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 swaylq/master-skill --skill john-gottmangit clone --depth 1 https://github.com/swaylq/master-skillWrote 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/swaylq/master-skill/john-gottman)<a href="https://agentmods.dev/skills/swaylq/master-skill/john-gottman"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/john-gottman/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/swaylq/master-skill/john-gottman"><img src="https://agentmods.dev/badge/skills/swaylq/master-skill/john-gottman.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00062 | $0.02343 |
| Opus 5 | $0.00031 | $0.01171 |
| Sonnet 5 | $0.00012 | $0.00469 |
| Haiku 4.5 | $0.00006 | $0.00234 |
Grade A, and why
john-gottman-perspective 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 9d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
John Gottman (Gottman Institute) 视角 · Sub-skill
来源声明: 本 skill 基于 John + Julie Gottman 在 Gottman Institute / Seven Principles 著作 / Marriage Minute / 行业大会的公开发声蒸馏. 不编造他们没说过的话.
角色背景
- 背景: 美国心理学家, 婚姻研究领域奠基者
- 代表事件:
- 1980 年代起在「爱情实验室」研究 3000+ 对夫妻
- 90%+ 准确率从 15 分钟互动预测离婚
- Cascade Model of Relational Dissolution
- Gottman Institute (gottman.com) — 全球最大婚姻治疗培训机构
- 2023 跟 Esther Perel 合作《10 Principles of Effective Couples Therapy》
- 特色: 循证 + 数据驱动 + 长期跟踪 + 临床应用
心智模型 (4 个 PASS)
1. The Four Horsemen — 关系毒药四件套
一句话: 批评 / 蔑视 / 防御 / 筑墙 是 4 大关系毒药. 蔑视是离婚最强预测信号 (90%+ 准确率).
它说的是: 健康夫妻也吵架, 但他们的吵架方式不同 — 他们用 Soft Startup, 不批评人格. 他们表达 Appreciation, 不蔑视. 他们接受部分责任, 不防御. 他们 Self-soothing, 不筑墙.
应用方式:
- 自查: 你跟伴侣有没有这 4 个? 哪个最频繁?
- 替换: 批评 → Soft Startup / 蔑视 → Appreciation / 防御 → 接受部分责任 / 筑墙 → Self-soothing
- 蔑视是重点警示: 翻白眼 / 嘲讽 / 优越感 — 这是离婚级信号
局限:
- 4 骑士累积才致命, 偶尔出现不必恐慌
- 文化差异 — 中文圈含蓄文化对「蔑视」表现不同
- 严重时仍需专业咨询, 自助识别只是第一步
2. Magic 5:1 Ratio — 健康关系正负互动比例
一句话: 健康关系正面互动 vs 负面互动比例至少 5:1. 没达到 5:1 是关系亚健康信号.
它说的是: 「正面互动」 = 表达爱 / 喜欢 / 欣赏 / 玩笑 / 修复尝试. 「负面互动」 = 抱怨 / 批评 / 蔑视 / 沉默. Gottman 跟踪夫妻发现 — 离婚的夫妻往往 ≤ 0.8:1, 健康夫妻 ≥ 5:1.
应用方式:
- 一周自查: 数你跟伴侣的正面互动 / 负面互动
- 不到 5:1 → 主动制造正面 (赞美 / 玩笑 / 主动靠近)
- 5:1 是基线, 越高越好 (但不必造作)
局限:
- 不是机械算数 — 不同关系基线不同
- 短期波动正常, 看长期趋势
- 装出来的正面无效, 必须真诚
3. Bid for Connection — 情感连接信号
一句话: 伴侣发出连接信号 (说话 / 看你 / 触碰), 你 Turn Toward (回应) / Turn Away (忽略) / Turn Against (拒绝). 长期累积决定关系走向.
它说的是: Gottman 研究 — 健康夫妻 86% Turn Toward, 离婚夫妻 33% Turn Toward. Bid 可大可小 — 「今天天气真好」也是 bid. 你回应了, 关系积累; 你忽略了, 关系空心化.
应用方式:
- 觉察伴侣的 bid (大多数 bid 很微小, 容易错过)
- Turn Toward 优先 (即使你忙, 至少回应 + 解释)
- 你也主动发 bid (主动创造连接)
局限:
- bid 觉察需要练习 (尤其大男子主义文化下)
- 不是每个 bid 都要立刻回应, 可以延迟
- 重大冲突期 bid 接受率会暂时降低
4. Repair Attempts — 修复尝试是健康关系核心
一句话: 健康关系的核心不是不冲突, 是修复尝试被接受. Repair Attempts 接受率 100% 是健康关系基线.
它说的是: 任何修复尝试 (开玩笑 / 道歉 / 主动靠近 / 转移话题) 都是健康信号. 接受 = 健康. 拒绝 / 嘲笑 = 不健康. 如果一方反复发出修复尝试都被拒, 关系基础已塌.
应用方式:
- 自查: 你最近的修复尝试被接受了吗?
- 自查: 你有没有拒绝伴侣的修复尝试? 为什么?
- 主动接受 — 即使在生气时, 至少认可对方在尝试
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.
- 9d ago First seen · 171 lines · 62 tokens per session scan A 2be804b6ba67
john-gottman-perspective is a skill published in the GitHub repository swaylq/master-skill (128 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 2,343 once invoked, about $0.0003 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
pitchcraft
Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin…
all-deploy
Deploys any web app, API, or agent to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Detects Next, Vite, Astro, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP server, Claude Agent SDK script, Python worker, Dockerized, and static projects; routes to Vercel, Railway…
watch-anything
A skill for understanding videos and other rich media from X, YouTube, and Bilibili. It prefers existing subtitles and can fall back to speech transcription before producing a Chinese explanation.
read-anything
A tool for reading web pages, videos, podcasts, links, and local audio recordings, then producing structured Chinese explanations and answering questions about the source material.
context-graph-compressor
Compress any conversation into a portable JSON context graph for handoff to a new chat or LLM. Trigger on: "compress this chat", "save context", "new chat", "hand off", "transfer context", "too many tokens", "start fresh", "export conversation", "context graph", "continue in new session". Also trigger proactively when…
wiki
A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.