GitHub open-sources lever: a skills library that turns your agent session history into one-command automations
0xkarasy · x · 2026-10-29
Evan Boyle and a group of engineers launched github/lever, a library of skills for automating boring work. The team pooled their agent session histories, mined them for the patterns that produce the best results, and packaged them into low-barrier skills.
Usage follows /lever <verb> <your words> — "the verb picks the playbook, the rest is just you, talking normally":
- Build: brief (12 words in, runnable brief out), refactor (e.g. cut a 400k-line codebase in half across three terminals), shepherd (rebase/fix/rerun until it lands)
- Loop: loop, arms (one agent per idea), review (more than one model reads your PR)
- Run: automate (schedule an automation for a repo)
- Tuning: mirror (learns your last 30 days of prompts), steer (remembered corrections), autonomy (fine-grained agent permissions)
If you don't know the verb, just describe the problem and lever picks one for you.
More from coding & agent
- Build-A-Chip-Bench: end-to-end chip design benchmark, top agent scores just 16.6% — teortaxesTex · 2026-10-29
- Separate Discovery from Scoping: Grill the Agent Before It Writes Code — rseroter · 2026-10-29
- Autocomplete.dev brings Tab-style next-message suggestions to chatbots, 20k users already — josh_bickett · 2026-10-29
- Coinbase Agent trading hits all-time highs, with Grok Bot taking 67% of volume — MurrLincoln · 2026-10-29
- REA Turns App Recordings into RL Environments; 'Wave of Sloppy Envs' Incoming — teortaxesTex · 2026-10-29
- 86M-param decoder-only transformer plays chess on Lichess, full notebook public — andreisavu · 2026-10-29