ecosystem-bd
Skill2 starsChanged 20 days agoMITView on GitHub
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".
In this repository11 other files it gives its agents.
- build-statusSkill
- fundraisingSkill
- hackathonSkill
- idea-sprintSkill
- incident-commsSkill
- launchSkill
- market-sizingSkill
- pitch-deckSkill
- pitch-reviewSkill
- positioningSkill
- pricingSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Every row is dated 2026-10-05 and links its official source.
- Distinctive: line 57
No surface in the map is won by a pitch alone.
- Distinctive: line 59
No invented thresholds. Where an operator publishes none (Jupiter verification, DexScreener, Solflare beyond its 24h minimum age), say …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
- 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. - 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.mdas blockers. Do not draft an ask for a surface whose artifacts are missing. - 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.
- 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.
- 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.
- 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.
- Co-announcements go through launch. The onchain step gates them like any launch.
- 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.
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
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.

