Agent skill

Renderdoc GPU Debug

by rudybear in rudybear/renderdoc-skill

GPU frame debugging with RenderDoc via rdc-cli. An agent skill from rudybear/renderdoc-skill.

MITAuto-check passedDevelopment

Install Renderdoc GPU Debug

skills CLI
$ npx skills add rudybear/renderdoc-skill --skill renderdoc-gpu-debug -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rudybear/renderdoc-skill renderdoc-gpu-debug --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rudybear/renderdoc-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/renderdoc-gpu-debug .claude/skills/renderdoc-gpu-debug && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
renderdoc-gpu-debug
GitHub stars
211
Token cost
~4k tokens
SKILL.md length
750 words
Files
3 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

GPU frame debugging with RenderDoc via rdc-cli. An agent skill from rudybear/renderdoc-skill.

  • Works in 12 steps: Session Lifecycle → Capture Workflow → Frame Exploration → …
  • The user mentions: GPU debugging
  • SKILL.md covers Overview, 1. Session Lifecycle, 2. Capture Workflow and 3. Frame Exploration, plus 4 more sections
  • Calls jq, python and pip

What it does

Renderdoc GPU Debug is an agent skill from rudybear/renderdoc-skill. GPU frame debugging with RenderDoc via rdc-cli. Use this skill when the user mentions: GPU debugging, .rdc files, RenderDoc, shader issues, pipeline state, rendering artifacts, frame capture, shadow problems, visual glitches, draw calls, render targets, pixel history, texture inspection, depth buffer, blend state, rasterizer state, vertex shader, fragment shader, pixel shader, compute shader, mesh output, GPU performance, overdraw, bandwidth, shadow map, PCF filtering, screen-space artifacts, z-fighting, alpha…

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/commands-quick-ref.md` and `references/debugging-recipes.md`).

It sits in Development, covering Shaders, Debugging and Web performance. It works with React and Python. The repository describes itself as: A Claude Code skill for GPU frame debugging with RenderDoc via rdc-cli. The licence is MIT.

When your agent uses it

  • The user mentions: GPU debugging
  • Rendering artifacts
  • Shadow problems
  • Visual glitches

Example prompts

  • “why does this look wrong”
  • “debug this pixel”
  • “s drawing here”
  • “/renderdoc-gpu-debug”

Requirements

  • Python 3

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Session Lifecycle
  2. Capture Workflow
  3. Frame Exploration
  4. Pipeline State Inspection
  5. Shader Inspection
  6. Visual Inspection: Export-View-Analyze
  7. Pixel Debugging
  8. Shader Edit-Replay
  9. Frame Comparison
  10. Debugging Recipes
  11. Output Size Management
  12. Error Handling

What it can do on your machine

Read from SKILL.md and the folder at commit de33576. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • python
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Renderdoc GPU Debug loads about 4k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 223 tokens; SKILL.md has 750 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~223
When it runs · the whole SKILL.md, loaded when a task matches
~4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~12k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rudybear/renderdoc-skill at commit de33576, republished under its MIT licence (© rudybear). 750 words, ~3,953 tokens.

Download SKILL.mdSave it as .claude/skills/renderdoc-gpu-debug/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
renderdoc-gpu-debug
description
GPU frame debugging with RenderDoc via rdc-cli. Use this skill when the user mentions: GPU debugging, .rdc files, RenderDoc, shader issues, pipeline state, rendering artifacts, frame capture, shadow problems, visual glitches, draw calls, render targets, pixel history, texture inspection, depth buffer, blend state, rasterizer state, vertex shader, fragment shader, pixel shader, compute shader, mesh output, GPU performance, overdraw, bandwidth, shadow map, PCF filtering, screen-space artifacts, z-fighting, alpha blending, stencil, MSAA, "why does this look wrong", "debug this pixel", "what's drawing here", "capture a frame", "inspect the pipeline", "export render target", vulkan debugging, D3D debugging, GL debugging. DO NOT use for: CSS rendering, React rendering, server-side rendering, HTML layout, browser DevTools, web performance, canvas 2D, SVG rendering.

