godot-gameplay-guidelines
Godot 4.7 gameplay implementation and review.
Skill by ryanmazzolini
Chalk Labs
Need help deploying godot-gameplay-guidelines?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ryanmazzolini-godot-gameplay-guidelines
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/godot-gameplay-guidelines
What's inside
- Skill name
godot-gameplay-guidelines- Description
- Godot 4.7 gameplay implementation and review. Use when changing gameplay behavior, scene ownership, game feel, or runtime performance.
- License
- MIT
- Instructions
- 43 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- godot-4-7-correctness.md · references/
- mcp-feedback-loop.md · references/
- prototyping.md · references/
SKILL.md (first lines)
# Godot Gameplay Guidelines Close a feedback loop: define the player-visible change, give it a clear Godot owner, run it, and observe what happened. ## Choose experiment or production Before production implementation, decide whether the player-visible behavior is settled through evidence. When input, game feel, pacing, camera, feedback, or interaction flow remains materially uncertain, stop the production workflow and use one disposable experiment to settle one question. Read [Prototyping](references/prototyping.md) for the experiment defaults. Return to the production workflow only when the verdict settles the intended behavior and identifies a representative scenario that can prove it. ## Workflow 1. **Define the change.** Inspect the relevant scenes, scripts, Resources, autoloads, and project commands. Identify the player-visible behavior, its owner, and a representative scene or scenario that can prove it works. During review, question whether the current architecture should exist before recommending ways to harden it. Complete when the behavior, owner, and evidence are clear. 2. **Implement or review it.** Apply every relevant default below. Explain any new global state, mutable Resource, custom framework, or performance system. Complete when every relevant default is satisfied or has an explicit exception. 3. **Validate it in Godot.** Check changed scripts, run the representative scenario, and inspect editor and game errors. Prefer structured runtime evidence for behavior and screenshots for appearance. Run the project's full validation. A human must playtest game-feel changes; profile performance changes under representative load. Complete when every claim has evidence or is clearly reported as pending. ## Defaults - Use a fitting Godot feature before building custom infrastructure: scenes, nodes, Resources, signals, TileMapLayer, navigation, AnimationPlayer, or tweens. - Prefer self-contained scenes and composition over deep inheritance. Parent-child structure should express lifetime ownership; a common ancestor should connect siblings and provide external dependencies. - Call typed methods to start behavior. Emit typed, past-tense signals to report events. - Let one cohesive node or child scene own each gameplay capability and its lifecycle. Split it when responsibilities, lifetimes, update rates, or reuse needs diverge. - Treat exported Resources as shared configuration. Keep per-instance mutable state with its owning node unless the Resource is deliberately local or duplicated. - Follow the project's typing style. When no policy exists, add types at public boundaries: exported values, parameters, returns, signals, and collections. - Perform physics body movement and direct physics queries during the physics update. - Use an autoload when a responsibility must survive scene changes, has broad scope, and owns isolated state. Prefer scene-owned behavior for local responsibilities. - Let repeated gameplay needs earn an abstraction. Keep tunable gameplay values visible to designers and future maintainers. - Introduce data-oriented storage or performance systems only when measured scale or access patterns justify them. ## Progressive References - Before changing physics bodies, node lifecycle, mutable Resources, TileMapLayer, navigation, performance-sensitive code, or a project migrating from Godot 4.6, read [Godot 4.7 correctness](references/godot-4-7-correctness.md). - When Godot MCP tools are available, or the task needs editor or runtime evidence, read [MCP feedback loop](references/mcp-feedback-loop.md).
From ryanmazzolini/pi-skills, MIT.
More from ryanmazzolini/pi-skills
- 0.567score
daily-report
ryanmazzolini
Set up, create, update, or repair evidence-based daily work and personal reports from local Git, GitHub, and Shortcut activity in an Obsidian vault.
SkillAFreshness: AClaude Code +9 - 0.565score
handoff
ryanmazzolini
Write a Markdown handoff so another agent or fresh session can continue the work.
SkillAFreshness: AClaude Code +9 - 0.565score
herdr-automations
ryanmazzolini
Schedule recurring Pi work with the Herdr automations plugin, or change, pause, test, or inspect existing schedules.
SkillAFreshness: AClaude Code +9 - 0.564score
meta-review
ryanmazzolini
Review recent personal Pi sessions for recurring collaboration problems and return a few small, testable improvements.
SkillAFreshness: AClaude Code +9 - 0.564score
commit-pr
ryanmazzolini
Create or update a draft pull request from the current branch.
SkillAFreshness: AClaude Code +9 - 0.564score
commit-simple
ryanmazzolini
Prepare commits and push work, creating branches when needed.
SkillAFreshness: AClaude Code +9 - 0.564score
first-mate
ryanmazzolini
Coordinate connected Pi sessions on request: inspect evidence, resolve blockers, and advance clearly authorized work.
SkillAFreshness: AClaude Code +9 - 0.558score
agent-coordination
ryanmazzolini
Choose models and reasoning levels for delegated agents using configured preferences.
SkillAFreshness: AClaude Code +9 - 0.555score
firefox-tab-triage
ryanmazzolini
Triage tabs in personal and secondary Firefox profiles.
SkillAFreshness: AClaude Code +9 - 0.529score
herdr
ryanmazzolini
Control Herdr when the user explicitly asks, infer a fresh Pi destination in an existing tabbed workspace or a new workspace, or keep the current pane…
SkillBFreshness: BClaude Code +9 - 0.529score
diagnosing-bugs
ryanmazzolini
Diagnose hard, flaky, environment-specific, or performance bugs.
SkillBFreshness: BClaude Code +9 - 0.524score
architecture
ryanmazzolini
Route architecture work to the right lens.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 30, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ryanmazzolini/pi-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ryanmazzolini
- 0.567score
daily-report
ryanmazzolini
Set up, create, update, or repair evidence-based daily work and personal reports from local Git, GitHub, and Shortcut activity in an Obsidian vault.
SkillAFreshness: AClaude Code +9 - 0.565score
herdr-automations
ryanmazzolini
Schedule recurring Pi work with the Herdr automations plugin, or change, pause, test, or inspect existing schedules.
SkillAFreshness: AClaude Code +9 - 0.565score
handoff
ryanmazzolini
Write a Markdown handoff so another agent or fresh session can continue the work.
SkillAFreshness: AClaude Code +9 - 0.564score
commit-pr
ryanmazzolini
Create or update a draft pull request from the current branch.
SkillAFreshness: AClaude Code +9 - 0.564score
commit-simple
ryanmazzolini
Prepare commits and push work, creating branches when needed.
SkillAFreshness: AClaude Code +9 - 0.564score
first-mate
ryanmazzolini
Coordinate connected Pi sessions on request: inspect evidence, resolve blockers, and advance clearly authorized work.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get godot-gameplay-guidelines running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
godot-gameplay-guidelines skill. Agent Mart. https://agentmart.dev/skills/ryanmazzolini-godot-gameplay-guidelines (last updated 2026-10-24)