CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

expert-twitter

X/Twitter账号运营、起号定位、视频/图文内容 DNA、制作 Brief、发布与本人作品复盘;采集走 hunter,互动走 expert-bd。

Quality

72%

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-twitter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 exceptionally lean and packed with non-obvious operational constraints (weight limits, permission gotchas, unsupported features, storage layout, role split between main and content-producer). Its main weaknesses are that every detailed workflow is delegated to files absent from the bundle and no command syntax is given, leaving navigation and executable detail incomplete.

Suggestions

Include the referenced workflows/*.md files (account-setup, style-dna, content-production, native-ui-cards, account-benchmark, editing, review) in the bundle, or inline their key step sequences — all seven links currently dead-end.

Add at least one example wrapper invocation (e.g., a twitter-post call with preview check and warnings output) so the publish flow is copy-paste executable rather than 'read the tool docs' pointers.

Consolidate the unsupported-feature lists (通知、直播、关注流、粉丝/关注列表、收藏列表), currently scattered across two paragraphs, into a single '不支持' section so capability boundaries are scannable in one place.

DimensionReasoningScore

Conciseness

The body is telegraphic and dense with non-obvious operational specifics ('保持在280权重内(纯中文约140字)', '媒体搜索 --type video/image 不支持 --sort latest', '登录校验成功不等于有长推权限') and contains no concept explanations or padding. Every line carries information Claude could not know on its own.

5 / 5

Actionability

It names concrete tools (`twitter-post`, `twitter-engagement`, `twitter-style-profiler`, `x-hunter login/export`, `viral-chaser`, `video-edit/talking-head-cut`), storage paths (`twitter/ref/`, `twitter/outputs/`, `twitter/dna/`), and explicit decision rules ('帖串每条分别检查,不能自动拆帖', '缺项不补零'). Minor gaps: no command/wrapper syntax examples, and tool usage details are delegated to docs ('读取本包 tools 下对应说明') that are not present in the bundle.

4 / 5

Workflow Clarity

Ordered steps and validation checkpoints exist for video ('视频样本先 hunter 下载,再运行 viral-chaser'; '完成后检查成品') and publishing ('发布前检查…逐条权重和 warnings;超限先精简,不直接提交' — a check→fix→retry loop). However, sequences for most of the seven routed workflows (account setup, style DNA, content production, benchmarking, editing, review) are delegated entirely to `workflows/*.md` files that are absent from the bundle, leaving the actual step sequences unavailable.

3 / 5

Progressive Disclosure

The task→workflow routing table is good progressive-disclosure design in form, but the bundle contains no files at all: all seven `workflows/*.md` links, the 'tools 下对应说明' docs, and the DNA 文档/template are dead references. Navigation dead-ends, which is worse than inlining the content.

2 / 5

Total

14

/

20

Passed

Description

66%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 packs several concrete, domain-specific actions and explicit sibling-skill routing into one terse line, giving it a clear niche and good trigger vocabulary. Its main weakness is the complete absence of 'when to use this' trigger guidance, which caps completeness and leaves activation dependent on keyword luck.

Suggestions

Add an explicit trigger clause, e.g. '当用户要求运营/起号/发布 X(Twitter) 账号、建立内容风格或复盘本人作品时使用' — a 'Use when…' equivalent currently caps completeness at 3.

Add common user phrasings as trigger terms (推文/发推/发推特/涨粉/运营推特) to broaden natural-keyword coverage beyond the current set.

DimensionReasoningScore

Specificity

It lists several concrete actions — 'X/Twitter账号运营、起号定位、视频/图文内容 DNA、制作 Brief、发布与本人作品复盘' — plus explicit routing ('采集走 hunter,互动走 expert-bd'). Not 5 because coverage is compressed into noun phrases with minor gaps (e.g., benchmarking/editing workflows are not surfaced in the description); clearly above anchor 3's '1-2 concrete actions'.

4 / 5

Completeness

The 'what' is clear and multi-action, but there is no 'Use when…' clause or equivalent explicit trigger guidance anywhere in the description; per the judging guidelines this caps completeness at 3. Not 2 because the 'what' is concrete and comprehensive, not vague.

3 / 5

Trigger Term Quality

Good natural keyword coverage: 'X/Twitter', '账号运营', '起号', '定位', '视频/图文', 'Brief', '发布', '复盘' are phrases a Chinese-speaking user managing this account would actually say. Not 5 because common variations like '推文', '发推', '涨粉' are missing.

4 / 5

Distinctiveness Conflict Risk

A clear X/Twitter account-operations niche with explicit sibling-skill routing ('采集走 hunter,互动走 expert-bd') that actively disambiguates from related skills. Not 5 because interaction-adjacent requests (reply, like, DM) could still plausibly trigger expert-bd instead; minor overlap risk remains.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation — 13 / 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

relative_links

Relative link issues: 7 missing

Warning

Total

13

/

16

Passed

Repository

TeamWiseFlow/xiaobei

Path

crews/main/skills/expert-twitter/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.