CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kuaishou-style-profiler

快手定性内容 DNA 的样本报告、聚合模板和增量更新。

Quality

74%

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-style-profiler/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.

A lean, command-first skill body that respects the token budget while packing in concrete CLI usage, a clearly sequenced report/build/update workflow with user-confirmation checkpoints, and explicit per-medium dimension checklists including edge-case handling (visual dims marked N/A for text-only samples). Remaining gaps are minor: the update command is not shown, no error-recovery loop is specified, and the dense paragraphs would benefit from section headers.

DimensionReasoningScore

Conciseness

The body is lean and dense with operational content only — commands up front, then usage constraints ("统计 scaffold 不能替代 Agent 回读素材后的定性结论", "视频与图文/文字分别建 DNA,不混合样本统计") and dimension checklists, with zero padding or explanations of concepts Claude already knows. It matches anchor 5: every token earns its place.

5 / 5

Actionability

Concrete, executable commands are provided ("kuaishou-style-profiler report --input /绝对路径/样本文字稿.md --sample-id sample-01 --dna-id dna-0 --kind video") along with specific per-stage directives ("记录样本分母、共性、局部借鉴和例外"), and full parameter details are properly deferred to --help. It falls short of anchor 5 because the update command is never shown and some guidance is principle-level rather than executable (e.g. "用户偏好要转译到具体维度").

4 / 5

Workflow Clarity

The report → build → update sequence is clearly delineated with per-stage deliverables ("report 逐篇描述观测与依据;build 回读全部报告…再完善 DNA 文档与 template"), and there are guardrails/checkpoints such as "DNA 调整经用户确认后写入" and "少量样本不得称为稳定风格". It does not reach anchor 5 because there is no explicit validate→fix→retry feedback loop for error recovery.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no external bundle files needed; full CLI parameters are appropriately deferred to --help and outputs live in a documented default location ("kuaishou/dna/<dna-id>/"), which is good just-in-time structure. It misses anchor 5 because the body has no section headers — commands, usage constraints, workflow, and dimension checklists flow as undifferentiated dense paragraphs, creating minor navigation gaps.

4 / 5

Total

17

/

20

Passed

Description

53%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 identifies a distinct, well-scoped niche (Kuaishou qualitative content DNA) and enumerates three concrete deliverables, but it is a terse noun fragment with no trigger guidance. Missing 'when to use' phrasing and natural keyword variants (风格, 短视频, 图文) cap completeness and trigger quality at mid-scale.

Suggestions

Add an explicit trigger clause, e.g. "Use when profiling the style of Kuaishou (快手) accounts or building style DNA from video/image-text content samples" (使用于分析快手账号或内容风格、从视频/图文样本构建风格 DNA 时), to raise completeness above the cap of 3.

Include natural terms users would actually say — 快手, 风格, 短视频, 图文, 账号, 爆款分析 — alongside 内容 DNA to improve trigger_term_quality.

State capabilities as verb-led actions with their outputs, e.g. "Generates per-sample style reports, aggregates them into a content DNA document and creation template, and incrementally updates the DNA as new samples arrive", to strengthen specificity.

DimensionReasoningScore

Specificity

The description lists three domain-specific deliverables ("样本报告、聚合模板和增量更新") for "快手定性内容 DNA", but they appear as bare noun fragments without verbs, and coverage is incomplete — no mention of building the DNA document/template or the video vs. image-text split. It sits between anchor 3 (1-2 concrete actions) and anchor 4 (several actions, minor gaps): three items are listed, but the gaps are more than minor, so 3 fits best.

3 / 5

Completeness

The 'what' is present and fairly clear (sample reports, aggregation templates, incremental updates for Kuaishou qualitative content DNA), but the 'when' is entirely missing — there is no "Use when…" clause or equivalent trigger guidance, which per the rubric guidelines caps completeness at 3. It cannot score 4 because the 'when' is not even weakly implied.

3 / 5

Trigger Term Quality

"快手" and "内容 DNA" are relevant niche keywords a user might say, but common natural variations and synonyms — 风格 (style), 短视频 (short video), 图文 (image-text), 账号 (account) — are absent. This matches anchor 3 (some relevant keywords, missing common variations); it is not anchor 4 because keyword coverage is thin rather than good-with-few-missing.

3 / 5

Distinctiveness Conflict Risk

"快手定性内容 DNA" carves out a clearly platform-specific niche with minimal conflict risk against unrelated skills. It falls short of anchor 5 because the limited trigger phrasing (no 'use when' clause, few keyword variants) leaves minor overlap risk with closely related platform-style-profiler skills.

4 / 5

Total

13

/

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-style-profiler/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.