Skip to content
SkillCheatSheet Sign in

ljg-constraint

An AI agent skill from lijigang/ljg-skills, scored 69 out of 100 by code.

69/ 100C

Code score by group

  • Spec20/20
  • Description14/20
  • Procedure10/15
  • Done criteria0/15
  • Resources10/10
  • Scripts5/8
  • Safety7/7
  • Upkeep3/5

It loses the most points in Done criteria (15), the group that checks whether there is a checklist and a step that verifies the work.

What the author says it does

给一个领域、专业、角色、产品或争论找出真正框住它的几条约束，判明它们属于世界/规则/解释（硬/软/自设），看这组约束如何定义身份、补全问题、框出解空间并解释实际行为；尤其用于区分目标相同但约束不同导致的方案分歧，识别被误当硬事实的旧解释。USE WHEN 用户说 '约束', '找约束', '这个领域的约束是什么', '本质约束', '什么框住了它', '硬约束还是自设约束', '边界在哪', '这行为什么这么做', 'constraint', '/ljg-constraint', or gives any domain/profession/role/product/debate and wants its defining constraints and solution space mapped. NOT FOR 往下挖生成器（用 ljg-rank，找的是生成力不是边界）、纵向深钻一个观点到底（用 ljg-think）、拆一本书（用 ljg-book）、一个概念解剖（用 ljg-learn）。

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
lijigang/ljg-skills
Folder
skills/ljg-constraint
License
MIT
GitHub stars
7,736
SKILL.md lines
245
Other files
1

Add ljg-constraint to your agent

npx skills add lijigang/ljg-skills --skill ljg-constraint

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

More skills from lijigang/ljg-skills

  1. ljg-blind

    盲区扫描——读昨天你与 AI 的全部对话，照出暴露的思维盲区（不是不懂的知识，是让某类真相一直看不见的思维习惯），再从微信读书挑一本书的一章精准补上，落成一篇完整分析笔记。Use when user says '扫盲区', '盲区', '照盲区', '看看我的思维盲区', '我昨天想漏了什么', 'blind spot', 'ljg-blind', '/l…

    75B
  2. ljg-card

    Content caster (铸). Transforms text into PNG through precise HTML typography and, when the mold needs it, generated raster imagery. Four molds: -l (default) long reading card, -f…

    75B
  3. ljg-book

    Explain a whole book to readers without specialist knowledge: what it follows, how its main threads connect, where it ends, and how its evidence or events change understanding. Ke…

    69C
  4. ljg-qa

    信息提问机。给一篇文章/论文/书，把核心观点抽成 Q-A 对——Question 切要害，不教科书；Answer 简洁清晰，有形式化收口，逻辑链完整。读者顺 Q 链走过，每个 A 砸下一枚钉子，复现作者整套推理。Use when user says '问答', 'Q&A', 'QA', '提问', '抽取问题', '/ljg-qa', or shares…

    69C
  5. ljg-learn

    Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics,…

    68C
  6. ljg-explain

    把概念、公式、机制与原理讲到能辨认、能推导、能迁移：用通俗中文接通具体情境、判别依据、运作过程和成立条件。USE WHEN 用户调用 ljg-explain、说「通俗易懂地讲解」「讲透这个概念或公式」「费曼讲解」「ELI5」，或希望从零理解一个知识点并能用于新情境。NOT FOR 单纯润色或翻译、整篇伴读、整本书或论文解读、只要求形式证明或操作步骤。

    66C
  7. ljg-roundtable

    一个议题，一场圆桌：主持人请来 3-5 位真实人物，定义开场，逐轮交锋， 每轮收一张 ASCII 结构图，用户用指令控节奏（可/止/深入此节/引入新人物）， 散场后全文存入 Markdown 笔记。Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic…

    64C
  8. ljg-teach

    用体验而不是定义来教授概念、原理或检验观点：先给与学习者认知水平相称的局面，让其选择，再用公平的意外显化认知缺口，结构化后才命名，并以迁移局面循环复测。USE WHEN 用户调用 '/ljg-teach'、说 '用情境教我'、'别先讲答案'、'通过案例让我学会'，或希望通过选择与反馈理解一个概念或观点。NOT FOR 直接定义查询（用 ljg-is/ljg…

    64C

All skills in lijigang/ljg-skills

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.