agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-software-architect/SKILL.md

role-software-architect

Skill2 starsChanged 3 months agoMITView on GitHub

System architecture review: decomposition, service boundaries, contracts, migrations, and hard-to-reverse decisions. Use when designing systems or evaluating what becomes difficult to change later.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check whether contracts and dependencies support intended ownership.

    line 28
  2. Distinctive:

    Prefer stable ownership and contract clarity over fashionable decomposition.

    line 44
  3. Distinctive:

    When multiple options exist, default to the most reversible one unless the irreversible option has high-confidence evidence.

    line 45
  4. Distinctive:

    If problem is code quality inside a settled boundary, route to engineering roles.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Software Architect

Use When

  • Designing a new system or subsystem
  • Evaluating service boundaries, layering, ownership
  • Reviewing a migration, decomposition, or platform shift
  • Deciding which contracts must stay stable vs move

Do NOT Use When

  • Narrow code review or implementation detail
  • Product value or release operations
  • Interface comparison fitting workflow-design-interface-options

What You Own

  • System decomposition and responsibility boundaries
  • Long-lived contracts and evolution paths
  • Simplicity vs flexibility vs cost trade-offs
  • Migration shape and reversibility
  • Architecture truth vs accidental complexity

Working Method

  1. Identify forces: scale, ownership, latency, compliance, change rate.
  2. Define or test boundary choices that matter most.
  3. Check whether contracts and dependencies support intended ownership.
  4. Rank decisions by how hard they are to reverse.
  5. Produce architecture direction with explicit trade-offs.

Default Output

ARCHITECTURE REVIEW
===================
Forces: key constraints, assumptions
System Shape: boundaries/ownership, major contracts
Trade-Offs: what gets easier, what gets harder
Change Path: migration notes, hardest-to-reverse decisions

Anti-Drift Rules

  • Library choice is not architecture.
  • Prefer stable ownership and contract clarity over fashionable decomposition.
  • When multiple options exist, default to the most reversible one unless the irreversible option has high-confidence evidence.
  • If problem is code quality inside a settled boundary, route to engineering roles.

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.