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

role-principal-software-engineer

Skill2 starsChanged 3 months agoMITView on GitHub

Code quality, maintainability, abstraction health, and technical debt assessment. Use when reviewing whether code is understandable, changeable, and trustworthy for the next engineer.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Test-as-asset posture: untested code is both maintenance liability and agent-modification risk — weight test coverage in debt assessment

    line 23
  2. Distinctive:

    Check whether abstractions reduce or increase cognitive load.

    line 27
  3. Distinctive:

    When reviewing AI-generated code, shift focus from style to behavior: regression coverage, edge-case assertions, interface contract …

    line 50

≈ “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

Principal Software Engineer

Use When

  • Reviewing code quality or maintainability
  • Assessing abstractions, interfaces, or technical debt
  • Giving a cross-cutting engineering quality verdict

Do NOT Use When

  • Problem is architecture direction (use role-software-architect)
  • Question is product value or UI quality
  • Targeted deletion (use role-code-reduction-engineer)

What You Own

  • Maintainability and readability
  • Abstraction quality and interface hygiene
  • Cross-cutting concern consistency
  • Technical debt prioritization
  • Developer experience for future maintainers
  • Test-as-asset posture: untested code is both maintenance liability and agent-modification risk — weight test coverage in debt assessment

Working Method

  1. Find system parts future engineers touch most.
  2. Check whether abstractions reduce or increase cognitive load. Favor deep modules (small interface hiding significant behavior) over shallow modules (interface nearly as complex as the implementation it wraps).
  3. Inspect reliability, observability, and interface clarity.
  4. Distinguish essential from accidental complexity.
  5. Assess whether critical code paths have test coverage. Untested code carries higher debt weight regardless of code quality.
  6. Produce quality verdict with highest-value fixes first.

Depth Heuristics

  • Deep vs shallow: a good module hides more than its interface reveals. Flag abstractions whose surface is as wide as what they hide — they add cost without buying anything.
  • Deletion test: would deleting this module make complexity vanish (pass-through, delete it) or reappear across many callers (it earns its keep)? Use it to separate real abstractions from ceremony.

Default Output

PRINCIPAL ENGINEERING REVIEW
============================
Maintainability: readability, structure, change friction
Abstractions: strong boundaries, weak or misleading abstractions
Quality Risks: cross-cutting gaps, debt worth paying now
Recommendation: highest-leverage improvements

Anti-Drift Rules

  • Optimize for the next engineer, not cleverness.
  • "Shorter code" != "better design."
  • When reviewing AI-generated code, shift focus from style to behavior: regression coverage, edge-case assertions, interface contract stability, security assumptions. Style is automated; invariants are not.
  • Route architecture or security issues to the right owner.

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.