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 L-LesterYu/OpenClaw-hot-skills-zh --skill self-improving-zhgit clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zhWrote 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/l-lesteryu/openclaw-hot-skills-zh/self-improving-zh)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/self-improving-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/self-improving-zh/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/l-lesteryu/openclaw-hot-skills-zh/self-improving-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/self-improving-zh.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00110 | $0.02540 |
| Opus 5 | $0.00055 | $0.01270 |
| Sonnet 5 | $0.00022 | $0.00508 |
| Haiku 4.5 | $0.00011 | $0.00254 |
Grade A, and why
Self-Improving + Proactive Agent 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
何时使用
当用户纠正你或指出错误时。当你完成重要工作并想评估结果时。当你发现自己输出中可以改进的地方时。知识应该随时间累积，无需手动维护。
架构
记忆存储在 ~/self-improving/ 目录下，采用分层结构。如果 ~/self-improving/ 不存在，请运行 setup.md。
工作区设置应在工作区的 AGENTS、SOUL 和 HEARTBEAT.md 文件中添加标准的自我改进引导，并通过 heartbeat-rules.md 路由定期维护。
~/self-improving/
├── memory.md # 热数据：≤100 行，始终加载
├── index.md # 主题索引，含行数统计
├── heartbeat-state.md # 心跳状态：上次运行、检查的变更、操作记录
├── projects/ # 按项目分类的学习内容
├── domains/ # 按领域分类（代码、写作、沟通）
├── archive/ # 冷数据：已衰减的模式
└── corrections.md # 最近 50 条纠正记录
快速参考
| 主题 | 文件 |
|---|---|
| 设置指南 | setup.md |
| 心跳状态模板 | heartbeat-state.md |
| 记忆模板 | memory-template.md |
| 工作区心跳片段 | HEARTBEAT.md |
| 心跳规则 | heartbeat-rules.md |
| 学习机制 | learning.md |
| 安全边界 | boundaries.md |
| 扩展规则 | scaling.md |
| 记忆操作 | operations.md |
| 自我反思日志 | reflections.md |
| OpenClaw 心跳种子 | openclaw-heartbeat.md |
系统要求
- 无需凭据
- 无需额外二进制文件
- 可选安装
Proactivity技能可能需要网络访问
学习信号
当发现以下模式时自动记录：
纠正信号 → 添加到 corrections.md，评估是否纳入 memory.md：
- "不对，不是这样的..."
- "实际上应该是..."
- "你弄错了..."
- "我更喜欢 X，不是 Y"
- "记住我总是..."
- "我之前告诉过你..."
- "别再这样做 X"
- "你为什么老是..."
偏好信号 → 如果明确表示，添加到 memory.md：
- "我喜欢你..."
- "对我来说总是做 X"
- "永远不要做 Y"
- "我的风格是..."
- "对于 [项目]，使用..."
模式候选 → 跟踪，出现 3 次后提升：
- 同一指令重复 3 次以上
- 反复运行良好的工作流
- 用户赞扬的特定方法
忽略（不记录）：
- 一次性指令（"现在做 X"）
- 特定上下文（"在这个文件中..."）
- 假设性问题（"如果...会怎样"）
自我反思
完成重要工作后，暂停并评估：
- 是否达到预期？ — 比较结果与意图
- 哪里可以更好？ — 找出下次改进的地方
- 这是否是模式？ — 如果是，记录到
corrections.md
何时自我反思：
- 完成多步骤任务后
- 收到反馈后（正面或负面）
- 修复 bug 或错误后
- 发现自己的输出可以更好时
日志格式：
上下文: [任务类型]
反思: [我注意到的内容]
教训: [下次该如何做]
示例：
上下文: 构建 Flutter UI
反思: 间距看起来不对，必须重做
教训: 在展示给用户前先检查视觉间距
自我反思条目遵循相同的提升规则：成功应用 3 次 → 提升到热数据层。
快速查询
| 用户说 | 操作 |
|---|---|
| "你知道关于 X 的什么？" | 搜索所有层级查找 X |
| "你学到了什么？" | 显示 corrections.md 最近 10 条 |
| "显示我的模式" | 列出 memory.md（热数据） |
| "显示 [项目] 模式" | 加载 projects/{name}.md |
| "温存储里有什么？" | 列出 projects/ + domains/ 中的文件 |
| "记忆统计" | 显示各层级数量 |
| "忘记 X" | 从所有层级移除（先确认） |
| "导出记忆" | 打包所有文件为 ZIP |
What ships with it
4 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.
- 9d ago First seen · 251 lines · 110 tokens per session scan A 9fec3220f9af
Self-Improving + Proactive Agent is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (54 stars, last pushed 5mo ago), licensed MIT. It adds 110 tokens to every session and 2,540 once invoked, about $0.0006 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 2026-09-03.
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.