CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

huashu-video-outline

快速生成2-3个视频大纲方案,含标题、封面建议和结构设计。当用户提到"视频大纲"、"视频结构"、"脚本大纲"、"视频选题"时使用。

Quality

78%

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 ./huashu-video-outline/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-structured, actionable instruction skill: a concrete output template, five worked title formulas, and conditional cover strategies give Claude exactly what to produce. Weaknesses are non-instructional padding (promo footer and last-updated date), an incompletely specified workflow (nothing after user selection), and inline reference material that keeps organization a notch below ideal.

Suggestions

Remove the promotional author footer and the '最后更新: 2025-11-07' line (or move version notes into a dedicated section) — they consume tokens with no instructional value.

Add a short closing step specifying what to do after the user selects a proposal (e.g., refine it into the full script or hand off to the next skill step), completing the workflow.

Explain the template placeholders (how many 演示 items, how to choose 时长预估 ranges) or move the title/cover strategy details into a references/ file so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The core sections (output template, one-line title formulas, cover strategy bullets) are lean, but the body carries non-instructional padding: a promotional author footer ("花叔出品 | … 30万+粉丝 …《一本书玩转DeepSeek》"), a time-sensitive "最后更新: 2025-11-07" date outside any deprecated section, and an intro line duplicating the description. Mostly efficient but clearly could be tightened, matching anchor 3 rather than the minor-trim anchor 4.

3 / 5

Actionability

Concrete guidance throughout: a copy-paste markdown output template with per-section timings ("开头(30秒-1分钟):确认标题承诺 + 建立悬念"), five worked title formulas ("1个功能 vs 10个工具"), and conditional cover rules ("< 10万粉:结果展示封面优先"). Minor gaps keep it below anchor 5: placeholders (xxx) are unexplained and 时长预估 is hardcoded to 5-8分钟 in the template.

4 / 5

Workflow Clarity

The sequence is discernible (trigger → generate 2-3 proposals per template → apply title/cover strategies → "等待用户选择,不假设" as an explicit checkpoint), and no destructive/batch cap applies. Not anchor 5 because the steps are scattered across 何时使用/核心功能/注意事项 rather than sequenced, and the post-selection step (what happens after the user picks a proposal) is never defined.

4 / 5

Progressive Disclosure

No bundle files exist and none are referenced, and the sections are well-organized with clear headers, so navigation is easy. It sits just above the under-50-line simple-skill carve-out (~62 body lines), and the 标题策略/封面策略 reference material plus the off-topic promotional footer are inlined rather than separated — good structure with minor organization gaps, matching anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Description

78%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 strong description that clearly states what the skill does and when to use it, with four natural Chinese trigger phrases. Its main weakness is narrow capability coverage — the title-formula and cover-strategy work documented in the body is not reflected in the description.

Suggestions

Enumerate the concrete actions in the description, e.g. add applying title contrast formulas and follower-count-based cover selection alongside 'generate outline proposals with titles, covers, and structure'.

Add one or two missing natural trigger variants users might say, such as '给几个方案' or bare '大纲', to widen keyword coverage.

DimensionReasoningScore

Specificity

"快速生成2-3个视频大纲方案,含标题、封面建议和结构设计" names the domain and one concrete action with its deliverables, but capabilities the skill actually performs (5 title contrast formulas, follower-count-based cover strategy) are absent, matching '1-2 concrete actions, not comprehensive'. It is not a 4 because the action list is a single generate step rather than several specific actions.

3 / 5

Completeness

It explicitly answers both: what ("快速生成2-3个视频大纲方案,含标题、封面建议和结构设计") and when ("当用户提到…时使用") with concrete trigger phrases, matching the top anchor exactly. The 'Use when' clause is present, so no cap applies.

5 / 5

Trigger Term Quality

Four natural, user-sayable trigger phrases are quoted ("视频大纲"、"视频结构"、"脚本大纲"、"视频选题"), giving good keyword coverage with synonyms. Not a 5 because common variations such as the bare "大纲"、"给几个方案"、or "视频策划" are missing.

4 / 5

Distinctiveness Conflict Risk

The video-outline niche is mostly distinct with dedicated triggers, but "视频结构" and "视频选题" are broad enough to overlap with a topic-selection or script-writing skill — minor overlap risk, matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

16

/

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

alchaincyf/huashu-skills

Path

huashu-video-outline/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.