agentleFS
CodePhobiiaCodePhobiia/claude-roblox-game-studio/.claude/skills/team-combat/SKILL.md

team-combat

Skill9 starsChanged 7 months agoMITView on GitHub

Multi-agent orchestration for combat features. Coordinates game-designer, systems-designer, luau-gameplay-programmer, technical-artist, sound-designer, and exploit-security-specialist to tackle a combat feature end-to-end.

14 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    ui-programmer: Update HUD / damage numbers / health bar

    line 29
  2. Distinctive:

    qa-tester: Write test plan and execute

    line 34
  3. Distinctive:

    producer: Update sprint plan, systems-index

    line 40
  4. Distinctive:

    If a phase reveals a blocker (e.g., exploit-security-specialist says the design is unsafe):

    line 59
  5. Distinctive:

    Wait for user to resolve

    line 62
  6. Very specific:

    Update the combat GDD (design/gdd/combat-gdd.md)

    line 67
  7. Distinctive:

    Update the remotes manifest

    line 68
  8. Distinctive:

    Update the systems-index status

    line 69
  9. Distinctive:

    Add an entry to the changelog

    line 70

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “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

/team-combat — Combat Feature Team

Orchestration Flow

Combat features touch many specialists. This skill coordinates them.

Phase 1: Design

  1. game-designer: Define the feature — what mechanic, what player intent, how it feels
  2. systems-designer: Translate into detailed spec with formulas, edge cases, data schema

User reviews and approves the design before moving to Phase 2.

Phase 2: Architecture

  1. lead-programmer: Plan the implementation architecture
  2. remotes-networking-specialist: Design the client-server contract
  3. exploit-security-specialist: Review for attack surface (speed hacks, damage exploits, duplication)

User reviews the architecture before Phase 3.

Phase 3: Implementation

  1. luau-gameplay-programmer: Implement the combat logic
  2. technical-artist: Implement VFX (particles, beams, trails)
  3. sound-designer: Implement audio triggers
  4. ui-programmer: Update HUD / damage numbers / health bar

Each sub-step goes through the Question → Options → Decision → Draft → Approval flow.

Phase 4: Quality

  1. qa-tester: Write test plan and execute
  2. performance-analyst: Profile the feature on mobile
  3. exploit-security-specialist: Final security pass

Phase 5: Integration

  1. game-designer: Balance tuning (damage, cooldowns, etc.)
  2. producer: Update sprint plan, systems-index

Steps

1. Gather Context

Ask:

  • "What combat feature are we building?" (new weapon, new ability, new enemy, etc.)
  • "What's the intended player experience?"
  • "What systems does this touch?" (just combat, or also inventory/progression/UI?)
  • "What's the scope?" (afternoon prototype, full sprint feature, multi-sprint feature)

2. Delegate Through Each Phase

For each phase:

  1. Announce which specialist is about to work
  2. Have that specialist produce a draft
  3. Present to user for approval
  4. On approval, move to next phase

3. Handle Blockers

If a phase reveals a blocker (e.g., exploit-security-specialist says the design is unsafe):

  • Pause the flow
  • Escalate to the director (technical-director for tech blockers, creative-director for design blockers)
  • Wait for user to resolve
  • Resume the flow

4. Document the Feature

After completion:

  • Update the combat GDD (design/gdd/combat-gdd.md)
  • Update the remotes manifest
  • Update the systems-index status
  • Add an entry to the changelog

Output

A complete combat feature: design doc + code + VFX + audio + tests + security review.

Example Use

User: "Let's add a parry mechanic to combat" Flow:

  1. game-designer drafts the parry concept
  2. systems-designer specifies windows, timing, counter-attack damage
  3. remotes-networking-specialist adds ParryRemoteEvent with validation
  4. exploit-security-specialist checks for timing exploits
  5. luau-gameplay-programmer implements
  6. technical-artist adds the parry flash VFX
  7. sound-designer adds the parry sound
  8. ui-programmer updates HUD to show parry window indicator
  9. qa-tester writes test plan, tests edge cases
  10. performance-analyst verifies no FPS impact
  11. game-designer tunes timing windows based on playtest
  12. producer updates sprint plan

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.