self-improving-agent-next
记录错误、纠正、能力缺口与最佳实践，形成可复用的持续改进闭环。适用于：命令失败、用户纠正、外部 API/工具异常、发现更优做法、提出新能力需求，以及任务前复盘历史经验。
- Installs
- 333
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://skills.volces.com --skill self-improving-agent-next- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads self-improving-agent-next automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Self-Improving Agent（自我改进）
把“踩坑”变成“资产”。 每次失败、纠正或新发现，都写入结构化记录，后续可检索、可复盘、可沉淀到长期规则。
1. 什么时候必须记录
出现以下任一情况时，立即记录：
- 命令/操作失败（非 0 退出、超时、异常输出）
- 用户纠正你（“不对”“应该是…”）
- 用户提出你当前不具备的能力
- 外部服务失败（API 报错、限流、鉴权失败）
- 你意识到知识已过时或理解错误
- 你发现了可复用的更优流程
2. 记录到哪里
在工作区使用 .learnings/：
.learnings/LEARNINGS.md：纠正、认知缺口、最佳实践.learnings/ERRORS.md：失败与异常.learnings/FEATURE_REQUESTS.md：能力请求
若目录不存在，先创建：
mkdir -p .learnings
3. 快速分流规则
- 失败/报错 →
ERRORS.md - 被纠正/学到新规则 →
LEARNINGS.md - 想要但暂不支持的能力 →
FEATURE_REQUESTS.md
4. ID 规范
格式：TYPE-YYYYMMDD-XXX
- TYPE:
LRN/ERR/FEAT - 日期：当天日期
- XXX：三位序号（如
001）
示例：
LRN-20260308-001ERR-20260308-002FEAT-20260308-001
5. 模板（请严格使用）
5.1 Learning 模板（LEARNINGS.md）
## [LRN-YYYYMMDD-XXX] correction | knowledge_gap | best_practice
**Logged**: ISO-8601 时间
**Priority**: low | medium | high | critical
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config
### Summary
一句话总结
### Details
发生了什么、哪里错了、正确做法是什么
### Suggested Action
下一次应执行的具体动作
### Metadata
- Source: conversation | error | user_feedback | simplify-and-harden
- Related Files: path/to/file
- Tags: tag1, tag2
- See Also: LRN-...（可选）
- Pattern-Key: ...（可选）
- Recurrence-Count: 1（可选）
- First-Seen: YYYY-MM-DD（可选）
- Last-Seen: YYYY-MM-DD（可选）
---
5.2 Error 模板（ERRORS.md）
## [ERR-YYYYMMDD-XXX] command_or_integration
**Logged**: ISO-8601 时间
**Priority**: medium | high | critical
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config
### Summary
一句话说明失败点
### Error
完整报错文本
### Context
- 执行了什么命令/操作
- 使用了哪些参数
- 关键环境信息
### Suggested Fix
可执行的修复建议
### Metadata
- Reproducible: yes | no | unknown
- Related Files: path/to/file
- See Also: ERR-...（可选）
---
5.3 Feature Request 模板（FEATURE_REQUESTS.md）
## [FEAT-YYYYMMDD-XXX] capability_name
**Logged**: ISO-8601 时间
**Priority**: low | medium | high
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config
### Requested Capability
用户希望实现什么
### User Context
用户为什么需要它
### Complexity Estimate
simple | medium | complex
### Suggested Implementation
实现方向（脚本、工具、流程）
### Metadata
- Frequency: first_time | recurring
- Related Features: ...（可选）
---
6. 状态流转
允许状态：
pending：待处理in_progress：处理中resolved：已解决promoted：已提升到长期规则文件wont_fix：不处理（需写原因）
当问题已解决时，补充：
### Resolution
- **Resolved**: ISO-8601 时间
- **Commit/PR**: commit hash 或 PR 链接
- **Notes**: 做了什么
7. 何时“晋升”到长期记忆文件
满足以下任一条件，建议晋升：
- 同类问题重复出现
- 对多人/多任务都适用
- 不写下来就会反复踩坑
晋升目标：
- 工作流规则 →
AGENTS.md - 行为/表达规则 →
SOUL.md - 工具使用细节 →
TOOLS.md - 长期偏好/事实 →
MEMORY.md
晋升后把原条目状态改为 promoted，并注明目标文件。
8. 复盘频率
建议在以下时机快速复盘 .learnings/：
- 开始新任务前
- 完成复杂任务后
- 每周至少一次
可用命令：
# 统计 pending
grep -h "Status\*\*: pending" .learnings/*.md | wc -l
# 查看高优先级
grep -B5 "Priority\*\*: high" .learnings/*.md | grep "^## \["
9. 执行原则（简版）
- 立即记录：别等会儿，信息会丢。
- 写可执行建议：不是“再看看”，而是“下次先做 X”。
- 优先去重与关联：能关联就加
See Also。 - 重复三次就系统化：提升到
AGENTS.md/SOUL.md/TOOLS.md。 - 短而准：结论可复用，描述可追溯。
10. OpenClaw 场景建议
- 在主会话中把高价值学习同步到
MEMORY.md。 - 在需要跨会话协作时，使用
sessions_send分享关键学习。 - 对高频重复问题，优先将规则写入工作区文档，减少未来上下文成本。
目标不是“记日志”，而是持续降低错误率、提高可复用性。
FAQ
What does the self-improving-agent-next skill do?
记录错误、纠正、能力缺口与最佳实践，形成可复用的持续改进闭环。适用于：命令失败、用户纠正、外部 API/工具异常、发现更优做法、提出新能力需求，以及任务前复盘历史经验。
How do I install self-improving-agent-next?
Run npx skills add https://skills.volces.com --skill self-improving-agent-next in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/self-improving-agent-next/ (personal) or .claude/skills/self-improving-agent-next/ (project).
Which AI agents can use self-improving-agent-next?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is self-improving-agent-next safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains self-improving-agent-next?
It is published by skills.volces.com in skills.volces.com. It has 333 recorded installs.
More from skills.volces.com
byted-web-search
skills.volces.com
火山引擎豆包搜索 API（原联网搜索/融合信息搜索），返回网页/图片结果。联网搜索场景优先使用本 skill。触发词包括：豆包搜索、查/搜/找、真的吗/靠谱吗/确认/核实、最近/今天/最新/近期、出处/来源/链接、Agent Plan、融合信息搜索、Harness、有什么/有哪些/推荐、价格/政策/汇率/行情、对比/区别/哪个好、听说/据说/不太确定、热搜/热门/火、帮我看/了解一下、求证/辟谣、值不值得/该不该。任务依赖在线事实或时效性时优先使用。若回答可能依赖外部事实，优先调用本 skill 再作答。
byted-supabase
skills.volces.com
火山引擎 Supabase . 管理 AIDAP Supabase 项目、工作区、数据库、分支、Auth、Realtime、Edge Functions、Storage、API Keys、SQL、Schema 变更、TypeScript 类型生成和 MCP 集成。
find-skills
skills.volces.com
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
byted-util-ark-cua
skills.volces.com
Delegate broad computer-use tasks to ARK CUA for Volcengine AgentPlan users through an authenticated cloud desktop, and synchronize explicit credentials to a caller-owned CUA through Credential Agent. Use for web or desktop-app operation, file workflows, reusable task contexts, artifacts, temporary CUA App URLs, desktop shutdown/start/recovery, inspection, or exact browser, environment, secret, Credential Set, and managed-file credential setup/sync/status/reset. Do not use when local reasoning or a purpose-built local/API tool can complete the request more directly.
agent-browser
skills.volces.com
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
self-improving-agent
skills.volces.com
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。
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.