renderdoc-performance-report
Generate an evidence-based RenderDoc performance and resource footprint report from the current capture.
Skill by Kirkice
Chalk Labs
Need help deploying renderdoc-performance-report?
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/kirkice-renderdoc-performance-report
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
Use cases: documents
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 and code. Checked Oct 26, 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/renderdoc-performance-report
What's inside
- Skill name
renderdoc-performance-report- Description
- Generate an evidence-based RenderDoc performance and resource footprint report from the current capture.
- License
- MIT
- Instructions
- 14 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# RenderDoc Performance Report 1. Resolve the current capture with `renderdoc_openCapture` when needed. 2. Call `renderdoc_getFrameSummary` and `renderdoc_getCaptureInfo` for context. 3. Call `renderdoc_generatePerformanceReport` for GPU-timed hotspots. 4. Call `renderdoc_resourceMemoryAudit` for the largest captured resources when memory pressure is relevant. 5. Drill into selected EIDs with event, shader, pipeline, mesh, and resource tools. 6. Preserve the evidence chain for every conclusion: EID, GPU timing, marker/pass path, resource IDs/byte sizes, pipeline state, shader identity, and mesh data when available. 7. Classify findings as confirmed, inferred, or toVerify. If timing, byte-size, replay, or native-bridge evidence is unavailable, state the limitation instead of estimating it. 8. For side-effecting report export, confirm the returned output path and format before claiming the report was written. Never call an event hot or expensive without timing evidence. Separate confirmed facts, likely causes, and follow-up validation.
From Kirkice/renderdoc-for-vscode, MIT.
More from Kirkice/renderdoc-for-vscode
- 0.617score
renderdoc-app-launch-capture
Kirkice
Launch a Windows executable or Android application through RenderDoc and capture a frame from the active session.
SkillBFreshness: B★ 44Claude Code +9 - 0.606score
renderdoc-shader-optimization
Kirkice
Review captured shader variants, bindings, source, and timing evidence to identify shader optimization opportunities.
SkillBFreshness: B★ 44Claude Code +9 - 0.567score
renderdoc-texture-trace
Kirkice
Trace how a texture is produced, consumed, and related to passes in a RenderDoc capture.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-current-selection-explainer
Kirkice
Explain the currently selected RenderDoc draw, event, or resource in practical terms.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-frame-overview
Kirkice
Summarize the structure of a RenderDoc capture and identify its top-level passes, markers, and likely inspection targets.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-performance-investigation
Kirkice
Investigate performance bottlenecks in a RenderDoc capture and explain which passes or draws are expensive and why.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-shader-review
Kirkice
Review shader behavior for a RenderDoc event, including stage roles, bindings, constant buffers, and likely issues.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-buffer-inspector
Kirkice
Inspect buffer resources and their contents in a RenderDoc capture, including raw bytes and event context.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-replay-recovery-helper
Kirkice
Recover from missing RenderDoc capture or replay state before attempting deeper analysis.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-pass-to-project-mapping
Kirkice
Map RenderDoc passes, events, and shaders back to likely project-side source files and implementation points.
SkillCFreshness: C★ 44Claude Code +9 - 0.556score
renderdoc-capture-diff
Kirkice
Compare two RenderDoc captures and explain metadata and resource footprint changes without inventing timing evidence.
SkillCFreshness: C★ 44Claude Code +9 - 0.303score
renderdoc-replay-diagnostics
Kirkice
No description from the publisher yet.
SkillCFreshness: C★ 44Claude Code +9
Signals
- Stars
- 44
- Forks
- 8
- Open issues
- 1
- Last commit (this folder)
- Jul 30, 2026 (3 months ago)
- Last release
- May 22, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Kirkice/renderdoc-for-vscode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Kirkice
- 0.617score
renderdoc-app-launch-capture
Kirkice
Launch a Windows executable or Android application through RenderDoc and capture a frame from the active session.
SkillBFreshness: B★ 44Claude Code +9 - 0.606score
renderdoc-shader-optimization
Kirkice
Review captured shader variants, bindings, source, and timing evidence to identify shader optimization opportunities.
SkillBFreshness: B★ 44Claude Code +9 - 0.567score
renderdoc-texture-trace
Kirkice
Trace how a texture is produced, consumed, and related to passes in a RenderDoc capture.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-current-selection-explainer
Kirkice
Explain the currently selected RenderDoc draw, event, or resource in practical terms.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-frame-overview
Kirkice
Summarize the structure of a RenderDoc capture and identify its top-level passes, markers, and likely inspection targets.
SkillCFreshness: C★ 44Claude Code +9 - 0.567score
renderdoc-performance-investigation
Kirkice
Investigate performance bottlenecks in a RenderDoc capture and explain which passes or draws are expensive and why.
SkillCFreshness: C★ 44Claude 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 renderdoc-performance-report 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
renderdoc-performance-report skill. Agent Mart. https://agentmart.dev/skills/kirkice-renderdoc-performance-report (last updated 2026-10-24)