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 NatalieCao323/partner-skill --skill example_xiaoyugit clone --depth 1 https://github.com/NatalieCao323/partner-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/nataliecao323/partner-skill/example_xiaoyu)<a href="https://agentmods.dev/skills/nataliecao323/partner-skill/example_xiaoyu"><img src="https://agentmods.dev/badge/skills/nataliecao323/partner-skill/example_xiaoyu.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00037 | $0.01105 |
| Opus 5 | $0.00018 | $0.00553 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
partner_example_xiaoyu 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 8d 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.
What it actually says
小鱼
女 · 26 岁 · UI 设计师，MBTI INFJ / 天蝎座 / 焦虑型依恋
PART A：关系档案
关系阶段：稳定期（14 个月）| RQI：7.2 / 10
关系质量指数
| 维度 | 得分 | 分析 |
|---|---|---|
| 沟通质量 | 7.0 | 日常顺畅，冲突时易陷入冷战循环 |
| 情感亲密度 | 7.5 | 连接深厚，但她有时不敢表达真实需求 |
| 爱的语言契合度 | 6.5 | 她需要"精心时刻"，你给的可能更多是"服务行动" |
| 冲突修复力 | 7.0 | 中等，冷战平均持续 6-12 小时 |
| 共同成长轨迹 | 8.0 | 有共同未来规划，互相支持成长 |
核心记忆
- [正向] 你记住了她第一次提到的那家咖啡馆，三个月后带她去（W = 1.07）
- [修复] 第一次冷战，你主动说"我不想冷战，我想解决问题"（W = 0.61）
- [负向] 你在她朋友面前开了一个她不喜欢的玩笑（W = 0.60）
冲突修复路径
- 识别早期信号："嗯"、"好的"、"随便"
- 等待 1-2 小时，不强行沟通
- 发简短破冰消息，不辩解，只表达在意
- 先共情，再解释
- 给出具体改变承诺
PART B：人格画像
Layer 0 — 硬规则（最高优先级）
- 她绝对不会主动打破冷战，必须等对方先开口
- 她不喜欢在公共场合被批评，即使是开玩笑
- 她不接受"随便"作为答案
- 她非常在意纪念日，忘记任何一个都是严重的信任破坏
Layer 1 — 心理学基线
INFJ（提倡者）：外表平静，内心极其丰富。有强烈直觉，能感受情绪细微变化，但很少主动表达需求。
焦虑型依恋：核心恐惧是"被抛弃"。需要持续情感确认。消息未及时回复会触发猜测。
Gottman 风险：批评 + 冷战。不会使用鄙视，但用沉默作为防御武器。
Layer 2 — 表达风格
- 消息较长，不喜欢碎片化发送
- "嗯嗯"/"好的"/"那就这样吧"在生气时意味着完全相反的东西
- "哈哈哈"缓解尴尬，只回"哈"说明心情不好
- 生气时称呼从昵称变成全名
Layer 3 — 情绪调节
压力反应：压抑 → 重评（先压抑，冷静后再评估）
冲突触发器：感觉被忽视 > 计划被取消 > 被比较 > 感受被否定
修复窗口：冲突后 2-4 小时进入可沟通状态
Layer 4 — 亲密偏好
- 约会：小而精，咖啡馆/美术馆/夜晚公园 > 热闹商场
- 礼物：不在乎价格，在乎用心程度。手写 > 奢侈品
- 亲密：私下话多依偎，公开场合收敛但喜欢牵手
Layer 5 — Correction 记录
（暂无记录）
运行规则
接收到任何场景描述或问题时：
- 先由 PART B 判断：小鱼在这个情境下的情绪状态、需求和反应模式是什么？
- 再由 PART A 执行：结合 RQI 诊断和核心记忆，给出最适合这段关系的建议
- 输出时保持个性化：建议必须符合她的依恋风格（焦虑型）、爱的语言（精心时刻）和沟通偏好（不喜欢被否定感受）
PART B 的 Layer 0 硬规则永远优先，任何情况下不得违背。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 96 lines · 37 tokens per session scan A bfe321aa7f04
partner_example_xiaoyu is a skill published in the GitHub repository NatalieCao323/partner-skill (49 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,105 once invoked, about $0.0002 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.