CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kuaishou-publish

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

Quality

75%

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/expert-kuaishou/tools/kuaishou-publish/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 content is exceptionally actionable — copy-paste commands, hard platform limits, and an explicit outcome-state machine for record keeping — with a clearly sequenced private-publish workflow and genuine validation checkpoints. Its weaknesses are organizational: repeated safety rules inflate token cost, and the absence of any section headers makes the dense material hard to navigate. Consolidating duplicated rules and adding headers would address both without losing operational detail.

Suggestions

Add section headers (e.g. ## 协作流程 / ## 预览与登录 / ## 视频与图集约束 / ## 提交结果与状态 / ## 失败与风控) so the dense content is scannable without reading every paragraph.

Consolidate the repeated receipt-preservation, no-resend, and publish-authorization rules into a single section to remove redundant tokens.

Consider moving the result.publication field semantics and state-combination meanings (accepted/id_resolved/resolution_pending/ownership_status) into a small reference file, keeping only the decision rules inline.

DimensionReasoningScore

Conciseness

The body is dense with zero conceptual padding and assumes Claude's competence, but several safety rules are stated two to three times (receipt preservation: "保留收据,不自行删除后重发" vs "不要删除收据换目录重发"; no-resend on failure; publish-authorization preconditions), so it could be meaningfully tightened — fitting 'mostly efficient but could be tightened' rather than the minor-trim profile of a 4.

3 / 5

Actionability

Fully executable copy-paste commands cover both main branches (image: "kuaishou-publish publish --text @/绝对路径/body.txt --image ... --account default --confirm"; video: "--visibility private"), with hard limits (4 hashtags, 图集 1–31 张每张不超过 15MB), explicit flag constraints, and precise decision rules for outcome states ("published:true, recorded:false" → rerun same directory only to complete the record).

5 / 5

Workflow Clarity

The 4-step sequence has explicit validation checkpoints (preview without --confirm before requesting login, confirm the private submission result, verify via kuaishou-engagement after the user publishes) and error-recovery rules for failures and ambiguous states, so the destructive-operation cap does not apply; it is not a 5 because critical workflow rules (forbidden-resend logic, state handling) are scattered across later unstructured paragraphs rather than sequenced with the main flow.

4 / 5

Progressive Disclosure

No bundle files exist and all content is appropriately inline for a ~50-line skill, but the body has no section headers — dense paragraphs covering distinct topics (workflow, media constraints, result semantics, error handling) are navigable only by full scanning, matching 'some structure but could be better organized' rather than the well-organized-sections bar for a 5.

3 / 5

Total

15

/

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 is concise, concrete, and clearly niche-scoped to Kuaishou publishing, listing the four core pipeline actions without any fluff. Its main weakness is the complete absence of 'when to use' trigger guidance, which both caps completeness and limits its usefulness for skill selection. Adding an explicit trigger clause and content-type terms (视频/图集) would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "需要向快手发布视频或图集,或用户提到快手发布、发快手、上传作品到快手时使用。"

Include natural content-type keywords (视频、短视频、图集) in the description so common user phrasings match.

Briefly hint at the private-first publish-then-manual-public workflow, since it is the skill's defining behavior and a commitment users should know up front.

DimensionReasoningScore

Specificity

Lists four concrete pipeline actions — "脚本预览、媒体上传、提交结果保存和 published-track 入库" — naming the Kuaishou domain, but omits notable skill functions (login handling, result-state verification, the private-then-public collaboration flow), matching 'several specific actions; minor gaps' rather than the comprehensive coverage of a 5.

4 / 5

Completeness

The 'what' is explicit (preview, upload, result saving, published-track entry), but there is no 'Use when...' clause or any equivalent trigger guidance, which caps completeness at 3 per the rubric guideline; it is not a 2 because the 'what' is clear and specific.

3 / 5

Trigger Term Quality

"快手" and "内容发布/上传" are terms a user would naturally say when needing this skill, giving good keyword coverage, but common variations like "视频", "短视频", and "图集" are absent, so it falls short of the comprehensive synonym coverage anchor.

4 / 5

Distinctiveness Conflict Risk

The Kuaishou platform niche plus the publish action is mostly distinct, but the body references sibling skills (kuaishou-hunter, kuaishou-engagement, published-track) that share the "快手" trigger space, leaving minor overlap risk with closely related skills rather than the minimal risk of a 5.

4 / 5

Total

15

/

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-kuaishou/tools/kuaishou-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.