CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tiktok-interact

TikTok作品互动,支持范围以工具能力表为准。

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-bd/tools/tiktok-interact/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.

The body is an exemplary lean operational reference: concrete commands, quantified defaults, explicit safety guards and failure-handling rules for risky write operations, and clear one-level handoffs to sibling skills. The only gaps are a placeholder for the 'call' subcommand and the absence of section headers.

DimensionReasoningScore

Conciseness

The body is extremely dense — every sentence carries an operational fact or constraint ("写操作默认预览,已有授权时加 --confirm", "列表默认20条、最多100条", "不无限监听,不把样本当完整历史") with zero explanation of concepts Claude already knows. This matches the 'lean and efficient, every token earns its place' anchor exactly.

5 / 5

Actionability

Commands are concrete with real flags (tiktok-interact like "<作品链接>", comment --text, reply --reply-to, follow --confirm), and defaults are quantified. It falls short of fully copy-paste ready because 'call <resource> <action> [平台选项]' is a placeholder pattern with no concrete example, matching the 'concrete commands with minor gaps' anchor.

4 / 5

Workflow Clarity

The risky write operations have explicit validation checkpoints: default preview gated by --confirm, pre-request blocking when ticket-guard material is missing ("脚本在请求前阻止"), a defined failure protocol ("超时/断连先核对结果,不换通道重发"), and mandatory local verification of responses. It sits above the checkpoint-missing anchor but below 5 because the sequence is rule-based paragraphs rather than an explicit ordered workflow with feedback loops.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references; handoffs to sibling skills (tiktok-hunter, expert-osbi, expert-bd) are clearly named and one level deep. It misses 5 because the body is paragraph-based with no section headers to aid navigation, fitting the 'good structure, minor organization gaps' anchor.

4 / 5

Total

17

/

20

Passed

Description

48%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 correctly identifies the niche but is under-specified: it delegates capability enumeration to a capability table and omits any 'use when' trigger guidance. Concrete actions and trigger phrases exist in the body but were not surfaced into the description.

Suggestions

Enumerate the concrete actions in the description itself, e.g. 点赞/收藏/关注/评论 TikTok 作品及管理收藏夹, instead of deferring scope to the tool capability table.

Add an explicit trigger clause such as 'Use when 需要对 TikTok 作品或账号执行点赞、收藏、关注、评论等互动操作时'.

Include natural user vocabulary and synonyms (点赞, 收藏, 关注, 评论, TikTok 视频/作品) so the description surfaces the phrases users actually say.

DimensionReasoningScore

Specificity

The description names the domain ("TikTok作品互动") but the action is generic — the concrete verbs (like, favorite, follow, comment) appear only in the body — and "支持范围以工具能力表为准" defers scope to a capability table instead of stating actions. This matches the anchor for naming the domain with minimal or generic actions, not the level above which requires 1-2 concrete stated actions.

2 / 5

Completeness

A "what" is present (interacting with TikTok works) but the "when" is entirely absent, which caps completeness at 3 per the missing-'Use when' guideline. It is not 2 because the what identifies a concrete domain and action category rather than being purely vague.

3 / 5

Trigger Term Quality

"TikTok" and "作品互动" are relevant natural keywords, but the description misses the common phrases a user would actually say (点赞, 收藏, 关注, 评论, video/TikTok post terms). Some relevant keywords with missing variations matches anchor 3; it is above anchor 2 because TikTok is a specific, naturally spoken trigger, not generic filler.

3 / 5

Distinctiveness Conflict Risk

"TikTok作品互动" carves a distinct niche (interaction actions) versus sibling skills like tiktok-hunter (collection/search), with only minor overlap risk against closely related TikTok skills. This matches the 'mostly distinct' anchor rather than 5 because the single generic word 互动 leaves some overlap with any TikTok-engagement skill.

4 / 5

Total

12

/

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-bd/tools/tiktok-interact/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.