CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-plain

Cognitive atom: Plain (白). Rewrites any content so a smart 12-year-old groks it. Structure-free — form follows content. Use when user says '白话说', '说人话', '解释一下', 'plain', 'grok'.

71

Quality

89%

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

96%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 model instruction-only skill: dense, concrete, and immediately actionable, with a clearly sequenced workflow that includes an explicit red-line validation pass and acceptance criteria. The only structural note is that everything lives inline in a ~100-line file, which is appropriate here but sits just past the simple-skill threshold for progressive disclosure.

DimensionReasoningScore

Conciseness

The body is exceptionally lean: every rule carries a concrete test or before→after example (「进行分析」→「看」, "大概 70%" 比"可能"诚实), with no padding and no explanation of concepts Claude already knows — a clean match for anchor 5.

5 / 5

Actionability

It provides copy-paste-ready commands (date +%Y%m%dT%H%M%S), a concrete filename pattern {时间戳}--plain-{简短标题}__plain.org, a literal Org header template, an output directory, and multiple concrete rewrite examples; the open-ended writing step is explicitly justified ("不规定怎么写。规定不能怎么写"), matching anchor 5.

5 / 5

Workflow Clarity

A clear four-step sequence (获取内容 → 写 → 过红线 → 生成 Org 文件) with an explicit validation pass — the red-line scan produces a 修改清单 (哪句触发什么,改前→改后) — plus a 验收 acceptance checklist, matching anchor 5. This is an instruction-only, non-destructive skill, so the validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist and all content is appropriately inline for a cohesive single-file style guide, with well-organized sections and clear headers. Anchor 4 fits better than 5 because the ~100-line body exceeds the under-50-line simple-skill threshold where section organization alone earns a 5.

4 / 5

Total

19

/

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.

The description is compact and does an excellent job on completeness — a clear 'what' paired with an explicit 'Use when' clause containing concrete bilingual trigger phrases. It is slightly weaker on specificity of capabilities and has minor conflict risk from the generic trigger '解释一下'.

Suggestions

Enumerate 1–2 more concrete capabilities (e.g., 'simplifies articles, papers, or concepts into plain language and saves them as Org notes in ~/Documents/notes/') to raise specificity beyond a single action.

Add common trigger synonyms such as 'ELI5', 'in simple terms', or '讲通俗点' to broaden natural keyword coverage.

Narrow the generic trigger '解释一下' (e.g., '解释一下 when asking for a plain-language rewrite, not a factual answer') to reduce overlap with general explanation requests.

DimensionReasoningScore

Specificity

"Rewrites any content so a smart 12-year-old groks it" names the domain and one concrete, testable action, but "Structure-free — form follows content" is a property rather than an action, so coverage of specific capabilities is not comprehensive (anchor 3). Not 4: it does not list several specific concrete actions.

3 / 5

Completeness

It clearly answers both 'what' ("Rewrites any content so a smart 12-year-old groks it") and 'when' with an explicit "Use when user says…" clause listing concrete trigger phrases — a direct match for anchor 5.

5 / 5

Trigger Term Quality

Five explicit triggers including natural Chinese phrases users would say ('白话说', '说人话') and English ones ('plain', 'grok') give good keyword coverage, but common variations like 'ELI5' or 'in simple terms' are missing (anchor 4). Not 5 for that gap; not 3 because synonyms across two languages are present.

4 / 5

Distinctiveness Conflict Risk

Plain-language rewriting is a clear niche with distinctive triggers ('白话说', 'grok'), but '解释一下' is generic enough to fire on routine explanation requests, creating minor overlap risk (anchor 4). Not 5 because of that generic trigger; not 3 because the core triggers are distinctive.

4 / 5

Total

16

/

20

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.

Validation — 15 / 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.