dylanpulver

Research Factory — Development skill for Claude Code

Development community

A research factory for Claude Code — structured research that returns decision-ready, sourced briefs, then remembers them so the next question starts ahead.

How to install Research Factory

This entry records only its repository, not the path inside it, so there is no exact command to give. Open dylanpulver/research-factory and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Research Factory does

A research factory for Claude Code — structured research that returns decision-ready, sourced briefs, then remembers them so the next question starts ahead. Prediction quarantine, rival-hunting, decoy-gated judging.

Alternatives in Development

Agent Skills Platform — Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery 2.4k ★
Agent Skill Creator — Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery 2.3k ★
/hunt — Active vulnerability hunting on a target 1.8k ★

README

research-factory

[![CI](https://github.com/dylanpulver/research-factory/actions/workflows/ci.yml/badge.svg)](https://github.com/dylanpulver/research-factory/actions/workflows/ci.yml)

A portable **research factory** for Claude Code. Given a task, it runs structured research and returns a **decision-ready, sourced brief** — then **remembers** it, so the next question starts ahead.

Research is the first step of almost every objective. This is the factory for that step — sibling of a code factory (that drives code; this drives research). Same bones: one **core** loop + swappable **modes** (one per research scenario), global-installed.

FRAME → GATHER → VERIFY → COMPOUND

What it does

Verb	What
Frame	Sharpen the fuzzy question, check the library for a prior answer, pick the mode. The highest-leverage step — ~44% of research-agent failures are bad scoping.
Gather	Retrieve via the pipeline the mode dictates. Breadth modes fan out (reuse the `deep-research` engine); a fact lookup doesn't (fan-out ≈ 15x tokens); an internal question reads the codebase.
Verify	Every claim ties to a real source or is marked `unverified`; confidence + staleness labels. Fabrication is the #1 failure locus (~39%) — this is the safeguard that matters.
Compound	File the brief to `library/`, indexed. The library is checked first next time — the flywheel.

Grounded in a `deep-research` pass over how OpenAI / Anthropic / STORM / GPT-Researcher actually build these (see [`docs/PLAN.md`](docs/PLAN.md) — the factory's first library entry was the research that designed it). This public repo ships [`library/`](library/) with two **example briefs** showing the format; your own briefs accumulate there as you run it.