Superteam Brasil · Official Skill Startup Builder

ecosystem-bd

Get a Solana product listed, routed and integrated by others (Jupiter, wallets, explorers, DefiLlama, Superteam, Foundation): a dated map of what each surface requires, readiness gaps, two-way diligence and the partner ask. Use for "get listed on Jupiter", "partnerships", "integration BD".

Open .md

Just this skill, with its reference files, at the pinned commit:

$ mkdir -p .claude/skills/ecosystem-bd && curl -fsSL https://codeload.github.com/solanabr/startup-builder-skill/tar.gz/a738bc8f54fcc39d40647ca791a5af375025c72d | tar -xz -C .claude/skills/ecosystem-bd --strip-components=3 startup-builder-skill-a738bc8f54fcc39d40647ca791a5af375025c72d/skills/ecosystem-bd

Or the whole set. The skills link to each other's format files, so the set works best together:

$ npx skills add solanabr/startup-builder-skill

No install: tell your agent

Read https://kit.superteam.codes/s/startup-builder-skill/skills/ecosystem-bd/SKILL.md and follow it for this task:

SKILL.md

Open .md

Ecosystem BD

On Solana, being integrated by someone else is usually a bigger distribution channel than anything a small team does alone. Almost every surface asks for a technical artifact or an onchain fact before it says yes, so this skill starts from what each one requires and treats outreach as the last step.

Context handoff

At start, read .claude/context/idea.md, build.md, positioning.md and launch.md if present: the product, what is deployed, the one-liner and any launch date. If .claude/context/partners.md exists, resume the pipeline instead of starting over.

Writes .claude/context/partners.md in the format at the end of partner-map.md.

Workflow

  1. Pick target surfaces from surfaces.md: aggregators and routers, wallets, explorers and analytics, DeFi dashboards, Superteam, the Foundation. Every row is dated 2026-10-05 and links its official source. Re-open the source before acting, and update the date in partners.md. Skip rows marked unverified unless the user has a current source.
  2. Readiness first. For each target, check the artifacts it asks for with readiness.md: published IDL, verifiable build, audit naming the deployed commit, typed client, token metadata, an onchain TVL or fees computation. Missing ones go to solanabr/ai-kit as engineering work and into partners.md as blockers. Do not draft an ask for a surface whose artifacts are missing.
  3. File the self-serve surfaces. Forms and PRs (Jupiter verification, the platform list, DefiLlama adapters, Solscan’s one-shot token form, Dune decoding) are done exactly as their docs say. Many can only be filed after the program, mint or pool exists; put those in the launch runbook’s L+ window if a launch is planned.
  4. Map the partners with partner-map.md: size candidates from DefiLlama, read fees against TVL, choose a depth (listed, integrated, strategic), and consider sponsoring an Earn bounty or hackathon track.
  5. Diligence both ways with diligence.md. Inbound (should we depend on them?) goes to counterparty-gate. Outbound (what they take on by depending on you: upgrade authority, admin keys, pause powers, support load) is written here before the first call.
  6. Write the ask from ask.md: the integration artifact and the volume number first, the smallest next step as the ask, the leverage stated honestly. A yes becomes a signed one-page charter with exit criteria.
  7. Co-announcements go through launch. The onchain step gates them like any launch.
  8. Write partners.md: readiness, pipeline with owner and next date, charters.

Rules

  • No surface in the map is won by a pitch alone. If readiness fails, the next step is engineering, and the skill says so.
  • No invented thresholds. Where an operator publishes none (Jupiter verification, DexScreener, Solflare beyond its 24h minimum age), say that, and do not supply a number.
  • Revenue shares, token allocations to partners, exclusivity and anything contractual or regulatory go to crypto-legal-skill. Say so and stop.
Solana AI Kit v2.4.0

One install for the whole kit

Superteam Brasil builds these skills as part of the Solana AI Kit, its open-source Claude Code and Codex kit for Solana. 15 specialist agents, 32 commands, 4 MCP servers and 46 skill packs, behind a firewall that keeps agents away from wallet keypairs.

Specialist agents
15
Commands
32
Skill packs
46
MCP servers
4
$ curl -fsSL https://aikit.superteam.codes | bash