agentleFS
iuryszaiurysza/agent-skills/skills/type-breakdown/SKILL.md

type-breakdown

Skill5 starsChanged 11 days agoMITView on GitHub

Maps a code path's types, abstractions, data flow, side effects, and errors. Use only when the user explicitly asks for a type breakdown of a feature, flow, or code path.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the subject is simple, keep the walkthrough concise.

    line 16
  2. Distinctive:

    Start from the entry point and expand the call path recursively in execution order.

    line 29
  3. Very specific:

    Use × N for repeated calls over collections.

    line 63
  4. Distinctive:

    Prefer domain-specific types over primitive strings and numbers when they encode identity, validation, units, or invariants.

    line 97
  5. Distinctive:

    Keep the output concrete, source-aware, and directly reviewable as an implementation plan.

    line 120

≈ “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

Type Breakdown

Walk the user through the requested code paths, types, abstractions, and data flow.

Turn a broad plan into a concrete, type-driven implementation outline. Prefer pseudocode, type signatures, and execution structure over PRD-style prose.

Inspect the existing code before proposing new abstractions.

If the subject is simple, keep the walkthrough concise. Otherwise, use the structure below as a reference. Do not follow it rigidly when a section does not apply.

Use these markers:

[existing]  Confirmed in the codebase
[inferred]  Implied by the current implementation
[proposed]  Introduced by this plan
[?]         Unresolved

Execution Tree

Start from the entry point and expand the call path recursively in execution order.

For every relevant call, show:

  • Fully qualified function, method, class, or module name
  • File where it is defined
  • Parent file and call site
  • Responsibility
  • Input and output types
  • Data transformations
  • Side effects
  • Possible errors
  • Child calls

Use this format:

▼ [existing] CheckoutController.create
  defined: src/checkout/api/CheckoutController.ts:24
  input:   CreateCheckoutRequest
  output:  Promise<HttpResponse<CreateCheckoutResponse>>

  └─▶ [existing] CreateCheckout.execute
      defined: src/checkout/application/CreateCheckout.ts:18
      called:  CheckoutController.ts:42
      input:   CreateCheckoutCommand
      output:  Result<Checkout, CreateCheckoutError>
      effects: reads customer, writes checkout

      ├─▶ CustomerRepository.find
      ├─▶ Checkout.create
      └─▶ CheckoutRepository.save

Use × N for repeated calls over collections. Do not invent line numbers when they are unavailable.

Type Flow

Show how data becomes progressively more constrained:

unknown
  → CreateCheckoutRequest
  → CreateCheckoutCommand
  → ResolvedCheckoutInput
  → Checkout
  → CheckoutRow
  → CreateCheckoutResponse

Identify the validation or transformation responsible for each transition.

Type Definitions

Provide pseudocode definitions for the important boundary, application, domain, persistence, state, and error types.

type CreateCheckoutCommand = {
  customerId: CustomerId;
  items: NonEmptyArray<CheckoutItemInput>;
};

type CreateCheckoutError =
  | { type: "CustomerNotFound"; customerId: CustomerId }
  | { type: "InvalidCheckout"; cause: CheckoutValidationError }
  | { type: "PersistenceFailure"; cause: PersistenceError };

Prefer domain-specific types over primitive strings and numbers when they encode identity, validation, units, or invariants.

Error Flow

Show where each error originates and how it is mapped and propagated:

UniqueConstraintViolation
  → PersistenceError.Conflict
  → CreateCheckoutError.PersistenceFailure
  → HTTP 409

Implementation Outline

Finish with:

  1. Proposed functions and type signatures
  2. Type ownership by file or module
  3. Existing code that must change
  4. New files or abstractions required
  5. Unresolved design questions

Keep the output concrete, source-aware, and directly reviewable as an implementation plan.

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.