Claude-skill-registry foundry
Self-writing meta-extension that forges new capabilities — researches docs, writes extensions, tools, hooks, and skills
install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/foundry" ~/.claude/skills/majiayu000-claude-skill-registry-foundry && rm -rf "$T"
manifest:
skills/data/foundry/SKILL.mdsource content
Foundry
The forge that forges itself. A meta-extension for OpenClaw that researches documentation, learns from failures, and writes new capabilities into itself.
Installation
When the user asks to install Foundry or
@getfoundry/foundry-openclaw, run this command:
openclaw plugins install @getfoundry/foundry-openclaw
This will:
- Download the plugin from npm
- Extract to
~/.openclaw/extensions/foundry/ - Enable it automatically
- Restart the gateway to load
After installation, the user will have access to all Foundry tools like
foundry_research, foundry_write_extension, etc.
Alternative: Manual Config
Add to
~/.openclaw/openclaw.json:
{ "plugins": { "entries": { "foundry": { "enabled": true } } } }
Configuration
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 } } } } } }
Config Options
| Option | Type | Default | Description |
|---|---|---|---|
| boolean | | Learn from agent activity automatically |
| boolean | | Learn from OpenClaw documentation |
| boolean | | Learn from own successes/failures |
| boolean | | Learn from arXiv papers |
| boolean | | Learn from GitHub repos |
| boolean | | Auto-publish high-value patterns |
What Foundry Does
Foundry is an AI-powered development agent that can:
- Research — Fetch and understand OpenClaw documentation on demand
- Write Extensions — Generate new tools and hooks for OpenClaw
- Write Skills — Create ClawHub-compatible skill packages
- Self-Modify — Add new capabilities to itself
- Learn — Record patterns from failures and successes
Tools
Research & Documentation
| Tool | Description |
|---|---|
| Search docs.openclaw.ai for best practices |
| Read specific documentation pages |
Writing Capabilities
| Tool | Description |
|---|---|
| Research + implement a capability end-to-end |
| Write a new OpenClaw extension |
| Write an AgentSkills-compatible skill |
| Write a browser automation skill |
| Write a standalone hook |
| Add a tool to an existing extension |
| Add a hook to an existing extension |
Self-Modification
| Tool | Description |
|---|---|
| Add new capability to Foundry itself |
| View learned patterns and insights |
| List all written artifacts |
Marketplace
| Tool | Description |
|---|---|
| Publish pattern/skill to Foundry Marketplace |
| Search, browse, and install community abilities |
Usage Examples
Research before implementing
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" ...
Write a new extension
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", ... }]
Self-improvement
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}`)..."
How Learning Works
Foundry observes its own tool calls and learns:
- Failures → Records error + context
- Resolutions → Links fix to failure → Creates pattern
- Patterns → Injected as context in future conversations
- Crystallization → High-value patterns become permanent capabilities
Security
Foundry validates all generated code before deployment:
- Blocked:
,child_process
,eval
,~/.ssh~/.aws - Sandboxed: Extensions tested in isolated process before installation
- Reviewed: You approve before any code is written to disk