validate-urp-render-graph-renderer-feature
An agent skill by Unity-Technologies, from Unity-Technologies/unity-agent-plugin. Tags: code-review, debugging, render-graph, urp, validation.
What it does
Use when the user wants to review or validate a Unity 6+ URP ScriptableRendererFeature that uses the Render Graph API. Checks for correctness issues - resource wiring, material binding, execution structure, descriptor usage, global resource exposure, and Render Graph best practices.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add Unity-Technologies/unity-agent-plugin --skill validate-urp-render-graph-renderer-feature
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/Unity-Technologies/unity-agent-plugin
cp -r unity-agent-plugin/skills/validate-urp-render-graph-renderer-feature ~/.claude/skills/validate-urp-render-graph-renderer-feature
Safety box score
Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-15. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is documentation-only: it reviews Unity URP Render Graph renderer-feature code and does not ship executable scripts, installers, or networked components. The main limitation is scope, not machine risk: it is an opinionated checklist that can miss issues outside the listed render-graph patterns.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | The only shipped file is `SKILL.md`; there are no shell scripts, binaries, or code that could execute on the machine. |
| Network access | 0 (none) | No downloads, API calls, or remote data transfers are defined in the skill files. |
| Filesystem reach | 0 (none) | The skill describes code review behavior only and does not read, write, or delete files on the user's machine. |
| Secrets & credentials | 0 (none) | There is no handling of tokens, keys, passwords, `.env` files, or credential stores. |
| Privilege & persistence | 0 (none) | Nothing in the skill requests sudo, installs services, or changes OS/shell settings. |
| Instruction hijack surface | 0 (none) | The file contains a normal validation checklist and does not tell the agent to ignore instructions, hide actions, or follow remote content. |
| Irreversible actions | 0 (none) | The skill is advisory only; it does not push, deploy, post, pay, book, or delete anything. |
| Transparency | 0 (none) | There are no binaries, minified blobs, or runtime-downloaded code; the full content is readable in `SKILL.md`. |
Before installing
- Confirm the skill folder contains only `SKILL.md` and no companion scripts or binaries.
- Check that its checklist matches your Unity/URP version and the Render Graph APIs you actually use.
- If you want to assess usefulness, try it on a non-production renderer feature first to see whether its opinionated checks fit your workflow.
Rated 2026-10-15 by an automated review of 1 file from the skill's repository.
Source
- Repository
- Unity-Technologies/unity-agent-plugin (all skills from this repository)
- Path
- skills/validate-urp-render-graph-renderer-feature/SKILL.md
- Branch
- main
- Updated
- 2026-09-22
Related skills
- thermo-nuclear-review — Comprehensive security and correctness audit of a branch's changes.
- blast-radius — Find what a change could break somewhere else before it ships, beyond the diff.
- check-compiler-errors — Run compile and type-check commands and report failures
- control-cli — Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services.
- control-ui — Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI.
- debug-voice — Use when the user runs /debug-voice, says voice mode has flaws, asks to see or capture what happened in a Grok realtime voice session.