SkillAgentSearch skills...

unity-agent-workflows

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…

Install / Use

npx skills add hashgraph-online/awesome-codex-plugins --skill unity-agent-workflows

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

93/100

Category

Automation

Supported Platforms

Universal

Tags

Our assessment of unity-agent-workflows

unity-agent-workflows scores 93/100 on our quality scale, 711th of 2,790 Automation skills we index (top 26%).

Its SKILL.md is 21 KB long, well organised into 9 sections with 7 code examples: a thorough specification that gives an agent plenty to work with.

With 1,075 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so unity-agent-workflows is actively maintained.
  • Our last check on 2026-10-25 found the source still online.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

unity-agent-workflows compared with similar skills

All 4 of these similar skills score higher than unity-agent-workflows; compare them before choosing.

SkillScoreStarsUpdatedFormat
unity-agent-workflows (this skill)by hashgraph-online931.1k53d agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md
Scraplingby D4Vinci100103.6k2d agoMCP Server

Frequently asked questions

How do I install unity-agent-workflows?
Run npx skills add hashgraph-online/awesome-codex-plugins --skill unity-agent-workflows. The install tabs above show the steps for each supported agent.
Which AI agents does unity-agent-workflows work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is unity-agent-workflows safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is unity-agent-workflows still maintained?
The repository was last updated about 2 months ago, so unity-agent-workflows is actively maintained.

name: unity-agent-workflows description: 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. license: MIT

Unity Agent Workflows

AI contract for Unity work. Keep answers compact, but never remove exact paths, object/class names, commands, errors, validation, rollback notes, or proof requirements.

Core Loop

  1. No proof, no edit.
  2. Treat this injected SKILL.md as authoritative; do not search for its own path unless missing or asked for diagnostics.
  3. Read live project instructions narrowly: AGENTS.md if present, git status --short, and existing UNITY_STRUCTURE.md plus only the focused map that matches the task when available. Read README.md, architecture docs, .agents/*, or repo-local agent files only when the task cites them, needs architecture/new-file/asmdef/routing decisions, or maps are missing/stale.
  4. Run git status --short; preserve unrelated dirty files.
  5. If user says only $unity-agent-workflows. Teach, run Teach.
  6. Derive only relevant live structure before architecture claims: folders, namespaces, .asmdef, scenes/prefabs, bootstraps, graphs, docs, UNITY_STRUCTURE*.
  7. Classify task with Task Gate, then load required references before edits.
  8. Inspect real owner files; never start from memory, nearest-name guessing, semantic similarity, or screenshot proximity alone.
  9. Fill useful Routing Card fields for structure, visible output, state flow, multi-agent, or hub changes.
  10. Patch the smallest proven owner/artifact.
  11. Validate, sync mirrors if package skill files changed, then close out with proof.

