agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/team-dev-team/SKILL.md

team-dev-team

Skill2 starsChanged 3 months agoMITView on GitHub

Technical review team: architecture, code quality, and test coverage in one unified assessment. Use for code review, design review, or implementation validation.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    role-qa-engineer: test coverage, regression risk, verification gaps

    line 14
  2. Distinctive:

    Check what already exists before judging what should change.

    line 28
  3. Distinctive:

    Run specialist passes in parallel.

    line 30
  4. Distinctive:

    Call out what is out of scope and the top failure modes.

    line 32
  5. Distinctive:

    When architecture and code-quality findings conflict, resolve by asking: "What serves the next engineer better?"

    line 53
  6. Distinctive:

    Do not expand into product or economy analysis under technical review label.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Dev Team

Purpose

Single technical verdict on whether implementation is structurally sound, maintainable, and sufficiently verified.

Composition

  • role-software-architect: structure, boundaries, design fit
  • role-principal-software-engineer: code quality, maintainability, tech debt
  • role-qa-engineer: test coverage, regression risk, verification gaps
  • Synthesis: conflict handling, acceptance

Use When

  • Reviewing a pull request, module, or implementation slice
  • Validating a refactor or design before merge
  • Checking code quality and verification match intended architecture

Do NOT Use When

  • Adversarial security review (use team-red-team)
  • Product, UX, or economy analysis
  • Reduction verification (use team-blue-team)

Workflow

  1. Check what already exists before judging what should change.
  2. Review structure, code quality, and test posture together.
  3. Run specialist passes in parallel. QA pass includes AI test quality checks (redundancy, assertion strength, isolation) on any test suite under review.
  4. Merge findings: test gaps map to risky code, risky code maps to architecture.
  5. Call out what is out of scope and the top failure modes.
  6. Resolve conflicts, produce one technical verdict.

Default Output

DEV TEAM REVIEW
===============
Current State: relevant existing code paths, boundaries, reuse opportunities
Architecture: boundary/design concerns
Code Quality: maintainability findings, debt/complexity risks
Verification: test gaps, regression risks
Failure Modes: top breakages to watch, what is not in scope
Recommendation: merge / rework / escalate, highest-priority fixes

Success Criteria

  • Architecture, code quality, and verification connected rather than siloed.
  • Output states what blocks acceptance vs what is advisory.

Conflict Resolution

  • Architect owns structural decisions. Principal Engineer owns code-quality assessment. QA owns verification gaps.
  • When architecture and code-quality findings conflict, resolve by asking: "What serves the next engineer better?"

Anti-Drift Rules

  • Stay constructive, not adversarial (that's Red Team's job).
  • Name what already exists before recommending new structure.
  • Output must state what blocks acceptance vs what is advisory.
  • Do not expand into product or economy analysis under technical review label.

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.