agentleFS
rudybearrudybear/renderdoc-skill/CLAUDE.md

renderdoc-skill

CLAUDE.md203 starsChanged 9 months agoMITView on GitHub

This project wires Claude Code to RenderDoc via rdc-cli, enabling automated GPU frame capture, inspection, and debugging for Vulkan/D3D/GL applications. See .claude/skills/renderdoc-gpu-debug/SKILL.md for the full GPU debugging skill with workflows, recipes, and command reference.

  • Installs packages

The file

We split this CLAUDE.md into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Vulkan layer: Must be registered (see README.md for setup)

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “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
CLAUDE.md

RenderDoc + Claude Code GPU Debugging

Project Overview

This project wires Claude Code to RenderDoc via rdc-cli, enabling automated GPU frame capture, inspection, and debugging for Vulkan/D3D/GL applications.

Tools

  • rdc-cli (rdc): 66-command CLI wrapping RenderDoc's Python API. Installed via pip install rdc-cli.
  • renderdoc.pyd: Python module from RenderDoc (built from source or from an official install).

Environment

  • RENDERDOC_PYTHON_PATH=<path-to-renderdoc-module> — rdc-cli uses this to find renderdoc.pyd
  • Captures go in ./captures/ (or any directory you choose)
  • Analysis exports (PNGs, meshes, buffers) go in ./captures/analysis/

Your Application (customize this section)

<!-- Replace with your application details -->
  • Executable: /path/to/your/app
  • CWD requirement: Set CWD to your project root if the app resolves assets relative to CWD
  • Debug markers: List any debug markers your app emits (e.g., "Shadow Pass", "GBuffer Pass")
  • Scenes / modes: List any flags or scenes relevant to your app

Capture Requirements

  • Vulkan layer: Must be registered (see README.md for setup)
  • Environment: ENABLE_VULKAN_RENDERDOC_CAPTURE=1 must be set for Vulkan apps
  • Swapchain: The app must present frames (headless apps without vkQueuePresentKHR cannot be captured)
  • Capture script: See capture_frame.py for an example using the RenderDoc Python API directly

Quick Start

# Check setup
rdc doctor

# Capture a frame (adapt the capture script for your app)
python capture_frame.py

# Inspect
rdc open ./captures/my_capture.rdc
rdc info --json
rdc draws --limit 20
rdc close

GPU Debugging Skill

See .claude/skills/renderdoc-gpu-debug/SKILL.md for the full GPU debugging skill with workflows, recipes, and command reference.

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.