Task Gate

| Trigger | Required action | |---|---| | Runtime/visible bug | Prove owner chain before editing. | | Runtime-visible output, target alignment, focus/highlight/marker/HUD, overlay, input blocker, modal dimming, duplicate names, hardcoded layout, "do not guess" | Runtime Visible Output Hard Stop. | | Screenshot or visible UI text fix | Screenshot Text Owner Gate; search exact visible text/localization key and prove creator plus refresh writer before editing. | | Visual/model/sprite/asset integration where feature name, source asset, factory, or visible surface may disagree | Visible Object Identity Lock, Multi-Surface Visible Behavior Lock, and Single-Agent Anti-Anchoring Guard before editing. | | Same visible behavior requested across multiple scenes/surfaces, or words like "also", "after transition", "menu and gameplay", "preview and runtime", "scene A and scene B" | Multi-Surface Visible Behavior Lock; prove each surface owner, active caller, asset/factory dependency, and fallback behavior before editing any surface. | | Shared factory/helper/style/global method candidate for a scoped visible surface | Shared Caller Blast Radius Gate: prove allowed runtime caller(s), all other callers, and whether the patch is surface-local before editing. | | Overlay/dim source-bound mistakes | Prove source target bounds; overlay/dim/mask/blocker rects are destination output unless explicit marker proof exists. | | Predictive aim, turret targeting, ballistic trajectory with drag, collision tunneling, CCD, proportional navigation (TPN), physics movement | Kinematic predictive intercept, drag ballistics, and TPN equations in references/runtime-numeric-proof.md; solve 2nd-order quadratic intercept with CPA fallback. | | 2D game physics, 2D platformer jump apex/gravity, Rigidbody2D drag, Box2D tunneling/Continuous Collision Detection (CCD), 2D predictive lead intercept, 2D steering/TPN, 2D orthographic camera, ScreenToWorldPoint z-plane distance, RectTransform in Canvas 2D (Overlay camera null & World Space 1/PPU scale), 2D pixel-perfect PPU snapping, Tilemap cell-to-world pivot | 2D kinematic equations, Box2D drag damping, 2D parabolic jump kinematics ($g = 2h/t_{\text{apex}}^2$), Orthographic projection, 2D Canvas RectTransform invariants, 2D CCD raycast, and Tilemap half-tile pivot invariants in references/coordinate-space-conversion.md and references/runtime-numeric-proof.md. | | Offscreen pointer, behind-camera target, near-clip singularity, optical axis degeneracy, 3D bounds frustum clipping, CanvasScaler aspect drift, stretch anchor mismatch | Projective geometry, near-clip plane w <= 0 clamping, optical axis guard, Sutherland-Hodgman 3D near-plane clipping, CanvasScaler log formula, and RectTransform invariants in references/coordinate-space-conversion.md. | | Quaternion rotation flip, gimbal lock, Euler snap, rotational slerp/nlerp, symplectic physics stability | Quaternion antipodal shortest-path condition (q1·q2 < 0), small-angle Nlerp fallback, and Symplectic Euler integration in references/runtime-numeric-proof.md. | | Focus ring / UI overlay alignment precision, quantitative spatial verification | Intersection over Union (IoU >= 0.95) and sub-pixel tolerance in references/runtime-numeric-proof.md. | | Repeated visible-output mismatch after patch | Runtime numeric proof before another coordinate/layout/fallback patch. | | Multi-agent visible-output or state work | Sub-agent decision and permission gate first; main-agent scope lock before workers patch; checker must review. | | New/moved files, expanded C# responsibility, asmdef/module routing, hub deflation | Project-derived routing, no fixed structure, hub stop gate. | | UI, screenshot, HUD, menu, safe area, TMP, spotlight, item-based UI assembly, picked UI parts, UI slices, extracted UI parts, textless UI sprites, design manifests | UI workflow plus runtime-owner proof, extracted item assembly proof, and validation. | | Visual source asset | Source asset/generator gate before Unity integration code. | | Content, progression, economy, levels, objectives, gameplay tuning | Data-first content workflow. | | Tutorial, onboarding, objective, unlock, selection, action, navigation, state transition, guided selection/action flows | State-step guards. | | Compile/runtime doubt, stale Bee/Roslyn response files, Play Mode proof | Validation workflow. | | Cleanup/deletion/generated files/git hygiene | Cleanup proof. | | Rule/session mining/workflow update | Patch only the owning artifact. |

Required References

Load only matching files; resolve relative to this skill directory. If a required reference is missing, stop broad edits, use only visible rules here, and report References missing:.

