CtrlK
BlogDocsLog inGet started
Tessl Logo

huashu-speech-coach

演讲与分享教练。基于Patrick Winston(MIT AI教授)的How to Speak方法论,帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"、"如何讲"、"演讲结构"时使用此技能。

68

Quality

81%

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

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.

A rich, actionable coaching guide with excellent concrete examples and checklists, weakened mainly by length and heavy duplication of the bundled reference file. Trimming the inlined methodology and promotional bio would improve both conciseness and progressive disclosure.

Suggestions

Move the bulk of the Winston methodology (sections 一–八) into references/patrick-winston-how-to-speak.md and keep SKILL.md as a lean overview pointing to it, avoiding duplication.

Remove the promotional author bio and follower/download stats from the footer; they consume tokens without aiding the skill's function.

Tighten explanatory paragraphs (e.g., the '为什么' rationales) into one-line cues so the checklists and examples carry the weight.

DimensionReasoningScore

Conciseness

Mostly substantive Winston-method content Claude may not fully know, but it includes unnecessary padding such as the promotional author bio ("30万+粉丝"/"AppStore付费榜Top1") and framing that could be tightened; the body also duplicates much of the bundled reference.

3 / 5

Actionability

Highly actionable for an instruction-only skill: worked good/bad examples (承诺/结尾), a concrete 7-sins table with fixes, a 10-point 5-dimension scoring rubric, and specific operational thresholds ("等待7秒"/"字体≥40号").

5 / 5

Workflow Clarity

Four clearly laid-out usage scenarios each with checklists, plus a defined review output (综合评分 + 逐项建议 + 优先修改项); the flow is clear though it reads as a scenario menu rather than a tightly sequenced pipeline.

4 / 5

Progressive Disclosure

A reference file is correctly signaled ("参考材料:references/patrick-winston-how-to-speak.md"), but the SKILL.md body inlines the full Winston methodology, substantially duplicating content that belongs in that one-level-deep reference rather than keeping the overview lean.

3 / 5

Total

15

/

20

Passed

Description

91%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, third-person description that explicitly covers what, when, and trigger terms with comprehensive natural keywords. The only weakness is that the action verbs are somewhat generic ("帮助准备") rather than enumerating distinct capabilities.

DimensionReasoningScore

Specificity

Names the speech-coaching domain and lists several concrete application scenarios ("线下培训、技术分享、B站教程视频"), but uses a single generic verb ("帮助准备") rather than multiple distinct actions, so it stops short of comprehensive.

4 / 5

Completeness

Clearly states both what the skill does ("演讲与分享教练...基于Patrick Winston的How to Speak方法论") and when to use it ("当用户提到...时使用此技能") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides a comprehensive list of natural trigger phrases including synonyms ("演讲"/"分享"/"讲课"/"培训") and phase-specific terms ("开场"/"结尾"/"演讲结构"/"PPT演讲") that users would naturally say.

5 / 5

Distinctiveness Conflict Risk

Has a clear niche (Winston-method presentation coaching) with distinctive triggers like "开场"/"结尾"/"演讲结构", though broad terms like "分享"/"培训" create minor overlap risk with generic training skills.

4 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
alchaincyf/huashu-skills
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.