agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/goose-agent-orchestration/SKILL.md

goose-agent-orchestration

Skill2 starsChanged 33 days agoMITView on GitHub

Designs agent orchestration and tool-routing procedures inspired by extensible agent runtimes

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Prefer NorthStar launcher surfaces (northstar skills|review|evaluate|…) over ad-hoc agent frameworks.

    line 29
  2. Distinctive:

    If inspired by an external runtime pattern, capture it as a Skill/procedure draft — never as a live dependency install from the Star.

    line 35
  3. Distinctive:

    Do not clone, npm-install, or execute Goose (or similar) from TI/learning paths

    line 47
  4. Very specific:

    Do not bypass IMPLEMENTATION_PLAN.md approval for product changes

    line 48
  5. Distinctive:

    Do not grant agents authority to self-approve promotions

    line 49

≈ “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

Goose Agent Orchestration

Use this Skill when

Designing multi-step agent workflows, tool routing, or runtime boundaries for NorthStar agents — without installing third-party agent frameworks into the control plane.

Origin

  • Starred discovery: aaif-goose/goose
  • Candidate: github-stars-aaif-goose-goose
  • Lifecycle: AVAILABLE_SKILL (Captain-promoted Wave 1 / OVA-71)
  • Metadata/procedure only — do not clone or execute the starred repo

Inputs

  • Objective / task graph or capability plan
  • Available Skills and agent profiles
  • Evidence expectations for the workstream

Procedure

  1. Prefer NorthStar launcher surfaces (northstar skills|review|evaluate|…) over ad-hoc agent frameworks.
  2. Map the objective to Skills + agents via capability planning / experience routing; keep Captain approval gates intact.
  3. Define clear tool boundaries: what runs in control vs product/sandbox.
  4. Require evidence paths for mutating steps; fail closed on missing gates.
  5. If inspired by an external runtime pattern, capture it as a Skill/procedure draft — never as a live dependency install from the Star.
  6. Record Experiences with skills_used including this slug when the pattern is applied successfully.

Output

  • Task/agent routing notes or capability-plan sections
  • Optional Skill improvement proposal for related orchestration Skills

Prohibited actions

  • Do not clone, npm-install, or execute Goose (or similar) from TI/learning paths
  • Do not bypass IMPLEMENTATION_PLAN.md approval for product changes
  • Do not grant agents authority to self-approve promotions

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