llama.cpp ships two new AI coding skills for code review and adding models
ngxson · x · 2026-07-25
llama.cpp adds AI coding skills for code review and adding new models
The llama.cpp project has shipped two new skills aimed at AI coding workflows:
- add-new-model: a more detailed extension of HOWTO-add-model.md
- code-review: a per-component review skill, currently covering src/models/, server, and GGML changes
The maintainer says the goal is not to eliminate low-effort contributions, but to reduce review burden by guiding the AI to produce better code from the start. The screenshot also shows the change being merged into master, alongside a pi-agent style open-source harness and open-weight models like GLM-5.2 and Kimi K3.
More from coding & agent
- 'My intelligence stack': developer splits AI coding work across Opus 5.5, Fable and Astra with human review gates — sh_reya · 2026-10-27
- Baseten webinar: evaluate open models for coding agents by benchmarking on your own merged PRs — baseten · 2026-10-27
- Thorsten Ball on working with agents: run more evals, automate everything, use the best models — omarsar0 · 2026-10-27
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- BELL: Open-Source Stack Combines Browserbase, Eve, iMessage and Stripe Link for Personal Agents — jeff_weinstein · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27