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'.

60

Quality

71%

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 ./skills/ljg-plain/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 dense, opinionated, and actionable with a clear sequenced workflow and a validation-style red-line checkpoint. It is token-efficient and well-structured for a self-contained skill, with only minor gaps in explicit output verification and reference splitting.

Suggestions

Add an explicit post-write verification step (e.g., confirm the .org file exists at the reported path and re-read it against the red-lines) to push workflow clarity to 5.

Consider extracting the format/Org/Denote conventions into a references file so the SKILL.md body stays a pure overview.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, delivering dense, opinionated guidance with minimal padding; a few explanatory glosses (e.g., expanding the red-line rationales) could be trimmed, but it largely avoids over-explaining concepts Claude already knows.

4 / 5

Actionability

It gives concrete, executable guidance: specific date commands, file-name templates, an Org header block, and concrete rewrite transforms with before→after examples ('进行分析'→'看'); minor gaps are the intentionally form-free writing step, which is a deliberate design choice.

4 / 5

Workflow Clarity

The 执行 section sequences four numbered steps (acquire → write → pass red-lines → generate Org file) with a red-line checklist acting as a validation gate and a post-sweep review list, giving clear checkpoints; the file-generation step lacks an explicit verify-output-exists loop, keeping it just below a 5.

4 / 5

Progressive Disclosure

Content is well-organized into clearly headed sections (格式约束, 红线, 工具箱, 执行, 验收) with no bundle files and no nested references; as a self-contained skill under ~110 lines this is appropriate structure, just shy of the 'ideal overview pointing to one-level-deep references' anchor since there are no references to split out.

4 / 5

Total

16

/

20

Passed

Description

67%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 clear, concise, and third-person with an explicit 'Use when' clause and concrete trigger phrases. It is strong on trigger-term quality and completeness, slightly less specific on enumerated capabilities.

Suggestions

Add 1-2 more concrete actions (e.g., 'simplifies jargon, breaks long sentences, replaces abstract nouns with visible ones') to lift specificity.

Include a common English synonym or two (e.g., 'eli5', 'simplify') to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

It names the domain (rewriting content for a young audience) and one concrete action ('Rewrites any content so a smart 12-year-old groks it'), but no further enumerated actions; the rest is style philosophy rather than discrete capabilities.

3 / 5

Completeness

It states both 'what' (rewrites content to be grokkable by a 12-year-old) and 'when' ('Use when user says ...'), with the 'when' explicit via concrete trigger phrases; just shy of fully comprehensive on the 'what' side.

4 / 5

Trigger Term Quality

It lists several natural trigger phrases users would actually say ('白话说', '说人话', '解释一下', 'plain', 'grok'), giving good coverage, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The trigger set and 'cognitive atom' framing give it a fairly distinct niche with minimal overlap risk against other skills, though the broad 'rewrite any content' scope leaves minor overlap with general explanation skills.

4 / 5

Total

15

/

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.

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.