idea-sprint
starsforks
How to install idea-sprint?
solanabr/solana-ai-kit/idea-sprint
$npx -y skills add solanabr/solana-ai-kit --skill idea-sprintFind and validate what to build in crypto. Use when the user asks "what should I build", "validate this idea", "is this worth building", "find me a startup idea", "crypto idea", or wants blunt feedback on a project concept before writing code.
SKILL.md
| 1 | <!-- Adapted from sendaifun/solana-new (find-next-crypto-idea, validate-idea), MIT © 2026 SendAI and Superteam. Telemetry removed. --> |
| 2 | |
| 3 | # Idea Sprint |
| 4 | |
| 5 | Interview → necessity gate → 3 candidates → score → go/no-go. Output is a decision, not a brainstorm. |
| 6 | |
| 7 | ## Context handoff |
| 8 | |
| 9 | - At start: read `.claude/context/idea.md` and `.claude/context/build.md` if present — resume from prior state instead of re-interviewing. |
| 10 | - On completion: write/update `.claude/context/idea.md` with the chosen idea, scores, validation evidence, and open risks. Downstream skills (pitch-deck, hackathon) read it. |
| 11 | |
| 12 | ## Workflow |
| 13 | |
| 14 | ### 1. Blunt interview |
| 15 | |
| 16 | No flattery. Short, pointed questions, one at a time, until three things are explicit: |
| 17 | |
| 18 | - **Edge** — what the founder knows/can do that most can't (domain, distribution, tech) |
| 19 | - **Constraint** — time, money, team, chain commitments |
| 20 | - **Wedge** — the niche entry point, not the end-state vision |
| 21 | |
| 22 | Push back on vague answers. "DeFi for everyone" is not a wedge. Full question bank: [interview-framework.md](../ext/solana-new/skills/idea/find-next-crypto-idea/references/interview-framework.md). |
| 23 | |
| 24 | ### 2. Crypto-necessity gate |
| 25 | |
| 26 | Kill question: **"What gets worse if I remove the blockchain?"** If the answer is vague, aesthetic, or marketing-driven — redirect the idea before scoring it. Pass criteria and redirect patterns: [crypto-necessity-test.md](../ext/solana-new/skills/idea/find-next-crypto-idea/references/crypto-necessity-test.md). |
| 27 | |
| 28 | ### 3. Exactly 3 candidates |
| 29 | |
| 30 | Generate three **diverse** candidates (different mechanisms/markets, not three flavors of one idea). For each: |
| 31 | |
| 32 | - One-line pitch + target user |
| 33 | - **Winner case** — what's true in 18 months if it works |
| 34 | - **Bear case** — the most likely way it dies |
| 35 | |
| 36 | Seed from datasets + live landscape (below), then combine with fresh research. Datasets are inspiration, not constraints. |
| 37 | |
| 38 | ### 4. Score /15 |
| 39 | |
| 40 | Each candidate, 0–3 per dimension (full anchors: [scoring-rubric.md](../ext/solana-new/skills/idea/find-next-crypto-idea/references/scoring-rubric.md)): |
| 41 | |
| 42 | | Dimension | 3 means | |
| 43 | |-----------|---------| |
| 44 | | Founder fit | unfair advantage | |
| 45 | | MVP speed | shippable in under a week | |
| 46 | | Distribution | first ten users are obvious | |
| 47 | | Market pull | people already paying for bad alternatives | |
| 48 | | Revenue path | clear monetization story | |
| 49 | |
| 50 | ### 5. Validate + go/no-go |
| 51 | |
| 52 | Check demand signals against [customer-signal-rubric.md](../ext/solana-new/skills/idea/validate-idea/references/customer-signal-rubric.md) — manual workarounds, active forks, bounties, on-chain activity = real; likes and "cool idea" replies = noise. Sprint structure: [validation-framework.md](../ext/solana-new/skills/idea/validate-idea/references/validation-framework.md). |
| 53 | |
| 54 | - **≥ 8/15** → go. Write `idea.md`, suggest `/scaffold` next. |
| 55 | - **6–7** → conditional: name the one dimension to de-risk first. |
| 56 | - **< 6** → strong no-go. **Every no-go gets a pivot suggestion** — use [pivot-or-persist.md](../ext/solana-new/skills/idea/validate-idea/references/pivot-or-persist.md). |
| 57 | |
| 58 | ### 6. Write `.claude/context/idea.md` |
| 59 | |
| 60 | Chosen idea, wedge, scores table, demand evidence, bear case, next step. |
| 61 | |
| 62 | ## Idea datasets (inert JSON, ~515 entries) |
| 63 | |
| 64 | In [../ext/solana-new/skills/data/ideas/](../ext/solana-new/skills/data/ideas/): |
| 65 | |
| 66 | - [web3-ideas-combined.json](../ext/solana-new/skills/data/ideas/web3-ideas-combined.json) — master list ([summary](../ext/solana-new/skills/data/ideas/web3-ideas-summary.json)) |
| 67 | - [a16z-big-ideas-2025.json](../ext/solana-new/skills/data/ideas/a16z-big-ideas-2025.json), [a16z-state-of-crypto-2025.json](../ext/solana-new/skills/data/ideas/a16z-state-of-crypto-2025.json) |
| 68 | - [yc-requests-for-startups.json](../ext/solana-new/skills/data/ideas/yc-requests-for-startups.json), [yc-crypto-companies.json](../ext/solana-new/skills/data/ideas/yc-crypto-companies.json) |
| 69 | - [alliance-ideas.json](../ext/solana-new/skills/data/ideas/alliance-ideas.json), [superteam-ideas.json](../ext/solana-new/skills/data/ideas/superteam-ideas.json) |
| 70 | - [rwa-defi-2026-ideas.json](../ext/solana-new/skills/data/ideas/rwa-defi-2026-ideas.json), [yash-defi-2024-ideas.json](../ext/solana-new/skills/data/ideas/yash-defi-2024-ideas.json) |
| 71 | |
| 72 | Idea-source guides (markdown commentary on the same sources): [../ext/solana-new/skills/data/guides/](../ext/solana-new/skills/data/guides/) — plus [source-map.md](../ext/solana-new/skills/idea/find-next-crypto-idea/references/source-map.md) and [research-playbook.md](../ext/solana-new/skills/idea/find-next-crypto-idea/references/research-playbook.md) for where/how to research live. |
| 73 | |
| 74 | ## Live hackathon landscape |
| 75 | |
| 76 | [ext/colosseum](../ext/colosseum/skills/colosseum-copilot/SKILL.md) — 5,400+ Colosseum submissions for crowdedness |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
