Game DevPROPRO REQUIREDFC-GDEV-006
Game Physics Claw
game-physics-claw
v0.2.0May 28, 2026Physics that holds up under stress — collision solvers, ragdoll stability, CCD thresholds, and constraint graphs with safety margins
I am the physics engineer who will break your collision solver before players do. I think in contact manifolds, constraint solvers, CCD thresholds, and penetration recovery tolerances. I will stress-test your ragdoll joints under extreme angular velocity, push your vehicle suspension through every ground plane edge case, and find the exact impulse value where your stack of boxes explodes. I generate test harnesses with slow-motion replay, write PhysX/Havok/Box2D tuning profiles, and produce constraint graphs annotated with stability margins.
OpenClaw
Hermes
Claude Code
Codex
Cursor
Windsurf
Aider
OllamaPRIMARY ACTION
Unlock with ProCOMPATIBLE WITH
OpenClawHermesClaude CodeCodex+4
8 compatible tools4 output formats
When to Use
- Design a clear core gameplay loop
- Tune economy and progression curves
- Plan difficulty ramps and retention beats
- Turn playtest feedback into concrete changes
Compatible Frameworks
OpenClawHermesClaude CodeCodexCursorWindsurfAiderOllama8 TOOLs
Quality Gates
- Collision detection accurate
- Physics determinism for multiplayer
- Performance within frame budget
- Edge cases handled (tunneling, stacking)
- Ragdoll constraints realistic
4 GATEs DEFINED
Expected Outputs
Physics Stress-Test Harness with Slow-Motion Replay CaptureCollision Tuning Profile with Per-Material Restitution/Friction TableConstraint Graph with Stability Margin AnnotationsRagdoll and Vehicle Edge-Case Report with Frame-by-Frame Breakdown
Native exports per tool
OpenClaw10 files
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 moreHermes5 files
hermes/skills/flickclaw/game-physics-claw/SKILL.mdhermes/skills/flickclaw/game-physics-claw/references/workflow.mdhermes/skills/flickclaw/game-physics-claw/references/quality-gates.md+2 moreClaude Code6 files
claude-code/CLAUDE.mdclaude-code/.claude/skills/game-physics-claw/SKILL.mdclaude-code/.claude/skills/game-physics-claw/references/workflow.md+3 moreCodex5 files
codex/AGENTS.mdcodex/.flickclaw/agents/game-physics-claw/codex.mdcodex/.flickclaw/agents/game-physics-claw/workflow.md+2 moreCursor3 files
cursor/.cursor/rules/flickclaw-game-physics-claw.mdccursor/.cursor/rules/flickclaw-game-physics-claw-workflow.mdccursor/.cursor/rules/flickclaw-game-physics-claw-quality-gates.mdcWindsurf3 files
windsurf/.windsurf/rules/flickclaw-game-physics-claw.mdwindsurf/.windsurf/rules/flickclaw-game-physics-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-game-physics-claw-quality-gates.mdAider3 files
aider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlOllama4 files
ollama/Modelfileollama/system-prompt.mdollama/template.md+1 moreInstall Commands
Install the FlickClaw CLI, then select your AI agent framework below to get the correct install command.
Step 1: Install CLI (one-time)
npm install -g @flickclaw/cli@latestStep 2: Select Framework
OpenClaw
npm exec --yes @flickclaw/cli@latest -- install game-physics-claw --target openclawDownload as ZIP
Example Prompt
Try this prompt with Game Physics Claw to see what it can do:
Review this game concept for core loop clarity, progression pacing, economy balance, difficulty curve, retention risks, and playtest plan. Produce Physics Stress-Test Harness with Slow-Motion Replay Capture, Collision Tuning Profile with Per-Material Restitution/Friction Table, Constraint Graph with Stability Margin Annotations.Example Output
IllustrativeWhat a typical Game Physics Claw report looks like:
# Game Physics Claw — Assessment Report **Project**: tactical-roguelite-prototype **Context**: a turn-based roguelite with a 20-minute session target, draftable abilities, and meta-progression **Example type**: Illustrative output ## Executive Summary The Game Physics Claw completed its review of tactical-roguelite-prototype (a turn-based roguelite with a 20-minute session target, draftable abilities, and meta-progression). 3 findings were identified with concrete remediation steps. All quality gates were verified before delivery. ## Findings | # | Severity | Area | Finding | Recommended Action | |---|----------|------|---------|-------------------| | 1 | **P1** | Core Loop | Combat rewards arrive after too many low-agency turns | Shorten encounter cadence and add a choice after every room | | 2 | **P1** | Progression | Power curve spikes after upgrade tier 3 and trivializes mid-game fights | Flatten tier multipliers and add enemy counter-traits from zone 2 | | 3 | **P2** | Playtesting | No retention test for first-session failure cases | Run 10-player blind test tracking retry intent after first defeat | ## Quality Gates - [✓] ccd_threshold_stress_test - [✓] ragdoll_joint_stability_profile - [✓] penetration_recovery_edge_case ## Outputs Generated - **Physics Stress-Test Harness with Slow-Motion Replay Capture**: Included in the report above. - **Collision Tuning Profile with Per-Material Restitution/Friction Table**: Included in the report above. - **Constraint Graph with Stability Margin Annotations**: Included in the report above. - **Ragdoll and Vehicle Edge-Case Report with Frame-by-Frame Breakdown**: Included in the report above. ## Validation - [x] All quality gates passed (3/3) - [x] 3 findings documented with severity and remediation - [x] 4 output sections generated - [x] Evidence collected and referenced --- *This is an illustrative example output from FlickClaw. Results vary based on project context.*
RELATED AGENTS