Bots that should be skills: auditing a Grok Bot fleet with six tests
bfrench · x · 2026-10-20
In a long-form article, the author argues the default instinct in Grok Bot — turn everything into a bot — is often wrong. He audited his own fleet against six tests and converted four bots into skills, while keeping the rest as bots with reasons. The piece explains how Skills work in Grok Bot (shared, reusable recipes as short Markdown files), why too many bots stress the system, and offers criteria for deciding what should stay a bot versus become a skill.
More from coding & agent
- Postiz hits $275K MRR: tools that agents use are the fastest-growing software — alvelda · 2026-10-20
- End each dev day by having Claude analyze your session transcript and build skills — EXM7777 · 2026-10-20
- CMU guest lecture covers deep research agents: eval, RL, and new retrieval paradigm — AkariAsai · 2026-10-20
- Dev asks: where's the observability company building tooling for agents, not humans? — DanielLockyer · 2026-10-20
- Inside Turso's MVCC: the birth and death of a row, from bytecode to checkpoint — glcst · 2026-10-20
- Agent-built isometric pixel map of London: LoRA finetune, multiday inference, tile viewer — latticecut · 2026-10-20