ljg-map

以《学习观》的知识观洞察用户文稿，提炼概念、判别依据与有条件的联结，按文稿自身的关系绘制通俗的形式化知识地图；每个节点都有白话定义、短公式和具体语义，图形不预设层级。USE WHEN 用户调用 /ljg-map，或要求把文章、笔记、讲稿画成形式化地图、思考地形图、概念判别与关系图。NOT FOR 普通摘要、逐段改写、地理地图或单独的公式证明。

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ljg-map/SKILL.md

Quality

Content

51%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 well-organized, concise, and rich in skill-specific guardrails, but its core execution content is delegated to two referenced files (Workflows/Map.md and Examples.md) that are not present in the bundle, leaving the actual map-generation workflow and expression examples unreachable. The result is a routing shell without the workflow it points to.

Suggestions

Include the referenced bundle files (Workflows/Map.md and Examples.md) or inline the essential map-generation steps into SKILL.md so the routing table has real targets.

Add one concrete worked example — a short input excerpt with its resulting Mermaid map and a node explanation (定义、短公式、语义、具体对应) — so the output format is executable rather than described.

Define the node-explanation and edge-label format concretely (e.g., a template line per node) in the body, since the 成品约定 section currently states requirements without a usable pattern.

Dimension	Reasoning	Score
Conciseness	The body is compact (~30 lines) with no padding and no explanations of concepts Claude already knows — the Gotchas are skill-specific constraints like "形式化不以符号数量计" and "箭头有语义", and each earns its tokens. A few dense, abstract sentences (e.g., the opening paragraph and "成品约定") could be tightened, which keeps it just below the lean anchor.	4 / 5
Actionability	Guidance is directional rather than executable for an instruction-only skill: the Gotchas give some concrete directives ("优先「中文名称 + 短公式」", "用短边标签") and the Examples describe expected behaviors per request type, but there is no worked example of an output map, node explanation, or Mermaid pattern, and the concrete execution detail is delegated to [Workflows/Map.md](Workflows/Map.md), which does not exist in the bundle. This matches the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	The routing table cleanly separates request types, but the actual multi-step sequence for generating a map lives entirely in Workflows/Map.md — a file absent from the bundle — so the executable steps are effectively missing, with only high-level output conventions ("主图显出…每个图中节点均能在解释中找到相同编号") inlined. Rough direction exists but many gaps and no validation checkpoints, matching the score-2 anchor rather than 3, where at least a complete in-body step list would exist.	2 / 5
Progressive Disclosure	Section structure is good and references are clearly signaled at one level deep in a routing table, but both referenced files (Workflows/Map.md, Examples.md) are missing from the bundle, so navigation to the detailed material fails. Per the guideline to score against the actual bundle structure, this is structure that could be well organized but is broken in practice — matching the mid anchor rather than 4.	3 / 5
	Total	12 / 20 Passed

Description

83%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 explicitly states what the skill does, when to use it with concrete trigger phrases, and what not to use it for. Trigger terms and specificity are good, with only minor gaps in synonym coverage and slight abstractness in the action statements.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "提炼概念、判别依据与有条件的联结", "绘制通俗的形式化知识地图", and specifies node output format ("白话定义、短公式和具体语义") with the constraint "图形不预设层级". Coverage is strong but the actions are described at a fairly abstract level of granularity, leaving minor gaps versus the comprehensive multi-action anchor.	4 / 5
Completeness	Both questions are explicitly answered: a clear multi-clause 'what' (analyze document, extract concepts/criteria/connections, draw formalized map with defined node format) and an explicit "USE WHEN" clause with concrete trigger phrases, further sharpened by a "NOT FOR" exclusion list (普通摘要、逐段改写、地理地图、单独的公式证明).	5 / 5
Trigger Term Quality	Triggers include the explicit slash invocation "/ljg-map", concrete input types ("文章、笔记、讲稿"), and several natural synonym phrases ("形式化地图、思考地形图、概念判别与关系图"). Good keyword coverage, though common user phrasings like "概念图" or "思维导图"-adjacent requests are not addressed, so it falls just short of the comprehensive synonym anchor.	4 / 5
Distinctiveness Conflict Risk	The skill occupies a clear niche (formalized knowledge maps grounded in a specific 知识观 framework) with distinct triggers and an explicit NOT FOR boundary. Minor overlap risk remains with generic diagram/mind-mapping or summarization requests, which keeps it just below the minimal-conflict anchor.	4 / 5
	Total	17 / 20 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
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: lijigang/ljg-skills
Path: skills/ljg-map/SKILL.md
Commit: 7449831

Reviewed: 2 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.