Terminal
Terminal/Skill
Looks up library and API facts your spec depends on and records them with sources, so your agent builds from facts instead of guesses.
By Julius Brussee
Works with
npx skills add juliusbrussee/cavekit --skill researchEvery finding cites a source. No source → flag it ?, never write a guess as fact.
"Process without library context gives you well-organized hallucinations." Build invents a plausible-but-wrong API & §B fills with avoidable bugs. Research is the external oracle: pull the real fact once, log it caveman, never re-derive.
/grill parked a ? that the outside world must answer.Skip when the build touches only code you already wrote. Research scales to the unknown, ⊥ to habit.
Turn the unknown into 1-3 concrete questions. Vague "research auth" → "JWT lib for Node ESM, maintained?" + "refresh-token rotation: current best practice?". A scoped question gets a citable answer; a vague one gets an essay.
Use web search / docs tools. Prefer primary sources: official docs, the repo, the RFC, the paper. Two independent sources beat one confident blog. For a big sweep, spawn a sub-agent so the raw pages never touch this context — it returns only the distilled finding + source.
Crush each answer to one caveman line + its source. Drop the prose. The §R row is the memory; the tab you read is not.
R3|refresh token|rotate on use, revoke family on reuse-detect|datatracker.ietf.org/doc/html/rfc6819#section-5.2.2.3
Emit the §R rows & hand to the spec skill to append. If a finding changes a constraint or interface, note the §C/§I edit for spec too. Research proposes; spec writes.
? in the finding & say so. An
unverified claim labeled honestly is fine; one disguised as fact is a future §B.Done when every scoped question has a sourced §R row (or an honest ?), and no
build decision still rests on an unchecked assumption. ⊥ research past the
questions you scoped — that is just burning the attention budget.