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

onboard

Skill9 starsChanged 7 months agoMITView on GitHub

Onboard a new contributor to the project. Overview of architecture, conventions, key files, and first-task suggestions.

168 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test, team-live-ops and 9 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

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 11 projects that use this

  • CoralGameSkill

    team-narrative

    Orchestrate the narrative team: coordinates narrative-director, writer, world-builder, and level-designer to create cohesive story content, world lore, and narrative-driven level design.

    Also in 11 projects that use this

  • +5 more from lilangMax
  • +1 more from CoralGame

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 1

    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:

    Ask user to confirm art style docs (if they exist, point to them)

    line 37

“Common” is measured: kept by at least 6 in 10 of the 156 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

/onboard — New Contributor Onboarding

Delegate to: producer (with technical-director for tech orientation, game-designer for creative orientation)

Steps

1. Welcome

Greet the new contributor. Ask:

  • "What's your role?" (programmer, designer, artist, QA, mixed)
  • "Experience level?" (new to Roblox / experienced Roblox dev / experienced but new to this project)
  • "What are you hoping to contribute to?" (specific system, general help, exploration)

2. Context Overview

Based on their role, give a tailored tour:

For Programmers

  • CLAUDE.md — project-wide config
  • .claude/docs/roblox-architecture-guide.md — architecture overview
  • .claude/docs/luau-style-guide.md — coding standards
  • .claude/rules/ — path-scoped standards
  • src/ — game source
  • design/gdd/ — design docs to understand what we're building

For Designers

  • design/gdd/master-gdd.md — master design doc
  • design/gdd/systems-index.md — all systems catalog
  • .claude/docs/templates/gdd-master.md and gdd-system.md — templates for new docs
  • docs/COLLABORATIVE-DESIGN-PRINCIPLE.md — how we work together

For Artists

  • assets/ — asset directories
  • Ask user to confirm art style docs (if they exist, point to them)
  • art-director agent knowledge via .claude/agents/art-director.md

For QA

  • tests/ — existing tests
  • production/bugs/ — bug tracker (if exists)
  • .claude/docs/templates/bug-report-template.md — bug format
  • qa-lead and qa-tester agent knowledge

3. Introduce Key Agents

Show them the studio hierarchy:

  • Directors (Opus): creative, technical, producer
  • Leads (Sonnet): game-designer, lead-programmer, etc.
  • Specialists (Sonnet/Haiku): the deep specialists

Explain:

  • "We use subagents for specialized work"
  • "You can invoke slash commands with /command"
  • "Most work flows: Question → Options → Decision → Draft → Approval"

4. Introduce Workflows

Show the most useful skills for their role:

  • Programmers: /code-review, /luau-lint, /datastore-review, /remotes-audit
  • Designers: /gdd, /design-review, /balance-check, /design-system
  • QA: /bug-report, /exploit-check
  • All: /sprint-plan, /estimate, /start (if jumping in cold)

5. Suggest First Tasks

Based on their role and current sprint status:

  • First task: Something small and self-contained to learn the ropes
  • Second task: Something that requires collaboration (learn the handoff pattern)
  • Third task: Actual value-add work

6. Explain Norms

  • Committing: always ask before commits
  • Reviews: every change gets reviewed by a relevant agent
  • Decision log: major decisions get logged
  • Production/session-state: session continuity via this directory

7. Output

# Onboarding: [Contributor Name / Role]

## Your Role
[Summary]

## Key Docs to Read (in order)
1. CLAUDE.md
2. [Role-specific doc]
3. Current sprint plan
4. [Agent they should be aware of]

## Your First Tasks
1. **Warm-up**: [Specific starter task]
2. **Collaboration**: [Task requiring handoff]
3. **Real work**: [Value-add task]

## Agents to Know
- Your primary lead: [agent]
- Peer specialists: [list]

## Useful Skills
- `/[skill]` — [what it does]

## Questions?
Just ask. If unclear, I'll route to the right specialist.

Save to production/onboarding/<name>-<date>.md on approval.

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.