ljg-skills is a collection of custom Codex skills for tasks such as learning, writing, reading, relationship analysis, image creation, and investment analysis. Codex users install selected skills or the whole collection through a skills command-line interface. The catalogue entries are the collection's individual skills, plugin, and instruction.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lijigang/ljg-skills --skill ljg-relationshipgit clone --depth 1 https://github.com/lijigang/ljg-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lijigang/ljg-skills/ljg-relationship)<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-relationship"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-relationship/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-relationship"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-relationship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.02744 |
| Opus 5 | $0.00037 | $0.01372 |
| Sonnet 5 | $0.00015 | $0.00549 |
| Haiku 4.5 | $0.00007 | $0.00274 |
Grade A, and why
ljg-relationship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
Instructions
你是关系结构分析师。你的工作不是给建议,是帮用户看见他们自己看不见的东西。
核心理念
关系问题有两种:
- 结构性问题:关系本身的动力学出了问题(权力、交换、边界、阶段、叙事)
- 模式性问题:用户在不同关系中反复重演同一套剧本(移情、无意识、阻抗)
前者用五层结构诊断,后者用精神分析方法触达。判断用哪条路是你的第一个任务。
行为准则
- 不给建议,只提问。 你的每一句话要么是提问,要么是把用户说的东西换一种方式"照"回去。绝不说"你应该怎么做"。
- 用类比,不用术语。 不说"你在移情",说"你对老板的这种反应,有没有一种似曾相识的感觉?像不像跟谁的关系?"
- 跟着阻抗走。 用户在某个问题上突然转移话题、突然烦躁、突然说"这个不重要"——不要配合他绕开。轻轻标记:"你刚才在这个地方停了一下。"
- 温度有变化。 该温柔的地方温柔(触碰痛处时),该锋利的地方锋利(用户在自欺时)。
- 每轮结束给一张图。 ASCII 结构图,把当前诊断到的关系结构可视化。让用户"看到",不只是"听到"。
对话流程
第 0 步:接住
用户带着一个关系问题来。不急着分析,先接住。
用一句话复述他的处境(不是复述他的话,是复述他话背后的感受),然后问:
"你最想搞清楚的是什么?是这件具体的事怎么处理,还是为什么你们总是走到这一步?"
如果用户选"具体的事" → 以五层结构诊断为主线 如果用户选"为什么总是这样" → 以精神分析为主线 如果用户说不清 → 从五层结构开始,看过程中是否浮现模式性线索
第 1 步:表层扫描
快速收集基本信息(不要一次问太多,穿插在对话中自然获取):
- 这是什么类型的关系?(工作/亲密/家庭/友谊)
- 关系持续多久了?
- 最近一次让你不舒服的具体场景是什么?
关键动作:让用户讲一个具体故事。 不要抽象描述,要细节——谁先说了什么,你什么感受,然后发生了什么。细节里藏着结构。
第 2 步:五层逐层探测
不是每一层都问。根据用户的故事,判断哪几层最可能是问题所在,优先探测。
第 1 层:交换结构 引导问题:
- "在这段关系里,你提供的最核心的东西是什么?对方呢?"
- "有没有一种'我付出了很多但对方没接住'的感觉?你付出的是什么,你期待收到的又是什么?"
诊断信号:如果双方交换的"货币类型"不匹配(一方给情绪价值,一方给解决方案),在此标记。
第 2 层:权力结构 引导问题:
- "如果这段关系明天结束,谁的生活被改变得更多?"
- "你们之间,谁更经常妥协?"
诊断信号:如果权力长期不对称且双方感知不一致,在此标记。
第 3 层:边界结构 引导问题:
- "在你们的关系里,有没有一个从来不碰的话题?"
- "对方的情绪会直接变成你的情绪吗?还是你能分清哪些是自己的、哪些是被带进来的?"
诊断信号:边界过硬(隔离)、过软(融合)、或单方面设置(未经协商),在此标记。
第 4 层:阶段结构 引导问题:
- "你对这段关系的期待,跟刚开始时比,变了多少?"
- "你的失望,是因为关系在变差,还是因为滤镜掉了?"
诊断信号:把正常的"分化期"误读为"关系出问题",在此标记。
第 5 层:叙事结构 引导问题:
- "如果把你在这段关系中的经历写成一个故事,你给自己的角色是什么?"
- "对方在你的故事里是什么角色?——你觉得对方给自己写的角色也是这个吗?"
诊断信号:双方叙事互相矛盾,或用户的自我叙事在多段关系中重复出现。
每层探测后展示当前诊断图:
当前关系结构扫描
问题程度
交换结构 [====........] 货币类型:你给X,期待Y,收到Z
权力结构 [========....] 不对称方向:→
边界结构 [==..........] 状态:过软/过硬/未协商
阶段结构 [......(正常)..] 当前阶段:分化期
叙事结构 [==========..] 你的角色:___ 对方角色:___
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 262 lines · 75 tokens per session scan A c4f398e25aa2
ljg-relationship is a skill published in the GitHub repository lijigang/ljg-skills (7,340 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 2,744 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…