| Task trigger | References before editing | |---|---| | UI, screenshot, HUD, menu, safe area, TMP, visible target, focus, highlight, spotlight, modal dimming, item-based UI assembly, picked UI parts, UI slices, extracted UI parts, textless UI sprites, design manifests | references/ui-and-visual-assets.md, references/runtime-owner-proof.md, then only needed visible/text/output details | | Screenshot text, visible UI label, localized UI text, runtime text styling, shared factory/helper candidate | references/runtime-owner-proof.md, references/screenshot-text-owner.md, references/ai-workflows.md | | Visual/model/sprite/asset integration where feature name, source asset, factory, or visible surface may disagree | references/runtime-owner-proof.md, references/visible-object-identity.md, references/asset-source-lock.md, references/ui-and-visual-assets.md | | Shared factory/helper/style/global method candidate for a scoped visible surface | references/runtime-owner-proof.md, references/shared-caller-blast-radius.md, references/ai-workflows.md | | Runtime-visible bug, repeated "still wrong", duplicate object names, real object/position request | references/runtime-owner-proof.md | | Overlay/dim source-bound mismatch, wrong source bounds, focus hole follows wrong target | references/runtime-owner-proof.md, references/runtime-visible-output.md, references/runtime-visible-targets.md, references/coordinate-space-conversion.md | | Repeated visible-output failure, wrong focus/highlight/marker/HUD/camera position, cross-root/cross-canvas mismatch | references/runtime-owner-proof.md, references/runtime-visible-output.md, references/runtime-numeric-proof.md, then only needed target/conversion details | | Same visible behavior across menu/gameplay/preview/runtime/transition/scene surfaces | references/runtime-owner-proof.md, references/multi-surface-visible.md, references/asset-source-lock.md | | Serialized scene object, prefab asset, prefab instance, prefab variant, component fields, object refs, editor tooling | references/runtime-owner-proof.md, references/serialized-persistence.md | | Multi-agent Unity visible-output/state-transition work, parallel workers, checker review | references/ai-workflows.md plus only the references for the actual visible surface or state flow | | New files/classes, moved scripts, asmdef/module routing, dependency direction, hub deflation/refactor | references/project-structure-discovery.md, references/modular-architecture.md, references/ai-workflows.md | | New runtime feature, content, progression, levels, economy, objective/data-first work | references/project-structure-discovery.md, references/content-and-systems.md, references/ai-workflows.md | | Tutorial, onboarding, objective step, unlock, selection/action step, navigation gate, state transition | references/project-structure-discovery.md, references/content-and-systems.md, references/ai-workflows.md, references/unity-validation.md | | Compile error, validation repair, stale Bee/Roslyn response files, Play Mode proof | references/unity-validation.md | | Cleanup/deletion/generated files/git hygiene | references/cleanup-and-git.md | | Rule/session mining/workflow update | references/session-mining.md |

Reference map: references/ai-workflows.md = Routing Card/workflow/closeout; references/workflow-recipes.md = named recipes; references/project-structure-discovery.md = Teach and UNITY_STRUCTURE*; references/modular-architecture.md = layering/asmdef/hub gates; references/runtime-owner-proof.md = core owner chain/router; references/visible-object-identity.md = competing visible owners/anti-anchoring; references/multi-surface-visible.md = menu/gameplay/preview/runtime surface proof; references/asset-source-lock.md = asset variants/source ID locks; references/screenshot-text-owner.md = visible text/TMP/localization owner proof; references/shared-caller-blast-radius.md = shared helper/factory caller proof; references/runtime-visible-output.md = output hard stop/hardcoded layout guard; references/runtime-numeric-proof.md = repeated visible mismatch numeric proof; references/serialized-persistence.md = scene/prefab serialized persistence; references/runtime-visible-targets.md = focus/click/overlay/fallback target rules; references/target-bounds-catalog.md = markerRect/visualRect/interactiveRect choices; references/coordinate-space-conversion.md = world/screen/canvas/camera/safe-area conversions; references/unity-validation.md = validation ladder/checker failures; references/ui-and-visual-assets.md = UI/safe area/visual asset gate; references/content-and-systems.md = data-first systems/state steps; references/cleanup-and-git.md = deletion/git hygiene; references/session-mining.md = durable rules.

Load references/unity-validation.md only

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars1.1k
CategoryAutomation
Updated1mo ago
Forks294

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions
unity-agent-workflows — Universal Skill: Install & Safety Check | SkillAgent