RenderDoc GPU Debugging Skill

Overview

This skill enables GPU frame capture, inspection, and debugging using rdc-cli, a 66-command CLI wrapping RenderDoc's Python API. It works with Vulkan, D3D11, D3D12, and OpenGL applications.

Prerequisites

Before any GPU debugging, verify the environment:

bash
rdc doctor

All checks should pass. If rdc doctor fails, check:

  • RENDERDOC_PYTHON_PATH is set to the directory containing renderdoc.pyd
  • renderdoc.dll is in the same directory as renderdoc.pyd
  • renderdoccmd.exe is on PATH or in the module directory

1. Session Lifecycle

Every inspection session follows open-work-close:

bash
rdc open path/to/capture.rdc   # Start daemon, load capture
# ... inspection commands ...
rdc close                       # Release resources, stop daemon

Check session state with rdc status. Only one capture can be open per session (use --session name for parallel sessions).

IMPORTANT: Always close sessions when done. Leaked daemon processes consume GPU memory.

2. Capture Workflow

Capture from an executable
bash
rdc capture -o output.rdc -- /path/to/app [app-args...]

Key options:

  • -o, --output: Output .rdc file path
  • --frame N: Capture frame N (default: first presented frame)
  • --timeout S: Capture timeout in seconds (default: 60)
  • --api-validation: Enable API validation layer
  • --ref-all-resources: Reference all resources (larger capture, more complete)
  • --wait-for-exit: Wait for the app to exit after capture
CWD matters

Many applications resolve assets relative to CWD. Always set CWD appropriately:

bash
cd /path/to/app/root && rdc capture -o /output/path/capture.rdc -- ./app

For lux-playground specifically:

bash
cd D:/shaderlang && python D:/renderdoc/capture_frame.py
Vulkan layer requirement

For Vulkan apps, the RenderDoc Vulkan layer must be registered:

  • Registry: HKCU\SOFTWARE\Khronos\Vulkan\ImplicitLayers must contain D:\renderdoc\module\renderdoc.json (DWORD 0)
  • Environment: ENABLE_VULKAN_RENDERDOC_CAPTURE=1 must be set
If headless capture fails

Headless Vulkan apps (no swapchain / no vkQueuePresentKHR) cannot be captured by RenderDoc since frame boundaries are defined by present calls. Options:

  1. Use --interactive mode if the app supports it (opens a window with a swapchain)
  2. Use the Python API via capture_frame.py for reliable programmatic capture
  3. Use --trigger mode (inject without auto-capture, then rdc capture-trigger)
  4. Fall back to renderdoccmd capture directly

3. Frame Exploration

After opening a capture, start with high-level overview:

bash
rdc info --json          # API, GPU, driver, resolution, frame number
rdc stats --json         # Per-pass breakdown, top draws, largest resources
rdc passes               # List render passes (debug markers / implicit passes)
rdc draws --limit 20     # First 20 draw calls
rdc count draws          # Total draw call count
Navigate by pass
bash
rdc draws --pass "Shadow Pass" --json    # Draws in a specific pass
rdc draws --pass "GBuffer" --limit 10    # First 10 GBuffer draws
Navigate by event
bash
rdc events --limit 50                    # All API events (not just draws)
rdc events --type DrawIndexed --json     # Filter by event type
rdc event 42 --json                      # Detail for one event
VFS browsing

The virtual filesystem provides a structured view of the capture:

bash
rdc ls /                      # Root directories
rdc ls /textures -l           # List textures with metadata
rdc tree /pipelines --depth 2 # Pipeline tree
rdc cat /events/42            # Event detail

4. Pipeline State Inspection

Get full pipeline state at any draw call:

bash
rdc pipeline EID --json              # Full pipeline state
rdc pipeline EID vs --json           # Vertex shader section only
rdc pipeline EID ps --json           # Pixel/fragment shader section only
rdc pipeline EID om --json           # Output merger (blend, depth, stencil)
rdc pipeline EID rs --json           # Rasterizer state (culling, viewport)
rdc pipeline EID ia --json           # Input assembler (vertex buffers, topology)
rdc pipeline EID ds --json           # Depth-stencil state
Bound resources
bash
rdc bindings EID --json              # All bindings for all stages
rdc bindings EID --set 0 --json      # Descriptor set 0 only

