agentleFS
Sign inStart free
InSciCoInSciCo/i-framework/.claude/skills/ideate/SKILL.md

ideate

Skill4 starsChanged 4 months agoMITView on GitHub

Stage 2 of the I-Framework. Diverge into many candidate solutions to the captured intent (fanning out across subagents for independent angles), then converge to 1-3 bets with a demand hypothesis, and write Product/ideation.md. Use after /intent.

36 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-arxiv, exp-eval and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • skyllwtSkill

    exp-pilot-eval

    Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.

    Also in 4 projects that use this

  • skyllwtSkill

    exp-pilot-run

    Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.

    Also in 4 projects that use this

  • phanghonghaoSkill

    poster

    HTML/CSS A4 海报生成。从沙龙/活动 Markdown 文件生成科技风 A4 海报 PDF/PNG。Use when user mentions: poster, 海报, 海报生成, make poster, generate poster, 活动海报, 沙龙海报.

    Also in 4 projects that use this

  • +6 more from Lambenthan
  • +1 more from skyllwt

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read Product/intent.md. If it's missing, suggest /intent first.

    line 14
  2. Very specific:

    Use the structure from the plugin's templates/ideation.md: the full option space (keep the killed ones and why), the chosen bet(s) and …

    line 36

“Common” is measured: kept by at least 6 in 10 of the 33 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/ideate — Stage 2: diverge, then converge

You retire solution & demand risk. First go wide (escape the first-idea trap), then narrow to a small number of bets with an explicit, testable demand hypothesis.

Procedure

1. Load context & check the gate (soft)

Read Product/intent.md. If it's missing, suggest /intent first. If its gate: open, warn that you're ideating on an unvalidated problem but proceed if the founder wants.

2. Diverge — fan out for breadth

Spawn a handful of subagents in parallel via the Task tool, each with a different lens, so the option space isn't anchored on one mindset. Suggested lenses (pick 4–6):

  • Cheapest MVP — the scrappiest thing that could work.
  • 10x technology — what becomes possible with the best available tech.
  • Different business model — subscription, marketplace, services, usage-based, free+data.
  • Adjacent analog — how an unrelated industry solved a structurally similar problem.
  • Do-it-for-them — a concierge/service version before any product.
  • Platform / ecosystem — enabling others to solve it.

Give each subagent the intent (problem, user, status quo) and ask for a short list of distinct candidate solutions with a one-line description each. Then dedupe and cluster the returned candidates yourself.

If the bet is tightly scoped or the user prefers, skip the fan-out and brainstorm a single broad pass inline.

3. Converge — score and narrow

Score each candidate on desirability (fit-to-intent / demand signal), feasibility, and differentiation potential (H/M/L). Narrow to 1–3 bets. Interview the founder to confirm the choice — their conviction and constraints matter as much as the scores.

4. Demand hypothesis & cheapest test

For the chosen bet(s), force a falsifiable demand hypothesis ("We believe <persona> will <behavior> because <reason>") and the smallest experiment that would confirm or kill it before building.

5. Write Product/ideation.md

Use the structure from the plugin's templates/ideation.md: the full option space (keep the killed ones and why), the chosen bet(s) and rationale, the demand hypothesis, and the cheapest test.

6. Gate & hand off

Set gate: passed when there's a chosen bet, a demand hypothesis, and a cheapest-test plan. Point to /innovate next.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free