📄 skillActivePromisingmedium

earendil-works/pi

by earendil-works

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

63.5k

Skill Type

📖 Library & API Reference

Quality Score

87/200

License

MIT

Forks

7.7k

Last Updated

Jul 27, 2026

Discovered

May 8, 2026

Validation

Passed

github.com/earendil-works/pi

Quality Breakdown

87/ 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

  • Repository contains AI agent framework with autonomous operation capabilities (agent-loop.ts, agent.ts)
  • Multi-agent spawning potential evidenced by AGENTS.md documentation file
  • Shell/Bash execution capabilities present (shell-output.ts, nodejs.ts execution environment)
  • Session state persistence and memory management (.pi/extensions, session storage with jsonl)
  • GitHub Actions workflows present that could execute arbitrary code during CI/CD (approve-contributor.yml, build-binaries.yml, pr-gate.yml)
  • Extensions system (.pi/extensions) allows dynamic code injection and execution

Related guides