CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tiktok-publish

TikTok内容发布:脚本预览、媒体上传、提交结果保存和 published-track 入库。

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 skill: fully executable commands, explicit validation gates before the destructive --confirm step, and well-defined failure/recovery semantics, all within a compact single file. The only minor weakness is that the workflow sequence is conveyed in dense prose rather than an ordered checklist, which keeps workflow clarity just below the top anchor.

DimensionReasoningScore

Conciseness

The ~23-line body is dense operational prose with zero padding and no explanations of concepts Claude already knows; every sentence carries a specific rule (file handling, quoting, flags, failure semantics). Matches 'lean and efficient; every token earns its place' — not 4 because nothing can be trimmed without losing operational content.

5 / 5

Actionability

Provides two copy-paste-ready `tiktok-publish publish` commands with full flags, complete invocations of `tiktok-publish check` and `tiktok-publish methods`, and concrete value domains (`public/private/friends`, `on|off`, video-requires-cover). Matches 'fully executable; copy-paste ready commands covering the common cases' — the only placeholders are file paths, which is expected.

5 / 5

Workflow Clarity

A chronological sequence is present (login/export → check → prepare body file → preview → 核对 → --confirm → result file → published-track) with explicit validation checkpoints and error-recovery paths (stop on failure/risk-control/timeout; recorded:false → re-run only ingests; unknown results → no re-send). Not 5 because the sequence is prose-implicit rather than an ordered checklist and a few transitions must be inferred; not 3 because validation for this risky operation is explicit, satisfying the destructive/batch cap.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, has no bundle files and needs no external references; content is appropriately placed in a logical paragraph flow (auth → check → command → defaults → confirm → results → failure handling). Per the rubric's simple-skill guideline this qualifies for 5; not 4 because there is nothing that belongs in a separate file at this size.

5 / 5

Total

19

/

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 is terse and names several concrete actions, but it reads as a compressed capability list rather than a trigger-oriented description. It completely lacks a 'when to use' clause and natural trigger synonyms, which caps both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to publish, post, or upload content (video or images) to TikTok.'

Include natural synonyms users would actually say — 发布视频 / 发作品 / post to TikTok / upload video — so the skill triggers on phrasing variants.

Briefly mention the key subcommands surfaced in the body (check, methods) and distinguish this skill from the read-only tiktok-hunter collection skill to reduce conflict risk.

DimensionReasoningScore

Specificity

Names the domain and four concrete actions ('脚本预览、媒体上传、提交结果保存和 published-track 入库'), matching 'several specific actions; minor gaps'. Not 5 because the description omits much of the body's actual scope (check, methods, visibility, permission flags).

4 / 5

Completeness

The 'what' is clear (preview, media upload, result saving, published-track ingestion) but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3. Not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Contains relevant keywords ('TikTok', '发布', '媒体上传', 'published-track') but misses common natural variations users would say ('发布视频', '发作品', 'post to TikTok', '上传视频'), matching 'some relevant keywords but missing common variations or synonyms'. Not 4 because coverage is sparse for a single terse line with no synonyms.

3 / 5

Distinctiveness Conflict Risk

'TikTok内容发布' carves a mostly distinct publishing niche, but the body references a sibling tiktok-hunter collection skill, creating minor overlap risk with a closely related skill. Not 5 because the description alone does not distinguish publishing from TikTok collection/scraping skills.

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-tiktok/tools/tiktok-publish/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.