Research Innovation Explorer
Turns a vague research-idea request into a sourced paper pool, scored idea matrix, and report.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 13, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 53961b2
Fed it a live topic (efficient long-context retrieval for LLM agents) with two real papers pulled via search; its structured decomposition produced a falsifiable hybrid hypothesis with explicit baselines, a full alpha-sweep, and a named failure condition, versus 'combine A and B, probably novel' from an unguided baseline.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What Research Innovation Explorer does
Runs a disciplined literature-to-idea pipeline: collect 20-50 recent papers, decompose them into reusable mechanisms, generate pairwise module combinations, score and shortlist candidates, and write a falsifiable hypothesis with baselines and ablations. Triggers when someone wants a publishable or novel research idea grounded in real prior work rather than an unfounded 'combine A and B' pitch; explicitly downgrades confidence and refuses to fabricate novelty or citations when evidence is thin.
How to install Research Innovation Explorer
git clone https://github.com/foryourhealth111-pixel/research-innovation-explorer
cd research-innovation-explorer
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/research-innovation-explorer
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Research Innovation Explorer
-
/research-innovation-explorerTurns a vague research-idea request into a sourced paper pool, scored idea matrix, and report.
It also activates on plain-language prompts like these:
-
I want a novel, publishable research idea grounded in recent papers on this topic -
Survey recent literature on this area and score me some new research directions -
Combine mechanisms from these papers into a falsifiable hypothesis with baselines
Frequently asked questions
- Is the Research Innovation Explorer skill free?
- Yes. The skill itself is free from foryourhealth111-pixel/research-innovation-explorer. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Research Innovation Explorer work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Fed it a live topic (efficient long-context retrieval for LLM agents) with two real papers pulled via search; its structured decomposition produced a falsifiable hybrid hypothesis with explicit baselines, a full alpha-sweep, and a named failure condition, versus 'combine A and B, probably novel' from an unguided baseline.
- What is the Research Innovation Explorer SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Research Innovation Explorer?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Research Innovation Explorer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.