5. Shader Inspection

View shader metadata and source
bash
rdc shader EID vs --json             # Vertex shader metadata
rdc shader EID ps --json             # Fragment/pixel shader metadata
rdc shader EID ps --source           # Debug source code (if available)
rdc shader EID ps --reflect --json   # Reflection: inputs, outputs, cbuffers
rdc shader EID ps --constants --json # Constant buffer values at this draw
Disassembly targets
bash
rdc shader EID ps --targets          # List available disassembly formats
rdc shader EID ps --target spirv     # SPIR-V disassembly
rdc shader EID ps --target glsl      # GLSL (cross-compiled, if available)
Search shaders
bash
rdc search "shadow" --json           # Search all shader disassembly for "shadow"
rdc search "main" --stage ps         # Search only pixel shaders
rdc shaders --stage ps --json        # List all unique pixel shaders
rdc shader-map --json                # EID-to-shader mapping

6. Visual Inspection: Export-View-Analyze

This is the core pattern for visual debugging. Always export to PNG, then use Claude Code's Read tool to view the image.

Export render targets
bash
rdc rt EID -o D:/renderdoc/captures/analysis/render_target.png
rdc rt EID --target 1 -o D:/renderdoc/captures/analysis/rt_target1.png  # MRT target 1
Export textures
bash
rdc texture RESID -o D:/renderdoc/captures/analysis/texture.png
rdc texture RESID --mip 2 -o D:/renderdoc/captures/analysis/mip2.png
Export thumbnail
bash
rdc thumbnail -o D:/renderdoc/captures/analysis/thumb.png
View exported images

After exporting a PNG, use the Read tool to view it (Claude Code is multimodal):

Read tool: D:/renderdoc/captures/analysis/render_target.png

Do NOT use cat or bash to view images. The Read tool renders them visually.

Analyze

Correlate what you see in the image with pipeline state data:

  1. Export the render target at the suspicious draw
  2. View it with the Read tool
  3. Check pipeline state (rdc pipeline EID --json)
  4. Check shader constants (rdc shader EID ps --constants --json)
  5. Form hypothesis and verify
Show full SKILL.md (301 more words)Show less

7. Pixel Debugging

Pixel history

Find all draws that wrote to a pixel:

bash
rdc pixel X Y --json                 # Full pixel history at current event
rdc pixel X Y EID --json             # Pixel history up to EID
Pick pixel color

Read the current color at a pixel:

bash
rdc pick-pixel X Y --json            # Color at (X,Y) from current render target
rdc pick-pixel X Y EID --json        # Color at specific event
Debug pixel shader

Step through shader execution for a specific pixel:

bash
rdc debug pixel EID X Y --json           # Shader inputs/outputs summary
rdc debug pixel EID X Y --trace          # Full execution trace (every line)
rdc debug pixel EID X Y --dump-at 42     # Variable snapshot at line 42
Debug vertex shader
bash
rdc debug vertex EID VTXID --json        # Vertex shader debug for vertex ID
rdc debug vertex EID VTXID --trace       # Full trace
Debug compute shader
bash
rdc debug thread EID GX GY GZ TX TY TZ --json   # Compute thread debug

8. Shader Edit-Replay

Modify shaders without recompiling the application:

bash
# 1. Check available encodings
rdc shader-encodings --json

# 2. Extract shader source
rdc shader EID ps --source -o D:/renderdoc/captures/analysis/shader.frag

# 3. Edit the shader (use Edit tool)

# 4. Build the modified shader
rdc shader-build D:/renderdoc/captures/analysis/shader.frag --encoding GLSL --stage ps --json

