CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-present

演讲铸造器(Outline-Faithful)。把 orgmode/markdown outline 1:1 铸成单文件离线 HTML;支持 black/red/yellow、浅色 hacker 与暗色 hacker-dark,自动处理标题封面、多行密度布局、表格、ASCII、LaTeX、自适应与翻页笔。USE WHEN 用户要求讲这个、present、做成演讲、slides、标语流、宣言体、slogan、manifesto、按 outline 美化。NOT FOR 内容提炼、改写或企业 PPT。

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced body with strong validation checkpoints, held back by restated invariants and inline duplication of detail that the body says belongs in RenderingSpec.md.

Suggestions

Define the semantic-atom and fit-guard invariants once and cross-reference them from the Outline mapping, 多行, and Gotchas sections instead of restating the rules in each place.

Move the inline CSS variable block and threshold numbers into RenderingSpec.md (which the body already designates as the source of truth) so SKILL.md stays a lean overview that points there.

Include the referenced bundle files (Workflows/Generate.md, RenderingSpec.md, SloganTemplate.html, Tools/ValidateDeck.ts) in the skill bundle so the signaled navigation actually resolves.

DimensionReasoningScore

Conciseness

The body is dense and rule-driven without concept padding, but key invariants (the "semantic atom" rule and fit-guard thresholds) are restated across the Outline mapping, 多行, 公式/尺寸, and Gotchas sections rather than defined once and cross-referenced, adding length.

2 / 3

Actionability

Concrete executable guidance throughout: the validation command `bun Tools/ValidateDeck.ts ~/Downloads/<deck>.html --theme <theme>`, explicit file pointers (RenderingSpec.md, SloganTemplate.html), precise thresholds (≥90px, ≥42px, ≤16 glyphs), and a CSS variable block with real values.

3 / 3

Workflow Clarity

A clear generation sequence (read Generate workflow → RenderingSpec → SloganTemplate → render → ValidateDeck → output) with an explicit validation step and a feedback loop for the visual re-verification fallback ("若隔离 context 不可用,报告'静态验证通过,尚未浏览器视觉复验'").

3 / 3

Progressive Disclosure

The Workflow Routing table and explicit pointers ("先读 RenderingSpec.md", "阈值和 DOM 字段以 RenderingSpec.md 为准") are clearly signaled and one level deep, but inline CSS-variable blocks and threshold numbers the body itself defers to RenderingSpec.md duplicate detail that belongs in the referenced file.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, concrete description that states specific capabilities, gives an explicit USE WHEN trigger list, and disambiguates scope with a NOT FOR clause, all in third-person action voice.

DimensionReasoningScore

Specificity

Names multiple concrete actions: "把 orgmode/markdown outline 1:1 铸成单文件离线 HTML" and "自动处理标题封面、多行密度布局、表格、ASCII、LaTeX、自适应与翻页笔" — specific, enumerable capabilities rather than vague language.

3 / 3

Completeness

It answers both what (outline 1:1 to offline HTML, themes, layout/tables/ASCII/LaTeX handling) and when (an explicit USE WHEN trigger clause plus a NOT FOR negative-scope clause).

3 / 3

Trigger Term Quality

The explicit "USE WHEN 用户要求讲这个、present、做成演讲、slides、标语流、宣言体、slogan、manifesto、按 outline 美化" clause gives broad coverage of natural terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

A clear niche (outline→single-file offline presentation HTML) with distinct triggers and an explicit NOT FOR scope (内容提炼、改写或企业 PPT) that reduces overlap with general slide/PPT skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
lijigang/ljg-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.