Agent skill

idea-creator

Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.

brycew6m4,252★ · +31/wk · 3 repos on radarProfile →
claude-codecan modify filesNOASSERTION
Install
npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill idea-creator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 11 KB
Bundled scripts: none
Allowed tools: Bash(*)ReadWriteGrepGlobWebSearchWebFetchAgentmcp__codex__codexmcp__codex__codex-reply
Path: skills/42-wanshuiyin-ARIS/skills/idea-creator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 3,244
Language: Stata
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Research Idea Creator Generate publishable research ideas for: $ARGUMENTS ## Overview Given a broad research direction from the user, systematically generate, validate, and rank concrete research ideas. This skill composes with `/research-lit`, `/novelty-check`, and `/research-review` to form a complete idea discovery pipeline. ## Constants - **PILOT_MAX_HOURS = 2** — Skip any pilot estimated to take > 2 hours per GPU. Flag as "needs manual pilot". - **PILOT_TIMEOUT_HOURS = 3** — Hard timeout: kill pilots exceeding 3 hours. Collect partial results if available. - **MAX_PILOT_IDEAS = 3** — Pilot at most 3 ideas in parallel. Additional ideas are validated on paper only. - **MAX_TOTAL_GPU_HOURS = 8** — Total GPU budget for all pilots combined. - **REVIEWER_MODEL = `gpt-5.4`** — Model used via Codex MCP for brainstorming and review. Must be an OpenAI model (e.g., `gpt-5.4`, `o3`, `gpt-4o`). > 💡 Override via argument, e.g., `/idea-creator "topic" — pilot budget: 4h per idea, 20h total`. ## Workflow ### Phase 1: Landscape Survey (5-10 min) Map the research area to understand what exists and where the gaps are. 1. **Scan local paper library first**: Check `papers/` and `literature/` in

What's inside
Steps it walks through
  1. Overview
  2. Constants
  3. Workflow
  4. Phase 1: Landscape Survey (5-10 min)
  5. Phase 2: Idea Generation (brainstorm with external LLM)
  6. Phase 3: First-Pass Filtering
  7. Phase 4: Deep Validation (for top ideas)
  8. Phase 5: Parallel Pilot Experiments (for top 2-3 ideas)
  9. Phase 6: Output — Ranked Idea Report
  10. Key Rules
  11. Composing with Other Skills
More from Auto-Empirical-Research-Skills
All skills →
About this skill
What does the idea-creator skill do?

Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.

How do I install it?

Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill idea-creator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going