# 5. Replace (use the shader_id from build output)
rdc shader-replace EID ps --with SHADER_ID --json

# 6. Export to verify the change
rdc rt EID -o D:/renderdoc/captures/analysis/after_edit.png

# 7. Restore when done
rdc shader-restore EID ps
# or: rdc shader-restore-all

9. Frame Comparison

Compare two captures:

bash
# Quick summary of differences
rdc diff capture_a.rdc capture_b.rdc --shortstat

# Detailed comparisons
rdc diff capture_a.rdc capture_b.rdc --draws --json       # Draw call differences
rdc diff capture_a.rdc capture_b.rdc --resources --json   # Resource differences
rdc diff capture_a.rdc capture_b.rdc --passes --json      # Pass structure differences
rdc diff capture_a.rdc capture_b.rdc --framebuffer --json  # Final framebuffer diff

# Visual diff
rdc diff capture_a.rdc capture_b.rdc --framebuffer --diff-output D:/renderdoc/captures/analysis/diff.png

10. Debugging Recipes

Recipe: Object is invisible
bash
# 1. Find the draw call that should render the object
rdc draws --json | jq '.[] | select(.name | contains("ObjectName"))'
# or search by pass:
rdc draws --pass "Main Pass" --json

# 2. Check if it's being culled
rdc pipeline EID rs --json   # Look at CullMode, FrontFace

# 3. Check depth state
rdc pipeline EID ds --json   # DepthEnable, DepthFunc, DepthWriteMask

# 4. Check blend state (maybe alpha is 0)
rdc pipeline EID om --json   # BlendEnable, SrcBlend, DestBlend

# 5. Check vertex transform
rdc debug vertex EID 0 --json   # Is the position off-screen or behind camera?

# 6. Check if the draw is even issuing primitives
rdc draw EID --json   # VertexCount, InstanceCount, IndexCount
Recipe: Colors are wrong
bash
# 1. Export the render target to see what's there
rdc rt EID -o D:/renderdoc/captures/analysis/wrong_color.png

# 2. Pick the problematic pixel
rdc pick-pixel X Y EID --json

# 3. Check texture bindings — is the right texture bound?
rdc bindings EID --json

# 4. Export the bound texture
rdc texture RESID -o D:/renderdoc/captures/analysis/bound_texture.png

# 5. Check shader constants — wrong material colors?
rdc shader EID ps --constants --json

# 6. Check blend state — additive when it should be alpha?
rdc pipeline EID om --json

# 7. Debug the pixel shader to trace the calculation
rdc debug pixel EID X Y --trace
Recipe: Shadows are broken
bash
# 1. Find the shadow pass
rdc passes --json
rdc draws --pass "Shadow*" --json

# 2. Export the shadow map
SHADOW_EID=$(rdc draws --pass "Shadow*" -q | tail -1)
rdc rt $SHADOW_EID -o D:/renderdoc/captures/analysis/shadow_map.png

# 3. Check shadow map resolution (is it too small?)
rdc bindings $SHADOW_EID --json   # Look at render target dimensions

# 4. Check depth bias
rdc pipeline $SHADOW_EID rs --json   # DepthBias, SlopeScaledDepthBias

# 5. Find the lighting pass that reads the shadow map
rdc draws --pass "Raster*" --json
LIGHT_EID=$(rdc draws --pass "Raster*" -q | head -1)

# 6. Check how the shadow map is sampled
rdc shader $LIGHT_EID ps --source   # Look for shadow sampling code
rdc shader $LIGHT_EID ps --constants --json   # Light matrices, bias values

# 7. Debug a shadowed pixel
rdc debug pixel $LIGHT_EID X Y --trace
Recipe: Performance is bad
bash
# 1. Get frame overview
rdc stats --json

# 2. Count draws per pass
rdc passes --json   # Look for passes with excessive draw counts

# 3. Look for redundant state changes
rdc events --limit 500 --json | jq 'group_by(.type) | map({type: .[0].type, count: length}) | sort_by(-.count)'

