agentleFS
Sign inStart free
RoyoTechRoyoTech/royo-learn/skills/royo-learn-onboarding/SKILL.md

royo-learn-onboarding

Skill7 starsChanged 4 months agoMITView on GitHub

Initialize and verify royo-learn for a project, optionally install its integrations, then continue with capture-learning.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the marker is absent, run royo-learn init --project-root <root> exactly once for that project root.

    line 21
  2. Very specific:

    Run royo-learn doctor --project-root <root> --json and resolve any reported failure before capturing a learning.

    line 22

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Royo Learn Onboarding

Use when

  • royo-learn is being used in a project for the first time;
  • an MCP call returns project_not_found;
  • the project marker or setup state is uncertain.

Workflow

  1. Identify the intended project root and check for <root>/.royo-learn/config.yaml.
  2. If the marker is absent, run royo-learn init --project-root <root> exactly once for that project root. Initialization is required; setup install is not a substitute.
  3. Run royo-learn doctor --project-root <root> --json and resolve any reported failure before capturing a learning.
  4. Optionally run royo-learn setup install --agent all --project-root <root> to register MCP and install skills for Claude Code, Codex, and OpenCode. This step is optional after initialization and is safe to repeat.
  5. Load and follow ../capture-learning/SKILL.md for capture eligibility, evidence, and output rules.

Clarifications

  • Initialize one store per project root, not one per working directory. Project discovery walks upward from a subfolder until it finds .royo-learn/config.yaml.
  • Re-running init for the same root is idempotent; do not initialize every subfolder.
  • setup install configures supported agents and installs every valid directory under <root>/skills/; it does not create the project store.
  • The royo-learn project store and Engram memory are separate, independent stores. Initializing, reading, or writing one does not initialize, synchronize, or replace the other.

Outcome

Return the project root, marker status, doctor result, whether optional setup ran, and whether control passed to capture-learning.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free