| name | lobu-builder |
| description | Use when working inside a Lobu project generated by @lobu/cli or any repository centered on lobu.toml, AGENTS.md, agent prompt files, local skills, and evals. This skill helps a coding agent inspect the right files, make Lobu-native changes, keep the stack runnable, and validate behavior with chat tests and evals. |
Lobu Builder
Overview
Use this skill when the repository is a Lobu project and the task is to build or change the agent itself: prompt files, lobu.toml, local skills, MCP configuration, connections, network settings, or evals.
If you are inside the Lobu monorepo rather than a generated Lobu project, follow that repository's own instructions first.
First Pass
- Read
AGENTS.md first. If it redirects to another file such as @TESTING.md, open that too.
- Read
lobu.toml.
- Enumerate agent directories under
agents/ and inspect the target agent's IDENTITY.md, SOUL.md, and USER.md.
- Check whether the repo has shared
skills/ or agent-local agents/<id>/skills/.
- Look for evals under
agents/<id>/evals/.
Do not assume there is only one agent or one platform connection.
What To Edit
IDENTITY.md: who the agent isSOUL.md: rules, workflows, guardrailsUSER.md: user or tenant contextlobu.toml: providers, connections, enabled skills, MCP servers, network allowlistskills/.../SKILL.md: shared reusable capabilitiesagents/<id>/skills/.../SKILL.md: agent-specific capabilitiesagents/<id>/evals/*.yaml: regression tests for behavior
Prefer editing these files directly instead of burying behavior in ad hoc code.
Workflow
- Keep the project runnable. Start or reuse the stack with
npx @lobu/cli@latest run -d.
- Make the smallest prompt, config, skill, or eval change that solves the task.
- Run
npx @lobu/cli@latest validate after changing lobu.toml or skill definitions.
- Test behavior with
npx @lobu/cli@latest chat "..." or the project's testing instructions.
- Run
npx @lobu/cli@latest eval when the behavior should be captured as a regression test.
If the repository already provides project-specific test scripts, use those.
Skills And MCP
- Prefer Lobu skills for reusable capabilities.
- For external data, prefer a small MCP surface over custom glue code.
- For MVP work, start with one MCP server and one skill.
- If per-user access matters, prefer MCP OAuth device authorization and let the gateway proxy handle authentication.
- Keep network access narrow; only add the domains the agent actually needs.
Useful Suggestions
- Add or reorder providers in
lobu.toml
- Enable built-in skills with
npx @lobu/cli@latest skills list, search, or add
- Add a custom MCP server under
[agents.<id>.skills.mcp.*]
- Add a shared skill under
skills/ for repeated workflows
- Add evals for risky behaviors and policy constraints
- Wire observability only when needed; Lobu supports Grafana/Tempo traces
References
