agentleFS
Sign inStart free
TheAstroByteTheAstroByte/astrobyte-agent-skills/skills/astrobyte-architect/SKILL.md

astrobyte-architect

Skill1 starsChanged 14 days agoMITView on GitHub

Settle data shapes, state transitions, public interfaces, module ownership, and test seams before non-trivial implementation. Use for architecture, API boundaries, new subsystems, shared state, cross-stack features, or designs where early code could lock in the wrong structure.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Read the current callers, contracts, data models, and repository conventions.

    line 10
  2. Distinctive:

    Write the primary usage from the caller's point of view.

    line 11

≈ “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

Astrobyte architect

  1. Read the current callers, contracts, data models, and repository conventions.
  2. Write the primary usage from the caller's point of view.
  3. Name the domain objects, identifiers, states, invariants, and transitions.
  4. Mark trust boundaries and ownership of persistence, concurrency, retries, and errors.
  5. Sketch the smallest public signatures and module tree that support the usage.
  6. Identify a test seam for each risky behavior.
  7. Compare a second design when the decision is novel, expensive to reverse, or based on an unproven abstraction.
  8. Select the design with the narrowest stable interface and clearest ownership.

Produce:

  • example caller usage
  • types or schemas
  • public signatures
  • module ownership map
  • invariants and error contract
  • test seams
  • rejected alternative with one-line reason

Architecture is complete when implementation can proceed without inventing a second source of truth or an unresolved ownership boundary.

For detailed module vocabulary, use codebase-design. For public HTTP or GraphQL contracts, also use api-and-interface-design. If that conditional specialist is unavailable, report the missing capability and request its installation before applying that branch. Other architecture tasks do not need it.

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