LumenLoop Stellar Skills
lumenloop/lumenloop-skills
Skills para pesquisar e construir no ecossistema Stellar via MCP
Ver no GitHubConjunto de playbooks pré-configurados que capacita assistentes de IA com 18 ferramentas de pesquisa e desenvolvimento no ecossistema Stellar. Conecta-se ao MCP público e read-only do LumenLoop para análise de projetos, submissões de funding e integrações sem necessidade de escrita de dados.
Instalação
npx convez-ai lumenloop/lumenloop-skills1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Mapear projetos e conteúdo em setores específicos do Stellar
- Fazer due diligence completa de projetos individuais
- Posicionar ideias SCF (Stellar Community Fund) contra submissões anteriores
- Encontrar integrações prontas (wallets, oracles, anchors, DEX) para construir
Veredito

Excelente MCP server para o ecossistema Stellar com oito skills bem definidas e baseadas em dados públicos. Recomendado para builders e pesquisadores que querem acelerar análise de projetos e oportunidades na rede, com instalação simples via Claude Code.
README
A tradução para o português deste README ainda está na fila.
LumenLoop Stellar Skills
Preconfigured playbooks that make any MCP-capable AI assistant useful for
researching and building on the Stellar ecosystem — wired
to LumenLoop's free, read-only ecosystem MCP at https://mcp.lumenloop.com.
LumenLoop indexes the public Stellar ecosystem — projects, Stellar Community Fund
(SCF) submissions, and editorial / news / audio-video content — and exposes it as 18
read-only query tools over the open Model Context Protocol.
Any MCP client can connect (Claude, ChatGPT, Gemini, Cursor, …). This repo adds the
playbooks for using those tools well, plus an .mcp.json that wires the connector.
The skills are packaged as Claude Code Agent Skills for one-command install, but the connector and the recipes inside each skill are model-agnostic — see Using these with other LLMs.
Read-only and public by design. These skills only ever query LumenLoop's public ecosystem data — they never write anything.
What's inside
| Skill | Use it when you want to… |
|---|---|
| lumenloop-mcp-connect | Connect the MCP and learn what each tool does / which skill to use. |
| stellar-ecosystem-scout | Map a sector or topic into a landscape of projects + content. |
| stellar-project-dossier | Build a due-diligence profile of a single project. |
| scf-submission-radar | Position an SCF idea against prior submissions before you apply. |
| stellar-integration-finder | Find the right wallet / oracle / anchor / RWA / DEX to integrate. |
| stellar-ecosystem-digest | Get a dated digest of recent activity on a theme or entity. |
| stellar-builder-quickstart | Go from idea → Stellar primitives → prior art → a build path. |
| stellar-content-auditor | Audit a draft against the ecosystem — fix @handles, add citations, flag bad claims. |
See VISION.md for the design and authoring standard.
Install
A. As a Claude Code plugin (recommended)
/plugin marketplace add lumenloop/lumenloop-skills
/plugin install lumenloop-skills@lumenloop
Installing the plugin enables all eight skills and wires the lumenloop MCP
connector from the bundled .mcp.json. Then connect the server (below).
B. Project-scoped (clone into a repo)
git clone https://github.com/lumenloop/lumenloop-skills.git
Run Claude Code from the clone (or copy .mcp.json + skills/ into your project's
.claude/). Project skills and the MCP server are auto-discovered.
C. Personal skills
git clone https://github.com/lumenloop/lumenloop-skills.git
cp -r lumenloop-skills/skills/* ~/.claude/skills/ # or symlink individual folders
Then add the server to your MCP config once:
claude mcp add --transport http lumenloop https://mcp.lumenloop.com
Connect the server
The skills query the lumenloop MCP server. After install, connect it in your client:
- Claude Code / desktop: the
lumenloopserver appears from.mcp.json(or theclaude mcp addabove). Run/mcp, pick lumenloop, and complete the one-time sign-in. - Claude.ai, ChatGPT, Gemini & other MCP clients: add a custom / remote MCP
connector pointing at
https://mcp.lumenloop.com(transport: streamable HTTP) and sign in once.
Once connected, ask your assistant something like "map the RWA projects on Stellar"
or "vet project <slug> for me" and the matching skill (or playbook) takes over. In
Claude Code you can also invoke one directly, e.g.
/stellar-ecosystem-scout real-world assets.
Using these with other LLMs
The /plugin install is Claude Code-specific, but nothing else here is:
- Connect the MCP at
https://mcp.lumenloop.comfrom any MCP-capable client (Claude, ChatGPT, Gemini, Cursor, or your own agent). The 18 tools work the same everywhere. - Use the skill files as playbooks. Each
skills/<name>/SKILL.mdis plain markdown describing exactly which tools to call, in what order, with which parameters. Paste one in as a system prompt / instructions, or hand it to your agent as a reference — the recipes are model-agnostic MCP tool-call sequences.
Develop / contribute
node scripts/validate_skills.mjs # validate all skills + manifests
node scripts/validate_skills.mjs skills/stellar-ecosystem-scout # one skill
claude plugin validate . # Anthropic manifest validation
The validator enforces the authoring contract in VISION.md, including the rule
that skills may reference only the 18 public read tools. New skills are added
one validated folder at a time.
License
MIT — see LICENSE. Stellar ecosystem data is served by LumenLoop and
remains subject to its source terms.