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

team-blue-team

Skill2 starsChanged 3 months agoMITView on GitHub

Verification team for cleanup and simplification work. Confirms behavior, contracts, and architecture truth still hold after code removal or collapse.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Do not accept cosmetic simplification that hides risk.

    line 55

≈ “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

Blue Team

Purpose

Did we make this smaller without breaking behavior or drifting from intended architecture?

Composition

  • role-qa-engineer: functional behavior, regression risk, acceptance criteria
  • role-software-architect: architecture truth, boundaries, contract preservation
  • role-principal-software-engineer: maintainability, removal quality, complexity reduction
  • Synthesis: verdict, blocks cosmetic simplification hiding risk
  • Domain specialist (conditional): add when reduced code is in specialized area

Use When

  • role-code-reduction-engineer has proposed or performed cleanup
  • Refactor claims simplification by removing code
  • Dead-code removal without behavior change
  • Risky cleanup where contracts or architecture edges must stay fixed

Do NOT Use When

  • General implementation or bug fixing
  • Adversarial security review (use team-red-team)
  • Architecture design (use team-architecture-review)

Workflow

  1. Load truth source: architecture diagram, ADR, intended functionality, acceptance criteria.
  2. Inspect what was removed, collapsed, or merged.
  3. Confirm behaviors and contracts still hold.
  4. Confirm system boundaries and integration contracts didn't drift.
  5. Accept only if system is simpler AND protected behavior stands.

Default Output

BLUE TEAM VERDICT
=================
Behavior Check: preserved list, regressions found
Architecture Check: truth sources used, boundaries preserved, drift detected
Simplification Quality: complexity actually reduced, hidden replacement complexity
Verdict: Accept / Rework / Escalate, required follow-up

Conflict Resolution

  • Behavior regressed -> block.
  • Architecture truth drifted -> block.
  • Complexity merely moved -> rework.
  • Touched specialized logic -> add specialist before accepting.

Anti-Drift Rules

  • This team verifies cleanup, not general code quality.
  • "Looks cleaner" is not an acceptance criterion. Behavior and architecture truth must hold.
  • Do not accept cosmetic simplification that hides risk.

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.