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

team-polish

Skill9 starsChanged 7 months agoMITView on GitHub

Multi-agent orchestration for polish passes. Coordinates game-designer, luau-gameplay-programmer, technical-artist, sound-designer, ui-programmer, and qa-tester to refine an existing feature.

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use asset-spec, create-control-manifest and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 10 projects that use this

  • +10 more from lilangMax

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 8

    Distinctive

    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:

    Before a demo or launch

    line 13
  2. Distinctive:

    After external playtest feedback

    line 14
  3. Distinctive:

    technical-artist: Add juice (particle effects, camera shake, screen flashes)

    line 27
  4. Distinctive:

    sound-designer: Add missing sound effects (every action should have feedback)

    line 32
  5. Distinctive:

    performance-analyst: Verify polish didn't tank performance

    line 41
  6. Distinctive:

    Update the feature's GDD with polish notes

    line 71
  7. Distinctive:

    Add shortcuts for power users

    line 101
  8. Distinctive:

    Default options that match player intent

    line 102

“Common” is measured: kept by at least 6 in 10 of the 14 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-polish — Polish Pass Team

Purpose

Polish turns "it works" into "it feels great." This skill orchestrates a polish pass across multiple specialists.

When to Use

  • Feature is functional but feels rough
  • Before a demo or launch
  • After external playtest feedback
  • As part of a dedicated polish sprint

Orchestration Flow

Phase 1: Identify Rough Edges

  1. qa-tester: Play through the feature; note every moment that feels off
  2. ux-designer: Review the flow for friction points
  3. game-designer: Review for fun factor / moment-to-moment engagement

Present a consolidated list to user for prioritization.

Phase 2: Visual Polish

  1. technical-artist: Add juice (particle effects, camera shake, screen flashes)
  2. art-director: Review visual cohesion with game style
  3. ui-programmer: UI animation polish (tweens, fades, bounces)

Phase 3: Audio Polish

  1. sound-designer: Add missing sound effects (every action should have feedback)
  2. audio-director: Review audio mix (not too loud, not too quiet, ducking correctly)

Phase 4: Feel Polish

  1. luau-gameplay-programmer: Adjust timing, animation weights, input responsiveness
  2. game-designer: Tune numbers (damage multipliers, cooldowns, speeds)

Phase 5: Validation

  1. qa-tester: Replay and confirm improvements
  2. performance-analyst: Verify polish didn't tank performance

Steps

1. Scope the Polish

Ask:

  • "Which feature needs polish?"
  • "What specific concerns have you or players mentioned?"
  • "How much time do we have for polish?"

2. Run Rough Edge Audit

  • qa-tester plays the feature with "feel detector" mode: every moment that feels wrong is noted
  • Categorize issues: visual, audio, feel, flow

3. Prioritize

  • Some fixes are 10-minute wins (add a particle, add a sound)
  • Some are bigger (rework the UI flow)
  • User picks which to address first

4. Polish Phase

  • Each specialist addresses their items
  • Each change goes through Question → Options → Decision → Draft → Approval
  • Small changes can batch; big changes reviewed individually

5. Playtest the Result

  • qa-tester replays
  • Note improvements
  • Identify any new issues introduced

6. Document

  • Update the feature's GDD with polish notes
  • Log the polish pass in decision log

Polish Patterns

Visual Juice

  • Particle burst on key actions (impact, pickup, level-up)
  • Camera shake for emphasis (use sparingly)
  • Screen flash on critical events
  • UI element scale bounces on interaction
  • Number ticker for currency changes
  • Highlight on hover / focus

Audio Juice

  • Click on every button
  • Impact sound on every hit
  • Whoosh on movement
  • Confirmation on purchase / pickup
  • Ambient sound for empty moments

Feel Polish

  • Input response < 100ms (no delay between tap and feedback)
  • Animation weight (hit reactions, knockback)
  • Smoothing (camera follow, cursor movement)
  • Forgiveness (coyote time for jumps, input buffering)
  • Explicit feedback (damage numbers, status text)

Flow Polish

  • Reduce tap count to common actions
  • Skip steps that don't need explicit user confirmation
  • Add shortcuts for power users
  • Default options that match player intent

Output

A more polished feature with before/after notes. Document in production/polish-log.md.

Anti-Patterns

  • Polishing the wrong feature (always prioritize biggest impact)
  • Adding polish to something that's still broken (fix it first)
  • Polishing forever (set a time budget and stop)
  • Adding juice that hurts performance (mobile-first test)

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.