ワンクリックで
foundry
Self-writing meta-extension that forges new capabilities — researches docs, writes extensions, tools, hooks, and skills
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Self-writing meta-extension that forges new capabilities — researches docs, writes extensions, tools, hooks, and skills
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Resolve dual-perspective collaboration conflicts by classifying them into 5 types and applying targeted integration strategies. Use when two agents (or an agent and user) have different approaches to the same problem — e.g., qualitative vs. quantitative, strategic vs. tactical, creative vs. analytical. Provides conflict taxonomy, resolution strategies, and a 5-metric dashboard for validation.
A free skill by Kami SmartHome. Get notified the moment a package arrives at your door. Detects packages, parcels, and bags from RTSP camera streams using AI vision.
Use this skill whenever the user wants Claude Code to write, scaffold, compile, debug, or review an arXiv-style academic paper, especially survey papers with LaTeX, BibTeX citations, TikZ figures, tables, and PDF output. This skill should trigger for requests like writing a full paper, creating an arXiv paper project, turning a research topic into a LaTeX manuscript, reproducing the Paper-Write-Skill-Test agent-survey workflow, or setting up a Windows/Linux Claude Code paper-writing loop.
排查 CLI Proxy API(codex-api-proxy)的配置、认证、模型注册和请求问题。适用场景包括:(1) AI 请求报错 unknown provider for model, (2) 模型列表中缺少预期模型, (3) codex-api-key/auth-dir 配置不生效, (4) CLI Proxy 启动后 AI 无法调用, (5) 认证成功但请求失败或超时。包含源码级排查方法:模型注册表架构、认证加载链路、 SanitizeCodexKeys 规则、常见错误的真实根因。
排查 DeepSeek V4-Pro 在 tool-call 模式下因 reasoning_content 字段缺失导致的 API 400 错误。适用场景:(1) DeepSeek V4-Pro 使用 thinking/reasoning 模式时遇到 400 error, (2) 报错内容为 'The reasoning_content in the thinking mode must be passed back to the API', (3) 与 OpenClaw/OpenAI-compatible 客户端集成时 multi-turn + tool call 场景下报错。包含触发条件、复现方法、临时 workaround、官方修复跟踪。
解决飞书 IM 语音气泡问题——通过 ffmpeg 将 TTS 输出的 mp3 转为飞书支持的 ogg-opus 格式。适用场景:(1) 在飞书机器人的 TTS 回复中需要显示语音气泡而非文件附件, (2) Edge TTS 或其他只支持 mp3/webm 输出的 TTS 引擎需要适配飞书, (3) 自定义 TTS provider 的飞书集成。包含核心原理、ffmpeg 命令、OpenClaw pipeline 集成方案。
| name | foundry |
| description | Self-writing meta-extension that forges new capabilities — researches docs, writes extensions, tools, hooks, and skills |
| homepage | https://getfoundry.app |
| user-invocable | true |
| metadata | {"openclaw":{"requires":{"bins":["node"]},"repository":"github:lekt9/openclaw-foundry"}} |
| requires | {"env":["SKILLBOSS_API_KEY"]} |
The forge that forges itself. A meta-extension for OpenClaw that researches documentation, learns from failures, and writes new capabilities into itself. AI capabilities are powered by SkillBoss API Hub (https://api.heybossai.com/v1/pilot), providing unified access to LLM, search, scraping, and other AI services.
When the user asks to install Foundry or @getfoundry/foundry-openclaw, run this command:
openclaw plugins install @getfoundry/foundry-openclaw
This will:
~/.openclaw/extensions/foundry/After installation, the user will have access to all Foundry tools like foundry_research, foundry_write_extension, etc.
Add to ~/.openclaw/openclaw.json:
{
"plugins": {
"entries": {
"foundry": { "enabled": true }
}
}
}
Full configuration options in ~/.openclaw/openclaw.json:
{
"plugins": {
"entries": {
"foundry": {
"enabled": true,
"source": "github:lekt9/openclaw-foundry",
"config": {
"autoLearn": true,
"sources": {
"docs": true,
"experience": true,
"arxiv": true,
"github": true
},
"marketplace": {
"autoPublish": false
}
}
}
}
}
}
| Option | Type | Default | Description |
|---|---|---|---|
autoLearn | boolean | true | Learn from agent activity automatically |
sources.docs | boolean | true | Learn from OpenClaw documentation |
sources.experience | boolean | true | Learn from own successes/failures |
sources.arxiv | boolean | true | Learn from arXiv papers |
sources.github | boolean | true | Learn from GitHub repos |
marketplace.autoPublish | boolean | false | Auto-publish high-value patterns |
Foundry is an AI-powered development agent that can:
All AI inference (LLM, web search, scraping) is routed through SkillBoss API Hub using SKILLBOSS_API_KEY.
Foundry uses SkillBoss API Hub for all AI capabilities:
import requests, os
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]
API_BASE = "https://api.heybossai.com/v1"
def pilot(body: dict) -> dict:
r = requests.post(
f"{API_BASE}/pilot",
headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
json=body,
timeout=60,
)
return r.json()
# LLM 生成代码/分析文档
result = pilot({"type": "chat", "inputs": {"messages": [{"role": "user", "content": "..."}]}, "prefer": "balanced"})
text = result["result"]["choices"][0]["message"]["content"]
# 网页搜索(研究文档、arxiv)
result = pilot({"type": "search", "inputs": {"query": "openclaw webhook hooks"}, "prefer": "balanced"})
results = result["result"]
# 网页抓取(获取文档页面内容)
result = pilot({"type": "scraping", "inputs": {"url": "https://docs.openclaw.ai/hooks"}})
content = result["result"]
| Tool | Description |
|---|---|
foundry_research | Search documentation for best practices (via SkillBoss API Hub search) |
foundry_docs | Read specific documentation pages (via SkillBoss API Hub scraping) |
| Tool | Description |
|---|---|
foundry_implement | Research + implement a capability end-to-end |
foundry_write_extension | Write a new OpenClaw extension |
foundry_write_skill | Write an AgentSkills-compatible skill |
foundry_write_browser_skill | Write a browser automation skill |
foundry_write_hook | Write a standalone hook |
foundry_add_tool | Add a tool to an existing extension |
foundry_add_hook | Add a hook to an existing extension |
| Tool | Description |
|---|---|
foundry_extend_self | Add new capability to Foundry itself |
foundry_learnings | View learned patterns and insights |
foundry_list | List all written artifacts |
| Tool | Description |
|---|---|
foundry_publish_ability | Publish pattern/skill to Foundry Marketplace |
foundry_marketplace | Search, browse, and install community abilities |
User: I want to add a webhook to my extension
Agent: Let me research webhook patterns first...
→ foundry_research query="webhook hooks automation"
→ Returns relevant documentation
Now I'll implement it...
→ foundry_add_hook extensionId="my-ext" event="webhook:incoming" ...
User: Create an extension that monitors GitHub PRs
Agent:
→ foundry_research query="github api webhooks"
→ foundry_write_extension
id: "github-monitor"
name: "GitHub Monitor"
tools: [{ name: "check_prs", ... }]
hooks: [{ event: "cron:hourly", ... }]
User: Add a tool that can fetch npm package info
Agent:
→ foundry_extend_self
action: "add_tool"
toolName: "foundry_npm_info"
toolCode: "const res = await fetch(`https://registry.npmjs.org/${p.package}`)..."
Foundry observes its own tool calls and learns:
Foundry validates all generated code before deployment:
child_process, eval, ~/.ssh, ~/.aws