sendaifun/solana-new/validate-idea
Claude Code and agent skill by sendaifun/solana-new
- community
Checking that the SKILL.md file is still in the repository.
Run a structured validation sprint on a crypto startup idea. Use when a user says "validate this idea", "is this worth building", "run a validation sprint", "help me test demand", or "should I build this". Reads idea-context.md from a prior idea phase if available.
Install
npx vskill@latest install sendaifun/solana-new/validate-ideaSKILL.md
Preamble (run first)
If TEL_PROMPTED is no: Before starting the skill workflow, ask the user about telemetry. Use AskUserQuestion:
Help superstack get better! We track which skills get used and how long they take —no code, no file paths, no PII. Change anytime in~/.superstack/config.json.
Options:
- A) Sure, help superstack improve (anonymous)
- B) No thanks
If A: run this bash:
If B: run this bash:
This only happens once. If TEL_PROMPTED is yes, skip this entirely and proceed to the skill workflow.
Wrong skill? See SKILL_ROUTER.md for all available skills.
Validate Idea
Overview
Take an idea (from a prior find-next-crypto-idea session or fresh from the user) and stress-test it with a structured validation sprint. Produce a go/no-go recommendation backed by demand signals, risk analysis, and a concrete next-steps plan.
Workflow
- Check for
.superstack/idea-context.mdin the workspace. If found, load the chosen idea. If not, ask the user to describe their idea. - Read references/validation-framework.md for the sprint structure.
- Evaluate demand signals using references/customer-signal-rubric.md.
- Run the crypto necessity gut-check: "What breaks if you remove the blockchain?"
- Map risks: technical, market, regulatory, team.
- Apply references/pivot-or-persist.md to reach a go/no-go decision.
- Write a local HTML artifact with the validation report.
Non-Negotiables
- Do not rubber-stamp. If the idea is weak, say so with specifics.
- Every "go" recommendation must cite at least 2 concrete demand signals (not vibes).
- Every "no-go" must include a pivot suggestion, not just rejection.
- If the user has no evidence of demand, the answer is "go validate" with a specific sprint plan, not "go build".
- Always check if there is already a live product doing the same thing on Solana.
- Always write a local HTML artifact. Do not leave results only in chat.
- Integration-first assessment: As part of validation, identify whether the idea can be built by integrating existing Solana protocols rather than writing a custom program. If integration is viable, note it as an advantage (faster to ship, lower audit costs). If the idea requires novel on-chain logic or the user is building the protocol layer itself, custom development is the right call — don't penalize it. Include the integration-vs-build assessment in next_steps. See
data/solana-knowledge/04-protocols-and-sdks.md→ "Integrate First, Build Second".
Phase Handoff
This skill is Phase 1 (Idea) in the Idea → Build → Launch journey. After completing validation:
- Write/update
.superstack/idea-context.md(create if missing) with avalidationfield containing:
demand_signals: array of evidence itemsrisks: array of { category, description, severity }go_no_go: "go" | "no-go" | "pivot"confidence: 0.0 - 1.0next_steps: array of concrete actions
- Tell the user they can proceed to the Build phase if the verdict is "go".
- See
../../../data/specs/phase-handoff.mdfor the full JSON contract.
Quick Start
Decision Points
- No idea yet? Redirect to
find-next-crypto-ideafirst. - Which RPC for testing demand? Use Helius free tier for any on-chain research.
- Go vs. no-go threshold: Score ≥ 8/15 across founder-fit + MVP-speed + distribution + market-pull + revenue = Go. Below 6 = strong No-go.
- Hackathon precedents? If the user wants to check whether similar ideas have been tried in Solana hackathons (and what won/lost), suggest
/colosseum-copilot. Requires a free PAT — only mention if the user asks or opts in.
Resources
references/
- references/validation-framework.md
- references/customer-signal-rubric.md
- references/pivot-or-persist.md
Telemetry (run last)
After the skill workflow completes (success, error, or abort), log the telemetry event. Determine the outcome from the workflow result: success if completed normally, error if it failed, abort if the user interrupted.
Run this bash:
Replace OUTCOME with success/error/abort based on the workflow result.
Security
- Security scanPassed, 96 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/idea/validate-idea/SKILL.md
Popularity
- Repository stars
- 165
- Repository forks
- 46
- 7-day trend score
- 26
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 11 Aug 2026, 2 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/sendaifun/solana-new/validate-idea)