📄 skillActivePromisingmedium

devenjarvis/lathe

by devenjarvis

Generate hands-on, multi-part technical tutorials on demand, with LLM skills tuned to make content approachable. Then you work through them yourself, by hand ✋

Supported Platforms

🤖 Claude Code

Stars

1.5k

Skill Type

🔄 Business Process & Team Automation

Quality Score

87/200

License

MIT

Forks

39

Last Updated

Jul 24, 2026

Discovered

Jun 11, 2026

Validation

Passed

github.com/devenjarvis/lathe

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

  • Contains .claude/ directory with multiple LLM skill definitions that could modify AI behavior or integrate with coding agents
  • CLAUDE.md and AGENTS.md files suggest persistent configuration and multi-agent orchestration patterns
  • Install script (install.sh) present that could execute bootstrap automation
  • Repository designed to spawn/coordinate with multiple coding agents (Claude Code, Cursor, Codeium, Cline, Windsurf, etc.) as documented in README
  • Skills system (.claude/skills/) appears to define autonomous capabilities for LLM agents without explicit human approval gates
  • HTTP server component (internal/serve) enables network accessibility and external interaction

Related guides