Open source · applied research

ground-first

The skill that makes a model understand WHAT you meant before answering — with a public cross-vendor benchmark.

Open source Public on GitHub · Cross-vendor benchmark v2 validated

The problem

The model answers the MOST PLAUSIBLE version of your request — not necessarily YOURS. A cultural reference, slang, an internal project name: it fills the gap with a fluent guess, and you only notice after paying for the wrong answer.

The protocol

DETECT — the skill classifies the interpretation risk of a message (your-context reference? slang? recent content?). GROUND — on medium/high risk, it states the interpretation in a scannable block (searching the web when the outside world is the source). ANSWER — only then it answers. Wrong reading? You fix it in one line, not after 800 tokens.

Benchmark, not opinion

0 calls in benchmark v2 36 cases × 3 rounds × 6 vendors
0.94–1.00 specificity silence when the question is clear
0.905 balanced accuracy within benchmark scope

The hard part is not detecting ambiguity — it is staying quiet when there is none. The high specificity is the result I am proudest of: the skill does not become bureaucracy on simple questions.

Portable by design

Works in Claude Code, Codex, Gemini and any chat — the protocol is text, not a plugin. It is also a pattern I use in my products: Braga Suite demands evidence before answering for the same reason.

My role

Author of the protocol, the skill and the cross-vendor benchmark. Code and evaluation public.

Want to build something like this?

No strings attached: tell me the context and I'll tell you what can be proven first.

Start a conversation