PostprocessSAFE
AI automation skills specifically designed for Unity
Overview
AI automation skills specifically designed for Unity
7635012e8e68OBSERVED · 2026-10-10What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: unity-postprocess
description: Configure modern SRP post-processing on URP/HDRP
---
> **Before calling any skill in this module:** if you are about to call a skill with parameters guessed from its name or description, STOP — read this file (or fetch its schema via `GET /skills/recommend?includeSchema=true`) first. If you already have the parameter definitions from recommend/schema, you may proceed straight to dryRun.
## Triggers
- Setting up post-processing
- Adding effects to a VolumeProfile
- Tuning URP/HDRP scene look
- 搭建后处理、向 VolumeProfile 添加效果、调整 URP/HDRP 场景观感
# PostProcess Skills
Modern URP / HDRP post-processing skills built on top of the SRP Volume framework. For Volume container / profile CRUD (`volume_profile_create`, `volume_create`, etc.), use the `volume` module.
## Operating Mode
- Query skills (`postprocess_list_effects`, `postprocess_get_effect`) are `SkillMode.SemiAuto` — they run in all three modes without grant.
- Mutating skills (`postprocess_add_effect`, `postprocess_set_parameter`, `postprocess_set_bloom`, `postprocess_set_depth_of_field`, `postprocess_set_tonemapping`, `postprocess_set_vignette`, `postprocess_set_color_adjustments`) are `SkillMode.FullAuto` — under **Approval** they need user grant (grant triggers one server-side execute returning the result); under **Auto** / **Bypass** they execute directly.
- `postprocess_remove_effect` carries `SkillOperation.Delete` and is **auto-forbidden** in Approval / Auto modes (NeverInSemi). Only **Bypass** or the user-managed **Allowlist** can run it.
## SRP Package Stub
This module is compiled against `com.unity.render-pipelines.core` (`SRP_CORE`). When neither URP nor HDRP is installed (no SRP Core), **every** skill returns a stub `{ error: "Scriptable Render Pipeline Core package ... is not installed." }` (`RenderPipelineSkillsCommon.NoSRP()`). The stub is a diagnostic payload, not a permission denial — it does **not** require grant and is **not** treated as NeverInSemi.
## Guardrails
**DO NOT**:
- Use this module for PPv2 / `com.unity.postprocessing`
- Use this module for general Volume container/profile management; use `volume`
**Runtime-first rules**:
- Always call `postprocess_list_effects` before assuming an effect exists on the active pipeline
- Use `postprocess_get_effect` or `volume_get_component` to inspect real parameter names before setting generic parameters
- Prefer the dedicated high-frequency skills (`postprocess_set_bloom`, `postprocess_set_depth_of_field`, etc.) over guessing generic parameter names
- Treat URP and HDRP parameter surfaces as similar-but-not-identical; do not reuse names blindly across pipelines
## Skills
### `postprocess_list_effects`
List modern SRP post-processing effects supported by the active pipeline.
### `postprocess_add_effect`
Add a post-processing effect override to a VolumeProfile.
### `postprocess_remove_effect`
Remove a post-processing effect override from a VolumeProfile.
### `postprocess_get_effect`
Inspect a post-processing effect override.
### `postprocess_set_parameter`
Set one parameter on a post-processing effect override.
### `postprocess_set_bloom`
Configure Bloom.
### `postprocess_set_depth_of_field`
Configure Depth Of Field.
### `postprocess_set_tonemapping`
Configure Tonemapping.
### `postprocess_set_vignette`
Configure Vignette.
### `postprocess_set_color_adjustments`
Configure Color Adjustments.
---
## Exact Signatures
Exact names, parameters, defaults, and returns are defined by `GET /skills/schema` or `unity_skills.get_skill_schema()`, not by this file.Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
7635012e8e68full audit observations/trust-audit/skill/besty0728__postprocess.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 7635012e8e68 | SAFE | B | 89 | first audit |
Questions
What does the Postprocess skill do?
AI automation skills specifically designed for Unity
Is Postprocess safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Postprocess access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (7635012e8e68), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.