Skill of Skills
📄 skillActivePromisingmedium

antoinezambelli/forge

by antoinezambelli

A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows

Supported Platforms

🔧 Generic

Stars

2.1k

Skill Type

📖 Library & API Reference

Quality Score

95/200

License

MIT

Forks

150

Last Updated

Jul 27, 2026

Discovered

Jun 11, 2026

Validation

Passed

github.com/antoinezambelli/forge

Quality Breakdown

95/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Proxy server implementation (src/forge/proxy/) that intercepts and processes LLM API calls - could potentially modify model behavior or outputs
  • Multi-agent workflow orchestration framework that spawns and manages agentic loops with tool-calling capabilities
  • Server implementation (src/forge/server.py, src/forge/proxy/server.py) that runs as a standalone service accepting external connections
  • Tool execution framework with guardrails that processes arbitrary tool calls from LLM - execution context depends on tool definitions
  • Dockerfile present indicating containerized deployment capability
  • Scripts for running integration tests and proxy operations (scripts/integration_test_proxy.py, scripts/smoke_test_proxy.py) suggest operational automation