agentleFS
rikilamadridrikilamadrid/pathfinder/skills/teach-architecture/SKILL.md

teach-architecture

Skill1 starsChanged 44 days agoMITView on GitHub

Explain how one or more completed features fit into the wider application and system architecture.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the learner understands an individual feature and needs to zoom out.

    line 9
  2. Distinctive:

    Do not infer services or infrastructure that do not exist.

    line 23
  3. Distinctive:

    Create or update a scoped lesson under:

    line 46
  4. Distinctive:

    Use labels such as:

    line 67
  5. Distinctive:

    Do not present a future target diagram as current reality.

    line 74
  6. Distinctive:

    Do not refactor code.

    line 78
  7. Distinctive:

    Do not introduce microservices, microfrontends, queues, or real-time infrastructure merely to make the diagram impressive.

    line 79
  8. Distinctive:

    Prefer the simplest architecture that satisfies current requirements.

    line 80

≈ “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

Teach Architecture

Use this skill when the learner understands an individual feature and needs to zoom out.

The goal is to connect implementation details to system boundaries, ownership, scaling, and team architecture.

Read First

  1. context/project-overview.md
  2. Relevant completed feature specs and lessons
  3. Architecture-relevant source files only
  4. Data contracts, API boundaries, stores, routing, and deployment configuration relevant to the requested scope
  5. Existing ADRs, if present

Skip any of these that does not exist. Pathfinder creates these files only when a workflow first needs them, so their absence is normal and is not an error. Do not create them just to satisfy this list.

Do not infer services or infrastructure that do not exist. Clearly distinguish current architecture from likely future architecture.

Teach These Layers

Select only the relevant layers:

  • Product surfaces and user journeys
  • Component and design-system boundaries
  • Feature/module boundaries
  • Client state versus server state
  • Data fetching and cache lifecycle
  • API and backend contracts
  • Persistence
  • Authentication and authorization
  • Event and real-time flows
  • Observability and failure handling
  • Testing pyramid and contract boundaries
  • Build, deployment, and runtime boundaries
  • Team ownership and package boundaries
  • Performance and scale limits

Required Output

Create or update a scoped lesson under:

context/learning/lessons/YYYY-MM-DD-architecture-[scope].md

Include:

  1. Current architecture
  2. A Mermaid container or flow diagram
  3. Dependency direction
  4. State and data ownership
  5. Important invariants
  6. Failure paths
  7. Scaling pressure points
  8. Credible alternative architecture
  9. Why the current level of complexity is or is not appropriate
  10. Senior interview questions and answer outlines

Architecture Honesty

Use labels such as:

  • implemented
  • mocked
  • planned
  • recommended later

Do not present a future target diagram as current reality.

Scope

  • Do not refactor code.
  • Do not introduce microservices, microfrontends, queues, or real-time infrastructure merely to make the diagram impressive.
  • Prefer the simplest architecture that satisfies current requirements.

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.