# 4. Check for large resources
rdc resources --sort size --json | jq '.[-10:]'   # Top 10 largest resources

# 5. Look for overdraw (if GPU counters available)
rdc counters --list
rdc counters --name "overdraw" --json

# 6. Export with wireframe overlay to visualize overdraw
rdc rt EID --overlay wireframe -o D:/renderdoc/captures/analysis/wireframe.png
Recipe: What changed between two frames
bash
# Quick diff
rdc diff before.rdc after.rdc --shortstat

# Detailed diffs
rdc diff before.rdc after.rdc --draws --json
rdc diff before.rdc after.rdc --framebuffer --diff-output D:/renderdoc/captures/analysis/frame_diff.png

# Compare pipeline state at specific draw
rdc diff before.rdc after.rdc --pipeline EID --json
Recipe: Debug this pixel
bash
# 1. Get pixel history — which draws touched this pixel?
rdc pixel X Y --json

# 2. Pick the draw that produced the final color
# (usually the last non-failing entry in pixel history)

# 3. Get the pixel's current value
rdc pick-pixel X Y EID --json

# 4. Debug the shader at that pixel
rdc debug pixel EID X Y --json

# 5. Get full execution trace if needed
rdc debug pixel EID X Y --trace

# 6. Check variable values at a specific shader line
rdc debug pixel EID X Y --dump-at LINE_NUMBER

11. Output Size Management

GPU captures can produce enormous output. Follow these rules:

  1. Always use --limit for exploration: rdc draws --limit 20, rdc events --limit 50
  2. Filter by pass: rdc draws --pass "Shadow Pass" instead of all draws
  3. Use -q for ID lists: rdc draws -q returns only EIDs, not full details
  4. Use --json selectively: JSON is verbose; use TSV default for scanning
  5. Pipeline sections: rdc pipeline EID vs instead of full rdc pipeline EID
  6. Limit search results: rdc search "pattern" --limit 10
Size estimates
  • rdc info: ~20 lines
  • rdc draws --limit 20: ~25 lines
  • rdc pipeline EID --json: ~200-500 lines (full), ~50 lines (per section)
  • rdc shader EID ps --source: ~50-500 lines depending on shader
  • rdc debug pixel EID X Y --trace: ~100-1000 lines depending on shader complexity

12. Error Handling

rdc not found
bash
pip install rdc-cli
rdc doctor fails

Check RENDERDOC_PYTHON_PATH points to directory containing renderdoc.pyd and renderdoc.dll.

Capture fails with "no swapchain"

The app may not present frames in the expected way. Try:

bash
rdc capture --trigger -- /path/to/app   # Inject-only mode
# Then manually trigger: rdc capture-trigger
Daemon not responding
bash
rdc status          # Check if daemon is alive
rdc close           # Force close
rdc open capture.rdc  # Re-open
GPU feature not supported

Some features (GPU counters, pixel history) depend on the GPU and driver. Check:

bash
rdc gpus --json     # GPU capabilities
rdc counters --list # Available counters (empty if not supported)

Command Reference

For the complete list of all 66 commands with arguments, options, types, and defaults, see references/commands-quick-ref.md.

For extended debugging recipes with expected output shapes, see references/debugging-recipes.md.

© rudybear, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .claude/skills/renderdoc-gpu-debug of rudybear/renderdoc-skill.

  • SKILL.md
  • references/commands-quick-ref.md
  • references/debugging-recipes.md

Open the folder on GitHubat commit de33576

Compare with similar skills

Renderdoc GPU Debug next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Renderdoc GPU Debug compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Renderdoc GPU Debug this skillrudybear/renderdoc-skill211—~4kAutomated safety check: PassMIT
Electron DevTools Trace Analysiskeybase/client9.3k—~809Automated safety check: PassBSD-3-Clause
React Performanceaffaan-m/ECC274k1 repos~4.5kAutomated safety check: PassMIT
Fullstack Devinfometa/workbuddyskills342—~1kAutomated safety check: PassMIT
LangBot Core Developmentlangbot-app/LangBot18k—~1.4kAutomated safety check: NotesApache-2.0
Code Review SkillRain-kl/OpenFlare288—~2.3kAutomated safety check: NotesMIT

Similar skills

  • Analyzes Chrome or Electron DevTools Performance trace exports with Python scripts to find where render time actually goes, without opening DevTools.

