agentleFS
YunghoYungho/family-doctor/integration-strategy/SKILL.md

integration-strategy

Skill2 starsChanged 8 months agoMITView on GitHub

Blueprint for integrating new skills into Family Doctor. Use when adding a new skill, modifying routing rules, or planning how skills connect to the orchestrator. Triggers on \"add new skill\", \"integrate\", \"routing\", \"how do skills connect\".

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

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

    Update family-doctor/SKILL.md routing table with:

    line 49
  2. Distinctive:

    All external skills must support:

    line 77
  3. Distinctive:

    Verify skill file loads correctly

    line 125
  4. Very specific:

    Test routing from family-doctor entry point

    line 126
  5. Very specific:

    Verify citation output to health/References/

    line 128
  6. Distinctive:

    Check data contract compliance

    line 129

≈ “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

Integration Strategy

Blueprint for integrating new skills into the Family Doctor suite.

When to Use

  • Adding a new skill to the family-doctor ecosystem
  • Modifying how skills connect to the orchestrator
  • Planning routing rules for new capabilities
  • Designing data contracts between skills

Skill Types in Family Doctor

TypeExamplesRouting
Orchestratorfamily-doctorEntry point, routes to others
Clinicalchronic-care, vital-monitorHealth domain skills
Lifestylenutrition-advisor, fitness-coachBehavioral skills
Mental Healthmental-healthPsychological skills
General-Corepubmed-search, general-browser-searchExternal knowledge
Supportcare-coordinator, emergency-preparednessCoordination skills

Integration Checklist

1. Create Skill File

Create family-doctor/[skill-name]/SKILL.md:

---
name: [skill-name]
description: One-line description. Triggers on keywords.
allowed-tools: [tool1, tool2]
---

# [Skill Name]

... detailed instructions ...

2. Add to Routing Table

Update family-doctor/SKILL.md routing table with:

  • Entry trigger pattern (regex or keywords)
  • Parent skill (usually "family-doctor")
  • Output contract format

3. Define Data Contracts

Input Contract

{
  "query": "string",
  "context": "object",
  "preferences": "object"
}

Output Contract

{
  "query": "string",
  "results": [],
  "confidence": 0.0-1.0,
  "authorization": "session-wide|per-query|none"
}

4. Configure Authorization

All external skills must support:

ModeBehavior
session-wideUser consented once for all queries this session
per-queryUser approves each query individually
noneNo external access (default)

5. Define Reference Schema

For health data:

{
  "id": "uuid",
  "topic": "string",
  "query": "string",
  "date": "YYYY-MM-DD",
  "sources": ["source names"],
  "summary": "string"
}

Store at: health/References/

Routing Priority

Lower number = checked first:

SkillPriorityReason
family-doctor0Entry point
general-browser-search10External guidelines
pubmed-search20Literature
clinical skills30Domain-specific
lifestyle skills40Behavioral
support skills50Coordination

Conflicts to Avoid

New SkillDon't Overlap With
general-browser-searchpubmed-search (different sources)
pubmed-searchgeneral-browser-search
clinical skillsEach other in same domain

Testing Integration

  1. Verify skill file loads correctly
  2. Test routing from family-doctor entry point
  3. Test authorization flow
  4. Verify citation output to health/References/
  5. Check data contract compliance

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.