Skip to content

hashgraph-online/awesome-codex-plugins / plugins/AUN-PN/unity-agent-workflows/skills/unity-agent-workflows

unity-agent-workflows

Verified

Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first content changes, validation, cleanup proof, or durable workflow rules. Best when agents must prove the actual folder/module/scene/prefab/runtime owner before editing, especially runtime UI, generated assets, code graphs, tutorial/state flows, guided selection/action flows, overlay/dim source-bound mistakes, coordinate conversions, focus/highlight/marker/HUD alignment, predictive lead aiming, ballistic trajectories, spatial IoU verification, or repeated "fix still not visible" failures.

references/session-mining.md

View on GitHub
# Session Mining

Use this when asked to turn prior AI work, chat history, or project lessons into a reusable skill or durable workflow.

## Principles

- Mine repeated patterns, not raw chat.
- Keep private code, screenshots, stack dumps, and proprietary details out of reusable public artifacts.
- Separate collaboration preferences from architecture rules.
- Put each durable rule in the artifact that owns it.
- Treat memory as a lead; verify live files when the fact can drift.

## Structural Parsing

For Codex-style JSONL sessions:

- `session_meta.payload.id` identifies the session.
- `session_meta.payload.cwd` and `turn_context.payload.cwd` identify repo-scoped turns.
- `response_item.payload.type == "message"` and `role == "user"` contains user prompts.
- Filter out injected `AGENTS.md`, environment blocks, plugin lists, base64 images, and tool metadata.

Use native tools if shell wrappers distort counts:

```bash
/usr/bin/find /path/to/sessions -name '*.jsonl' | /usr/bin/wc -l
```

## Classification Buckets

- Collaboration/status/tone -> collaboration skill or repo instructions.
- Screenshot/UI/repeated visual failure -> runtime-owner proof and UI workflow.
- Visual source asset rules -> visual asset workflow.
- Structural C#/refactor rules -> modular architecture workflow.
- Validation/runtime doubts -> validation workflow.
- Cleanup/deletion -> cleanup workflow.
- Gameplay balance/content -> content/system workflow.
- Git/publish -> git workflow.

## Rule Update Workflow

1. Count and describe scan scope.
2. Filter to relevant repo/project turns unless user asks cross-project.
3. Group repeated failures and successful fixes.
4. Convert each lesson into a short reusable rule.
5. Patch only the owning artifact.
6. Validate docs/skill frontmatter and `git diff --check`.
7. Report scan scope, changed artifacts, and what was intentionally excluded.

## Do Not Include

- raw private prompts
- proprietary source code
- base64 images
- secrets, tokens, email, account IDs
- one-off user frustration as a permanent rule without repeated evidence
- stale runtime maps that should live in current architecture docs
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 321kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 197kUpdated Claude CodeCodexVerifiedInstall