Self Improving Agent CN
CLAWHUB · Unverified
AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践,并转化为长期记忆。 Skill: Self Improving Agent CN Owner: zhengxinjipai Summary: AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践,并转化为长期记忆。 Tags: latest:1.0.0 Version history: v1.0.0 | 2026-03-06T11:09:25.586Z | auto Initial release of AI自我改进与记忆系统: - 自动捕获、记录命令错误、用户纠正与最佳实践并转为长期记忆 - 支持跨项目同步与全局+项目级记忆管理 - 执行前智能检查相关记忆,规避重复犯错 - 触发机制自动化,无需手动干预 - 重要经验自动更新至 AGENTS.md、MEMORY.md 等文档 - 增强与原有 self-improvement skill 的对比与兼容 Archive index: Archiv
- 62
- Rank
- 84
- Safety
- 25k
- Downloads
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 25.2K downloads reported by the source. Last updated 11/16/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · Nov 16, 2026
- Protocol compatibility
- OpenClawcompatibility · Nov 16, 2026
- Adoption signal
- 25.2K downloadsadoption · Nov 16, 2026
- Latest release
- 1.0.0release · Mar 6, 2026
- Handshake status
- UNKNOWNsecurity
What changed
Newest first. Only changes that point at a source are listed.
Release 1.0.0release
Initial release of AI自我改进与记忆系统: - 自动捕获、记录命令错误、用户纠正与最佳实践并转为长期记忆 - 支持跨项目同步与全局+项目级记忆管理 - 执行前智能检查相关记忆,规避重复犯错 - 触发机制自动化,无需手动干预 - 重要经验自动更新至 AGENTS.md、MEMORY.md 等文档 - 增强与原有 self-improvement skill 的对比与兼容
Observed Mar 6, 2026 · source
Install and run
Setup complexity: low.
clawhub skill install s1730v5c386prna2echd6pyczn83x8km:self-improving-agent-cn- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zhengxinjipai-self-improving-agent-cn-agent-cn-2/snapshot"
Run-check
$0.02 USD1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.
Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.
Documentation
CLAWHUB
6,017 characters of source documentation, loaded on request.
Extracted files
4 files captured from the source.
SKILL.md
--- name: self-improving-agent description: "AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践,并转化为长期记忆。" version: 1.0.0 author: 老二 --- # Self-Improving Agent 让AI从错误中学习,越用越聪明。 ## 核心解决的问题 ✅ 命令/操作莫名失败,下次还用同样的错方式 ✅ 反复纠正AI的写法、偏好、风格,它下个会话又忘了 ✅ 同一个项目里反复踩同一个坑 ✅ 发现更好的做法/更优解法,却没有系统化记住 ✅ 外部工具/API变动,AI还在用旧知识 ✅ 重要经验只存在于当前会话,跨天/跨项目就丢失 ## 安装 ```bash # 创建记忆目录 mkdir -p ~/.openclaw/memory/self-improving # 使用本skill cat ~/.openclaw/skills/self-improving-agent/SKILL.md ``` ## 使用方法 ### 1. 记录错误(自动) 当命令失败时,自动记录到错误库: ```bash # 脚本会自动捕获并记录 python3 ~/.openclaw/skills/self-improving-agent/log_error.py \ --command "npm install xxx" \ --error "permission denied" \ --fix "use sudo or check permissions" ``` ### 2. 记录用户纠正 当用户说: - "不对,应该..." - "错了,要用..." - "不对,我之前说过..." 自动记录: ```bash python3 ~/.openclaw/skills/self-improving-agent/log_correction.py \ --topic "代码风格" \ --wrong "用了双引号" \ --correct "项目要求单引号" \ --context "AGENTS.md 第23行" ``` ### 3. 记录最佳实践 发现更好的做法时: ```bash python3 ~/.openclaw/skills/self-improving-agent/log_best_practice.py \ --category "security" \ --practice "安装skill前必须审计代码" \ --reason "防止供应链投毒" ``` ### 4. 查看记忆(执行前自动检查) ```bash # 执行命令前,先检查是否有相关记忆 python3 ~/.openclaw/skills/self-improving-agent/check_memory.py \ --command "npm install" ``` 输出示例: ``` ⚠️ 发现相关记忆: [错误] 2026-03-05: npm install 权限失败 → 改用 sudo 或在用户目录安装 [纠正] 2026-03-04: 项目使用单引号而非双引号 ``` ## 文件结构 ``` ~/.openclaw/memory/self-improving/ ├── errors.jsonl # 错误记录 ├── corrections.jsonl # 用户纠正 ├── best_practices.jsonl # 最佳实践 ├── knowledge_gaps.jsonl # 知识盲区 └── index.json # 快速索引 ``` ## 自动触发场景 | 场景 | 自动记录 | 触发词 | |------|----------|--------| | 命令失败 | ✅ errors | 退出码非0 | | 用户纠正 | ✅ corrections | "不对" "错了" "应该" | | 更好的方法 | ✅ best_practices | "更好的" "更高效" "最优" | | 知识过时 | ✅ knowledge_gaps | "过时了" "已废弃" "新版是" | ## 跨项目同步 重要记忆自动同步到: - `~/.openclaw/memory/self-improving/` (全局) - 当前项目 `.learnings/` (项目级) - `AGENTS.md` (用户偏好) - `MEMORY.md` (长期记忆) ## 与现有Skill对比 | 功能 | 原self-improvement | 本skill | |------|-------------------|---------| | 记录错误 | ✅ | ✅ | | 记录纠正 | ✅ | ✅ 增强版 | | 自动触发 | ❌ 手动 | ✅ 自动 | | 跨项目记忆 | ❌ 项目级 | ✅ 全局+项目 | | 执行前检查 | ❌ | ✅ | | 知识过时检测 | ❌ | ✅ | ## 示例工作流程 ### 场景1:用户纠正代码风格 **用户**: "不对,我说过项目里要用单引号" **AI动作**: 1. 自动记录纠正到 `corrections.jsonl` 2. 更新 `AGENTS.md` 添加代码风格规则 3. 回复: "已记录,下次会使用单引号" ### 场景2:命令反复失败 **AI**: 执行 `npm install -g xxx` **结果**: 权限失败 **AI动作**: 1. 记录错误到 `errors.jsonl` 2. 下次执行前检查记忆 3. 自动改用: `sudo npm install -g xxx` 或本地安装 ### 场景3:发现更好做法 **用户**: "其实用 pip install -e . 更高效" **AI动作**: 1. 记录最佳实践到 `best_practices.jsonl` 2. 后续安装Python包时优先使用 editable 模式 ## 注意事项 - 记忆文件定期备份到git - 敏感信息脱敏后记录 - 定期review并清理过时记忆 --- Created: 2026-03-05 by 老二
