Skill 与 AgentSKILLS & AGENTS
kayba-ai/agentic-context-engine
让AI agent从错误中学习,记住纠正,下次不再犯。A Python library that helps AI agents learn from their mistakes and improve without retraining.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
让程序从你的纠正中自动改进回答
从已有的操作记录中提取经验
查看程序已经学到了哪些策略
用一条命令完成模型选择和密钥配置
自动评估并优化程序的表现
Teach your helpers from a single correction
Analyze execution traces to extract strategies
Improve helpers behavior without retraining
Inspect learned strategies at any time
上手GET STARTED
docker run --rm -v ~/.openclaw:/home/node/.openclaw openclaw:local ace-learn --dry-run选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01读取 API KeyReads an API keyexamples/openclaw/kayba-ace/SKILL.md
The script also loads `.env` files from `$OPENCLAW_HOME/.env` and `~/.env`.
静态扫描发现脚本会读取 `$OPENCLAW_HOME/.env` 和 `~/.env` 中的 API Key,存在密钥泄露风险。仅核验官方页面,未审计服务端代码;数据处理和费用以官网为准。The setup script reads API keys from `.env` files, which could expose credentials if the file is shared. Review before using in shared environments.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+1.0%+1.0%
2.6k → 2.6k stars · 50 个快照2.6k → 2.6k stars · 50 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
3 条外部提及3 external mentions
状态STATUS
持续活跃Active
质量 AQuality A
在 Hacker News 上获得多次展示和讨论,社区活跃。Open-source implementation of Stanford's self-learning agent framework
HN_STORY · 5 points · 0 comments
HN_STORY · 3 points · 0 comments
HN_STORY · 10 points · 5 comments
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
}
],
"apiKey": "onfiguration: ```bash export OPENAI_API_KEY=\"your-key\" # or ANTHROPIC_API_KEY, o",
"docker": "install: docker only",
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 9,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 3,
"productivity": 3
},
"primary": "skill-agent",
"secondary": null
},
"localRuntime": null,
"skillMdTotal": 17,
"skillMdErrors": [
{
"path": "examples/openclaw/kayba-ace/SKILL.md",
"error": "no frontmatter"
}
],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 4,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "16 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "python dependency on mcp / fastmcp + MCP framing",
"weight": 0.8
},
{
"signal": "skills/ directory with 8 markdown files",
"weight": 0.75
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".claude/skills/kayba-pipeline/SKILL.md",
".claude/skills/kayba-pipeline/stage-1-api-analysis/SKILL.md",
".claude/skills/kayba-pipeline/stage-2-domain-context/SKILL.md",
".claude/skills/kayba-pipeline/stage-3-metrics/SKILL.md",
".claude/skills/kayba-pipeline/stage-4-rubric/SKILL.md",
".claude/skills/kayba-pipeline/stage-5-action-plan/SKILL.md",
".claude/skills/kayba-pipeline/stage-6-hitl/SKILL.md",
".claude/skills/kayba-pipeline/stage-7-fixer/SKILL.md",
"ace/cli/skills/kayba-pipeline/SKILL.md",
"ace/cli/skills/kayba-pipeline/stage-1-api-analysis/SKILL.md",
"ace/cli/skills/kayba-pipeline/stage-2-domain-context/SKILL.md",
"ace/cli/skills/kayba-pipeline/stage-3-metrics/SKILL.md",
"ace/cli/skills/kayba-pipeline/stage-4-rubric/SKILL.md",
"ace/cli/skills/kayba-pipeline/stage-5-action-plan/SKILL.md",
"ace/cli/skills/kayba-pipeline/stage-6-hitl/SKILL.md",
"ace/cli/skills/kayba-pipeline/stage-7-fixer/SKILL.md",
"examples/openclaw/kayba-ace/SKILL.md"
],
"skillMdFetched": 17
}