ljg-map

一个行业 → 一张生态地形图卡（PNG）。以《千脑智能》参考系理论为地基：把行业摊成一张可俯瞰的「生态地形」——价值像河一样流过地貌，再在地形上标出两处——「瓶颈」（流量/产能在此收窄的隘口/水坝）和「价值捕获点」（利润在此沉淀的宝藏堆）。地形让权力结构一眼可见：卡流量的地方常常不是钱沉淀的地方。配三个关键指标的 base rate（刻度）+ 三个「大问题」（前沿）。deep research 真联网，图用 AI 生图（默认 -a 吉田诚治式绘本画风，与 ljg-library 同源；可选 -c pixel+cyber），继刚作小测量员立在地形上俯瞰。Use when user says '行业地图', '产业地图', '生态地形图', '画一下这个行业', 'industry map', 'map this industry', '行业版图', '产业链地图', '/ljg-map', or gives an industry/领域 name wanting its terrain mapped. 风格：默认 -a 绘本（同 ljg-library），加 -c 走 cyber。NOT FOR 一个领域降秩找生成器（用 ljg-rank）、拆一本书（用 ljg-book）、单个项目投资分析（用 ljg-invest）、一个概念深钻（用 ljg-think）。

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%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 well-structured, highly actionable skill body with a sequenced workflow, validation feedback loops, and clean one-level-deep references into real bundle files. The only weakness is some conceptual/theoretical prose that pads the token budget.

Suggestions

Trim the '地基：参考系理论' section and inline thesis sentences to a few lines — Claude does not need the theory of frames explained to execute the steps.

Consolidate the duplicated bottleneck/value-capture signal lists (in body, '必过的检查', and research.md) into one authoritative place to cut tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and task-specific, but the foundational 'reference frame theory' section and several full-sentence theses add conceptual framing Claude does not need, padding the token budget.	2 / 3
Actionability	Provides concrete executable commands (gen_illustration.py invocation with flags, capture.js render line with dimensions), a full template variable table, and a worked example frame — copy-paste ready.	3 / 3
Workflow Clarity	A clearly numbered 10-step flow with explicit validation checkpoints (step 10 'Read 成品 PNG 亲验 → 不行调 frame 重生') and a dedicated '必过的检查' checklist with feedback loops for batch/destructive operations.	3 / 3
Progressive Disclosure	Overview points cleanly to one-level-deep, real bundle files (references/research.md, visual.md, example.md; assets/gen_illustration.py, map_template.html), each clearly signaled with what it covers and when to read it.	3 / 3
	Total	11 / 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, specific description that pairs concrete outputs (terrain map with two marked spots, base rates, big questions) with explicit trigger terms and a NOT-FOR boundary. It is long but every part earns its place and stays in third person.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: produces an ecosystem terrain map (PNG), marks bottlenecks and value-capture points, adds three base rates, three big questions, and runs image generation/rendering in defined styles — concrete rather than abstract.	3 / 3
Completeness	Explicitly answers what (one industry → one terrain map card with bottlenecks/value-capture/base rates/big questions) and when via a clearly worded 'Use when...' clause with concrete triggers.	3 / 3
Trigger Term Quality	Covers natural phrasings users would say ('行业地图', '产业地图', '生态地形图', '画一下这个行业', 'industry map', 'map this industry', '行业版图', '产业链地图', '/ljg-map') plus the generic 'industry name wanting terrain mapped'.	3 / 3
Distinctiveness Conflict Risk	A narrow niche with distinct triggers and an explicit 'NOT FOR...' clause steering away from ljg-rank, ljg-book, ljg-invest, ljg-think, so it is unlikely to fire for the wrong skill.	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-map/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.