CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

expert-kuaishou

快手账号运营、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

77%

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

Quality

Content

78%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 operational router skill: dense token-efficient guidance with concrete tool names, paths, error codes, and sensible stop-and-report checkpoints. Its weaknesses are delegated execution details with no inline copy-paste examples and referenced workflow/tool files that are absent from the bundle.

Suggestions

Include the referenced workflows/*.md and tools/kuaishou-publish/SKILL.md files in the bundle so the index's links resolve — currently every reference is dangling.

Inline one or two copy-paste-ready command examples (e.g. a minimal kuaishou-publish invocation or viral-chaser call) so common cases are executable without opening external files.

Make the validation loop for publishing explicit (preview → diagnose → fix → retry) in the body, since only fragments of it currently appear across separate paragraphs.

DimensionReasoningScore

Conciseness

The body is extremely dense and operational — e.g. "作品搜索不支持 --sort/--type/--time", "缺项不补零", "关注流只有首屏" — with no padding and no explanation of concepts Claude already knows. Every token earns its place, matching anchor 5 rather than anchor 4 (there is nothing to trim).

5 / 5

Actionability

Concrete, executable guidance is present: tool names invoked via wrapper ("kuaishou-publish methods"), storage paths (kuaishou/ref/, kuaishou/dna/, dna-meta.json, published-track), a specific error code (400002), and ordered steps ("先 hunter 下载,再运行 viral-chaser"). It stops short of anchor 5 because no copy-paste-ready commands or examples are inlined — execution details are delegated to workflow/tool files not present in the bundle.

4 / 5

Workflow Clarity

The task-to-workflow table plus inline sequencing and checkpoints ("先运行本地发布预览,再按需索取扫码", "完成后检查成品", stop-and-report on 400002/验证码/风控) gives a clear sequence with most checkpoints present. Not 5 because several processes (e.g. content production, benchmarking) delegate their full sequence and validation loops to workflow files that are not part of this bundle, leaving some checkpoints implicit.

4 / 5

Progressive Disclosure

The body is structured as a clean index — a table routing 7 tasks to workflow files plus a clearly signaled pointer to tools/kuaishou-publish/SKILL.md — which fits the one-level-deep reference pattern in design. However, no bundle files exist (no workflows/, tools/, references/, scripts/, or assets/), so every referenced path is dangling and unverifiable; per the guideline to score against the actual bundle structure, this caps it at anchor 3 rather than 4.

3 / 5

Total

16

/

20

Passed

Description

70%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.

A specific, well-bounded description that names concrete actions and explicitly routes collection/interaction away to sibling skills. Its main weakness is the absence of any explicit 'when to use' trigger clause, which caps completeness, and slightly incomplete keyword synonym coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions 快手/快手号, 起号, 账号定位, 短视频发布, 图文发布, or 作品复盘', to raise completeness.

Include common user-side synonyms (短视频, 涨粉, 快手号) alongside the current terms to broaden natural trigger coverage.

Mirror the body's full task table (benchmarking, editing/remake) in the description to close the coverage gaps in specificity.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("起号定位", "视频/图文内容 DNA", "制作 Brief", "发布与本人作品复盘") rather than vague domain language, but coverage has minor gaps — e.g., the benchmarking and re-editing tasks the body covers are absent — so it matches anchor 4, not the comprehensive anchor 5.

4 / 5

Completeness

The 'what' is clear (account operations, positioning, content DNA, briefs, publishing, review), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4, because 'when' is entirely absent rather than merely imprecise; not 2, because the 'what' half is concrete and specific.

3 / 5

Trigger Term Quality

Good natural keyword coverage (快手, 起号, 定位, 视频/图文, Brief, 发布, 复盘), but common synonyms like 短视频 or 涨粉 are missing and the internal router names "hunter"/"expert-bd" are not phrases a user would say. Fits anchor 4 rather than anchor 3 (coverage is clearly more than 'some') and short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The skill is platform-scoped to 快手 and explicitly de-conflicts siblings ("采集走 hunter,互动走 expert-bd"), giving it a clear niche with distinct triggers and minimal conflict risk — anchor 5. Anchor 4's 'minor overlap risk' understates the explicit boundary routing present here.

5 / 5

Total

16

/

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: 8 missing, 1 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

TeamWiseFlow/xiaobei

Path

crews/main/skills/expert-kuaishou/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.