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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 rich, original methodology skill with strong actionability and a well-sequenced, validated workflow. Its weaknesses are repetition that hurts token efficiency and a monolithic structure that underuses the available bundle file rather than splitting the large ASCII catalog into a referenced file.

Suggestions

Dedupe the repeated Deutsch 'hard to vary' rationale, '反坍缩闸' framing, and '别写进文章' reminder to a single statement each to recover token budget.

Move the 9-family ASCII diagram catalog into a references file (e.g. references/shapes.md) and link to it from the body, which would also let progressive_disclosure score higher.

Explicitly reference references/template.org from the output section (e.g. 'use references/template.org as the file header') so the existing bundle file is signaled rather than orphaned.

Dimension	Reasoning	Score
Conciseness	The ~480-line body is mostly earned (original methodology, 9 concrete ASCII examples, exact output commands) and avoids explaining concepts Claude already knows, but the Deutsch 'hard to vary' rationale, the '反坍缩闸' framing, and the '别写进文章' instruction are each repeated across several sections and could be tightened.	2 / 3
Actionability	Provides concrete executable guidance — a numbered 7-step process, 5 named criteria with explicit tests ('去掉一个,另一个还会不会自己冒出来?'), 9 shape families each with a worked ASCII example and demo requirements, and copy-paste-ready output commands ('date +%Y%m%dT%H%M%S') with a file-path template.	3 / 3
Workflow Clarity	The 7-step process is clearly sequenced with explicit validation checkpoints (step 6 反生成, step 7 预测+变更双测) and a real feedback loop — '过不了一条,推倒重来——回到工序第 3 步' — plus a clear 3-step output workflow, matching the level-3 anchor.	3 / 3
Progressive Disclosure	The body is a monolithic single file with the extensive 9-family ASCII catalog inline (content that could be split out), and the one bundle file present (references/template.org) is never explicitly linked or signaled from the body, fitting the 'some structure but references not clearly signaled' anchor.	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 description: it states a concrete capability, supplies explicit natural-language triggers in both Chinese and English, and occupies a distinct niche. The only soft spot is that the capability verbs are metaphorical ('砍', '生回来') rather than literal operations, but they still name distinct actions.

Dimension	Reasoning	Score
Specificity	Names several distinct 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' — matching the 'lists multiple specific concrete actions' anchor; phrasing is metaphorical but each is a distinct operation.	3 / 3
Completeness	Explicitly answers both what (decompose a domain to irreducible generators that regenerate the phenomena) and when via a 'Use when user says...' clause with concrete triggers, matching the level-3 anchor exactly.	3 / 3
Trigger Term Quality	Covers natural terms a user would actually say in both languages — '降秩', '找秩', '秩是什么', '这个领域靠什么撑着', '背后是什么' — plus 'decompose any domain to its irreducible generators', giving good coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The 'rank reduction / irreducible generators' niche is unusual and specific, with distinctive Chinese triggers ('降秩', '找秩') unlikely to fire for unrelated skills, so conflict risk is low.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: lijigang/ljg-skills
Path: skills/ljg-rank/SKILL.md
Commit: 0e78094

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.