specific capabilities in a third-person, appropriately concise form, but it is a 'what-only' description: it lacks any when-to-use trigger clause and omits the most natural keywords (抖音, 播放量, 点赞, 数据). Adding a Use-when clause with those user-facing terms would lift both completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for 抖音已发布作品的播放量、点赞、评论等数据 or wants to backfill metrics for publish records.'

Include the natural keywords users would actually say — 抖音, 播放量, 点赞, 评论, 数据 — instead of only the internal phrasing '基础、深度指标'.

Drop implementation jargon like '复用发布 profile 登录态' from the description (it belongs in the body) and replace it with user-facing capability language.

DimensionReasoningScore

Specificity

It lists several concrete actions — '获取本人已发布视频和图文的基础、深度指标', '复用发布 profile 登录态', '回填发布记录' — naming both content types. It is below anchor 5 because it never names the actual metrics (播放、点赞、评论、分享) and stays above anchor 3's '1-2 concrete actions' level.

4 / 5

Completeness

The 'what' is clearly stated (fetch basic/deep metrics for published videos and photo posts via HTTP, backfill publish records), but there is no 'Use when…' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Some relevant keywords are present ('已发布视频', '图文', '指标', '发布记录') but the most natural user terms are missing: the word 抖音/Douyin itself, 播放量, 点赞, 评论, 数据. Phrases like '复用发布 profile 登录态' are internal implementation jargon users would never say, matching the 'missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche — metrics collection and record backfill for one's own published Douyin works — with distinct intent from the sibling publish skill. '复用发布 profile 登录态' hints at overlap with that closely related skill, so it sits at anchor 4 rather than 5.

4 / 5

Total

14

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

TeamWiseFlow/xiaobei

Path

crews/main/skills/expert-douyin/tools/douyin-engagement/SKILL.md

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.