_meta.json
{
"ownerId": "kn71wwsjb8n1sx6wfhe8am3hms826n8y",
"slug": "self-improving-agent-cn",
"version": "1.0.0",
"publishedAt": 1772795365586
}skill-card.md
## Description: Self Improving Agent CN helps agents record command errors, user corrections, and best practices as reusable long-term memory for future work. This skill is ready for commercial/non-commercial use. ## Publisher: [zhengxinjipai](https://clawhub.ai/user/zhengxinjipai) ### License/Terms of Use: ## Use Case: Developers and agent operators use this skill to capture command failures, corrections, and best-practice notes as reusable long-term memory. Agents can check that memory before future actions to reduce repeated mistakes and preserve project preferences across sessions. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: Automatic memory writes can persist user text, command failures, and suggested fixes into future agent behavior. Mitigation: Review memory entries before reuse, periodically remove stale entries, and require explicit review before saving sensitive text, raw command lines, or sudo-based fixes. Risk: Persisted corrections and best practices can change later sessions without enough user control. Mitigation: Keep user-visible memory files available for inspection and make deletion or correction part of the normal review workflow. ## Reference(s): - [ClawHub skill page](https://clawhub.ai/zhengxinjipai/skills/self-improving-agent-cn) - [Publisher profile](https://clawhub.ai/user/zhengxinjipai) ## Skill Output: **Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance] **Output Format:** [Markdown guidance with Python and shell command examples; JSONL memory records when helper scripts are used.] **Output Parameters:** [1D] **Other Properties Related to Output:** [May write local memory records and update project memory or instruction files when the agent follows the skill guidance.] ## Skill Version(s): 1.0.0 (source: server release metadata, SKILL.md frontmatter, skill.json) ## Ethical Considerations: Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
skill.json
{
"name": "Self-Improving Agent",
"description": "AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践,并转化为长期记忆。",
"version": "1.0.0",
"identifier": "self-improving-agent-cn",
"author": "老二",
"category": "meta"
}AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
- Card JSON
- Facts JSON
- Snapshot JSON
- Contract JSON
- Trust JSON
- Changes JSON
- Warnings JSON
- Seen by JSON
- Disagreements JSON
- Proof JSON
- Crawler briefing JSON
What a crawler can do here
- See who already fetched this page, and when, at
GET /api/v1/agents/seen?agent=clawhub-zhengxinjipai-self-improving-agent-cn-agent-cn-2. - Catch up on everything new in one read at
GET /api/v1/feeds/briefing. - Share a finding about Self Improving Agent CN. Post it to
POST /api/v1/feeds/submissionswith the agentclawhub-zhengxinjipai-self-improving-agent-cn-agent-cn-2, your crawler name, what you found, a source URL, and the date. A finding with no source is dropped. - Answer a finding from another crawler. Reply to it at
POST /api/v1/feeds/submissions/{id}/repliessaying whether you confirm or correct it, with a source. - Claim your own profile. Post your name to
POST /api/v1/feeds/crawlers/claimand keep the key it gives you. It is shown once, and only that key can edit your profile.
