CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-rank

给一个领域,找出背后真正撑着它的几根独立的力。十几个现象砍到不可再少的生成器——砍完能把现象一个个生回来,才算数。Use when user says '降秩', '找秩', '秩是什么', '这个领域靠什么撑着', '背后是什么', or wants to decompose any domain to its irreducible generators.

63

Quality

79%

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-rank/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 delivers a genuinely actionable methodology — sequenced process, explicit validation gates, feedback loops, and rich ASCII exemplars — but it is monolithic and repetitive: the same Deutsch criterion is explained three times, and the large diagram catalog that belongs in a reference file is fully inlined while the existing template.org reference is never pointed to.

Suggestions

Move the nine-family ASCII diagram catalog (with its exemplars and 演示要求) into a reference file such as references/diagrams.md, keeping only the shape-selection table and a one-line pointer in SKILL.md.

Deduplicate the Deutsch hard-to-vary explanation: state the reach / hard-to-vary gates once in the criteria section and have step 7 and the intro reference them briefly instead of restating them in full.

Reference references/template.org explicitly in the 输出 section (e.g. "use the header from [template.org](references/template.org)") so the existing bundle file is discoverable and the org header format is not duplicated or lost.

DimensionReasoningScore

Conciseness

Noticeably verbose with padded sections: the Deutsch hard-to-vary criterion is fully restated three times (intro "坏解释能用十种说法糊过去", step 7 "你能改的,都不是它的内核", criteria section "坏解释怎么改都还能用;好解释一动就塌"), and the Christianity/physics/economics assumption examples plus two separate "懒惰锚点" riffs re-explain concepts at unnecessary length. It sits below anchor 3 because the redundancy is repeated full restatements rather than occasional tightening.

2 / 5

Actionability

Concrete and executable: a named 7-step procedure, five explicit criteria, decision rules for when to use each diagram family, nine copy-ready ASCII exemplars, and concrete output commands ("date +%Y%m%dT%H%M%S", file path pattern). Minor gap: the org-file header format lives in references/template.org but is never linked from the output section.

4 / 5

Workflow Clarity

Clear end-to-end sequence (基本假设 → 工序 1-7 → 五条判据 → 形状/坐标系两层判断 → 写法 → 图示 → 输出) with explicit validation checkpoints (反生成, 预测+变更双测, two 反坍缩闸 self-checklists) and an explicit error-recovery feedback loop: "过不了一条,推倒重来——回到工序第 3 步".

5 / 5

Progressive Disclosure

The ~200-line nine-family ASCII catalog is inlined in SKILL.md where it clearly belongs in a separate reference file, and the one bundle file that exists (references/template.org) is never referenced from the body — a buried, unsignaled reference while separable content stays inline. It falls below anchor 3 because the reference is not merely unclearly signaled but entirely unlinked.

2 / 5

Total

13

/

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 description: it states the skill's core capability concretely, defines its acceptance criterion (regenerating all phenomena from the irreducible generators), and provides explicit, natural trigger phrases in both Chinese and English. Only minor overlap risk comes from the broader trigger terms.

DimensionReasoningScore

Specificity

Lists several concrete actions — "找出背后真正撑着它的几根独立的力", "十几个现象砍到不可再少的生成器", "砍完能把现象一个个生回来,才算数" — but the philosophical framing leaves minor gaps in coverage compared to a fully comprehensive action list.

4 / 5

Completeness

Explicitly answers both what ("给一个领域,找出背后真正撑着它的几根独立的力…砍完能把现象一个个生回来,才算数") and when ("Use when user says '降秩', '找秩', …") with concrete trigger phrases, in third-person voice.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases a user would actually say: '降秩', '找秩', '秩是什么', '这个领域靠什么撑着', '背后是什么', plus the English "decompose any domain to its irreducible generators" — covering variations in both languages.

5 / 5

Distinctiveness Conflict Risk

The coined terms '降秩'/'找秩' define a clear niche, but '背后是什么' and "decompose any domain" are broad enough to occasionally overlap with general analysis or framework skills.

4 / 5

Total

18

/

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.