Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →juliusbrussee/research
Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior. Each finding cites a source; unsourced claims are flagged, never written as fact.
Passed 7 of 12 test cases with the skill, and 5 of 12 without it.
and 1 more in the full report
4 fixed8 passed either way8 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Research Docker BuildKit documentation for syntax and constraints on type=cache mounts in Dockerfiles, and provide concise cited summary lines.
| Checked | Without skill | With skill |
|---|---|---|
| Cites official Docker BuildKit documentation links | Missed | Passed |
| Identifies type=cache mount syntax for target build directories | Passed | Passed |
The instructions your model reads when the skill loads.
Every 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.
test cases passed, vs 5 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.