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'.

76

Quality

95%

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

100%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.

An exemplary craft skill body: lean, concrete, and tightly structured with explicit validation gates and acceptance criteria. It adds only what Claude would not already know and every directive is actionable.

DimensionReasoningScore

Conciseness

Terse, punchy prose that assumes Claude's competence ("让人 grok。不规定怎么写。规定不能怎么写。下限锁死,上限放开。") with no padded explanation of what rewriting is; every section earns its tokens.

3 / 3

Actionability

Instruction-only skill with fully concrete guidance: exact allowed ASCII charset, exact commands (`date +%Y%m%dT%H%M%S`), exact filename pattern, a complete org file-header template, and concrete before→after transforms ("「进行分析」→「看」", "「有人觉得情况不太好」→「张三说项目要黄了」").

3 / 3

Workflow Clarity

Four-step 执行 sequence (获取内容 → 写 → 过红线 → 生成 Org 文件) with an explicit red-line gate and 修改清单 before file generation, plus a 验收 acceptance checklist; not capped at 2 since the operation is non-destructive.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the single ~105-line body is cleanly sectioned (格式约束 / 红线 / 工具箱 / 执行 / 验收) with no monolithic dump to externalize and no nested references.

3 / 3

Total

12

/

12

Passed

Description

90%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 description with explicit what-and-when triggers and good natural-language coverage in both Chinese and English, written in correct third-person voice. The only gap is breadth of named actions.

Suggestions

Specificity: surface more than one concrete action (e.g., mention that it accepts URLs, files, or concepts as input and emits an Org/Denote note), so the capability list reads as multiple distinct actions rather than a single 'rewrites' verb.

Specificity: the 'form follows content / Structure-free' clause is a design principle, not a capability — consider replacing or augmenting it with a concrete action to lift the specificity anchor from 2 to 3.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("Rewrites any content so a smart 12-year-old groks it") but does not list multiple distinct actions as the anchor-3 example does; above 1 because a concrete action and outcome are stated.

2 / 3

Completeness

Explicitly answers what ("Rewrites any content so a smart 12-year-old groks it") and when (explicit "Use when..." clause with concrete triggers).

3 / 3

Trigger Term Quality

"Use when user says '白话说', '说人话', '解释一下', 'plain', 'grok'" provides strong bilingual coverage of phrases a user would naturally say.

3 / 3

Distinctiveness Conflict Risk

"Cognitive atom: Plain (白)" with distinctive Chinese triggers carves a clear niche unlikely to collide with other skills.

3 / 3

Total

11

/

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.