    9.3k GitHub stars~809 tokensUpdated today
    DevelopmentAuto-check passed
  • React Performance

    affaan-m/ECC

    React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills).

    274k GitHub starsUsed in 1 repo~4.5k tokens
    DevelopmentAuto-check passed
  • Fullstack Dev

    infometa/workbuddyskills

    Full-stack backend architecture and frontend-backend integration guide.

    342 GitHub stars~1k tokensUpdated today
    Backend & APIsAuto-check passed
  • LangBot Core Development

    langbot-app/LangBot

    Covers developing the LangBot core backend and web UI: dev setup, repo layout, API auth types, adding endpoints, migrations and keeping the MCP server in step.

    18k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check: notes
  • Code Review Skill

    Rain-kl/OpenFlare

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, PHP, Python, Django, Go, C/.NET, Kotlin, Swift, NestJS, C/C++, and more.

    288 GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check: notes
  • Shader for Interfaces

    v2space-labs/shader-for-interfaces

    Decides whether an interface effect belongs in CSS, SVG, Canvas 2D, WebGL or WebGPU, then builds, debugs and visually verifies focused GPU effects inside product UIs.

    115 GitHub stars~3.1k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed

Works with

Questions about Renderdoc GPU Debug

What does Renderdoc GPU Debug do?

GPU frame debugging with RenderDoc via rdc-cli. An agent skill from rudybear/renderdoc-skill. Renderdoc GPU Debug is an agent skill from rudybear/renderdoc-skill. GPU frame debugging with RenderDoc via rdc-cli.

When should I use Renderdoc GPU Debug?

Renderdoc GPU Debug fits situations like: the user mentions: GPU debugging; rendering artifacts; shadow problems; visual glitches.

How do I install Renderdoc GPU Debug in Claude Code?

Run `npx skills add rudybear/renderdoc-skill --skill renderdoc-gpu-debug -a claude-code`. Or copy the skill folder (.claude/skills/renderdoc-gpu-debug in rudybear/renderdoc-skill) into .claude/skills/renderdoc-gpu-debug in your project. Claude Code loads it when a task matches its description.

How do I install Renderdoc GPU Debug in Codex?

Run `npx skills add rudybear/renderdoc-skill --skill renderdoc-gpu-debug -a codex`. Or copy the skill folder (.claude/skills/renderdoc-gpu-debug in rudybear/renderdoc-skill) into .agents/skills/renderdoc-gpu-debug in your project. Codex loads it when a task matches its description.

Can I use Renderdoc GPU Debug in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rudybear/renderdoc-skill --skill renderdoc-gpu-debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/renderdoc-gpu-debug, .gemini/skills/renderdoc-gpu-debug, .github/skills/renderdoc-gpu-debug and .opencode/skills/renderdoc-gpu-debug in your project.

What does Renderdoc GPU Debug need to run?

Going by SKILL.md and its folder, Renderdoc GPU Debug needs the command-line tools its instructions call (jq, python and pip). Our summary lists: Python 3.

Does Renderdoc GPU Debug access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Renderdoc GPU Debug safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Renderdoc GPU Debug use?

Renderdoc GPU Debug is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Renderdoc GPU Debug use?

About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.3k tokens, read only when the agent opens those files.

What are the alternatives to Renderdoc GPU Debug?

Skills that share tags, products or a category with Renderdoc GPU Debug: Electron DevTools Trace Analysis (keybase/client, 9.3k stars), React Performance (affaan-m/ECC, 274k stars), Fullstack Dev (infometa/workbuddyskills, 342 stars) and LangBot Core Development (langbot-app/LangBot, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Renderdoc GPU Debug?

rudybear (a GitHub user) maintains it in rudybear/renderdoc-skill, which has 211 GitHub stars. The repository was last updated on February 28, 2026.

Source: rudybear/renderdoc-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.