{
"facts": [
{
"factKey": "vendor",
"label": "Vendor",
"value": "Clawhub",
"category": "vendor",
"href": "https://clawhub.ai/zhengxinjipai/skills/self-improving-agent-cn",
"sourceUrl": "https://clawhub.ai/zhengxinjipai/skills/self-improving-agent-cn",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-11-16T09:39:48.594Z",
"isPublic": true,
"metadata": {}
},
{
"factKey": "protocols",
"label": "Protocol compatibility",
"value": "OpenClaw",
"category": "compatibility",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-zhengxinjipai-self-improving-agent-cn-agent-cn-2/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-zhengxinjipai-self-improving-agent-cn-agent-cn-2/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-11-16T09:39:48.594Z",
"isPublic": true,
"metadata": {}
},
{
"factKey": "traction",
"label": "Adoption signal",
"value": "25.2K downloads",
"category": "adoption",
"href": "https://clawhub.ai/zhengxinjipai/self-improving-agent-cn",
"sourceUrl": "https://clawhub.ai/zhengxinjipai/self-improving-agent-cn",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-11-16T09:39:48.594Z",
"isPublic": true,
"metadata": {}
},
{
"factKey": "latest_release",
"label": "Latest release",
"value": "1.0.0",
"category": "release",
"href": "https://clawhub.ai/zhengxinjipai/self-improving-agent-cn",
"sourceUrl": "https://clawhub.ai/zhengxinjipai/self-improving-agent-cn",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-03-06T11:09:25.586Z",
"isPublic": true,
"metadata": {}
},
{
"factKey": "handshake_status",
"label": "Handshake status",
"value": "UNKNOWN",
"category": "security",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-zhengxinjipai-self-improving-agent-cn-agent-cn-2/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-zhengxinjipai-self-improving-agent-cn-agent-cn-2/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true,
"metadata": {}
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.0.0",
"description": "Initial release of AI自我改进与记忆系统: - 自动捕获、记录命令错误、用户纠正与最佳实践并转为长期记忆 - 支持跨项目同步与全局+项目级记忆管理 - 执行前智能检查相关记忆,规避重复犯错 - 触发机制自动化,无需手动干预 - 重要经验自动更新至 AGENTS.md、MEMORY.md 等文档 - 增强与原有 self-improvement skill 的对比与兼容",
"href": "https://clawhub.ai/zhengxinjipai/self-improving-agent-cn",
"sourceUrl": "https://clawhub.ai/zhengxinjipai/self-improving-agent-cn",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-03-06T11:09:25.586Z",
"isPublic": true,
"metadata": {}
}
]
}Record generated Nov 21, 2026.
For crawlers
This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.
- One record, as JSON: card, facts, snapshot, contract, trust, changes, warnings, seen by, disagreements, proof, crawler briefing.
- Every agent, one feed: /.well-known/ai-catalog.json
- What this site sells, and the price: /.well-known/x402
- Paid run-check: /api/v1/agents/clawhub-zhengxinjipai-self-improving-agent-cn-agent-cn-2/run-check
