CtrlK
BlogDocsLog inGet started
Tessl Logo

twitter-interact

Twitter/X 互动操作技能——支持点赞 / 取消点赞 / 转推 / 取消转推 / 收藏 / 取消收藏 / 关注 / 取关。camoufox-cli 主推路径 + 持久化 session `twitter`(与 twitter-post 共用,自管探活登录)+ 频率限制。

60

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/twitter-interact/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 executable commands, concrete selectors, and well-sequenced workflows carrying explicit validation checkpoints. It is held back from the top band by repeated session/profile explanation and a dangling docs/ reference that does not exist in the bundle.

Suggestions

Consolidate the repeated 'session twitter 共用 / 登录态落磁盘 profile / 重起无头复用' explanation into one authoritative section and reference it elsewhere instead of restating it five times.

Fix the dangling reference to docs/post-deploy-verification.md — either add the file to the bundle or remove/replace the pointer — so progressive-disclosure navigation is not broken.

Verify the external 'browser-guide' skill reference exists in the user's environment or inline the minimal headed-login steps to avoid an unresolvable cross-skill dependency.

DimensionReasoningScore

Conciseness

Mostly lean and assumes Claude's competence, but the session-sharing and '登录态落磁盘 profile / 重起无头复用' points are restated across the callout, 前置条件, 使用方式, 相关 skill, and Notes sections, adding redundant tokens that could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready invocations (e.g. 'camoufox-cli --session twitter --persistent --json open', 'twitter_interact like https://x.com/username/status/1234567890') with specific selectors and concrete poll parameters, matching the 'fully executable code/commands' anchor.

3 / 3

Workflow Clarity

Each action has a clearly numbered sequence with explicit validation checkpoints — button-flip verification ('_poll_probe(tid,["unlike"]) 验翻转'), 10s-not-found → exit 1, pre-operation check_freq_limit — plus an error-handling table with a cookie-fail → relogin → retry feedback loop.

3 / 3

Progressive Disclosure

Keeps the overview in SKILL.md and correctly pushes implementation detail to scripts/twitter_interact.py (one level deep), but references docs/post-deploy-verification.md (line 259) which is absent from the bundle, leaving a broken navigation pointer.

2 / 3

Total

10

/

12

Passed

Description

67%

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 and well-scoped, listing all eight engagement actions and cleanly distinguishing the skill from twitter-post. Its main weakness is the missing explicit 'Use when...' trigger guidance and limited trigger-term variation, which cap completeness and trigger quality at 2.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to like, retweet, bookmark, follow, or unfollow on Twitter/X' to answer the 'when' half of completeness.

Broaden trigger terms with common user phrasings and English equivalents (e.g. 'like/点赞', 'retweet/转推', 'follow/关注', 'bookmark/收藏') so natural utterances map more directly to the skill.

Trim the implementation-path detail ('camoufox-cli 主推路径 + 持久化 session... + 频率限制') from the description; it dilutes the user-facing trigger focus and belongs in the body.

DimensionReasoningScore

Specificity

Lists eight concrete engagement actions explicitly ('点赞 / 取消点赞 / 转推 / 取消转推 / 收藏 / 取消收藏 / 关注 / 取关') plus the implementation path and rate limiting, matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly states what the skill does (the eight actions) but lacks any 'Use when...' or equivalent explicit trigger guidance for when Claude should invoke it, capping completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

Contains natural Chinese terms users would say (点赞/转推/关注/收藏) but presents them as action labels rather than user-utterance variations and omits English equivalents, matching 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

Scoped tightly to Twitter/X engagement ('Twitter/X 互动操作技能') and explicitly carves Reply/Quote out to twitter-post, giving it a clear niche unlikely to conflict with sibling skills.

3 / 3

Total

10

/

12

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.