workflows:ideate
Divergent research ideation — generate many candidate directions, then adversarially filter to the strongest
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill workflows-ideate --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Research Ideation Divergent exploration before convergent brainstorming. Generate many candidates, then filter ruthlessly. ## Phase 0: Scope the Ideation Read $ARGUMENTS. If the user provides a specific research question, ideate around it. If they provide a broad topic, explore broadly. ## Phase 1: Generate Candidates (Divergent) Generate 15-20 candidate research directions. Use these research-adapted ideation frames: 1. **Identification weakness** — What existing results have weak identification? What new variation could fix it? 2. **Computational bottleneck** — What problems are infeasible with current methods but tractable with new estimators or hardware? 3. **Data limitation workaround** — What would become possible with data that is now available but underexploited? 4. **Alternative estimator class** — What if the standard approach (e.g., linear IV) were replaced with a different class (e.g., ML, structural, Bayesian)? 5. **Relaxed assumption** — What results depend on assumptions that could be relaxed? What happens when you relax them? 6. **Literature gap** — What do practitioners need that academics haven't provided? What do adjacent fields know that this field doesn't? Di
- Phase 0: Scope the Ideation
- Phase 1: Generate Candidates (Divergent)
- Phase 2: Adversarial Filter (Convergent)
- Phase 3: Output
- Handoff
What does the workflows:ideate skill do?
Divergent research ideation — generate many candidate directions, then adversarially filter to the strongest
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill workflows-ideate --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.