uw-skill-creator

uw-skill-creator is a skill for Claude Code, Codex from devdavv/unity-ai-workflow. It costs 66 tokens per session (7,243 once invoked), scanned A, a copy of skill-creator, MIT.

A skill-development workflow for creating, editing, and improving coding-agent skills. It combines draft writing, test prompts, repeated reviews, and measured evaluations.

In plain words
What is it for?
Use it to create a skill from scratch, revise an existing one, test it with example prompts, benchmark alternatives, or improve its description so it triggers more accurately.
Why use it?
It gives skill authors a structured way to find unclear instructions, triggering problems, and weak results. Repeated testing helps show whether a change actually improves the skill.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/devdavv/unity-ai-workflow/uw-skill-creator
Any agent
npx skills add devdavv/unity-ai-workflow --skill uw-skill-creator
Clone the repo
git clone --depth 1 https://github.com/devdavv/unity-ai-workflow

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for uw-skill-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/devdavv/unity-ai-workflow/uw-skill-creator.svg)](https://agentmods.dev/skills/devdavv/unity-ai-workflow/uw-skill-creator)
Your own site
<a href="https://agentmods.dev/skills/devdavv/unity-ai-workflow/uw-skill-creator"><img src="https://agentmods.dev/badge/skills/devdavv/unity-ai-workflow/uw-skill-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.07243
Opus 5 $0.00033 $0.03622
Sonnet 5 $0.00013 $0.01449
Haiku 4.5 $0.00007 $0.00724

Measured 3d ago against content hash 7e74454bbf90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

uw-skill-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (eval-viewer/generate_review.py, scripts/__init__.py, scripts/aggregate_benchmark.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

86% identical to skill-creator — 51 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/uw-skill-creator/SKILL.md · 486 lines

How it starts

The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator

A skill for creating new skills and iteratively improving them.

At a high level, the process of creating a skill goes like this:

  • Decide what you want the skill to do and roughly how it should do it
  • Write a draft of the skill
  • Create a few test prompts and run claude-with-access-to-the-skill on them
  • Help the user evaluate the results both qualitatively and quantitatively
    • While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
    • Use the eval-viewer/generate_review.py script to show the user the results for them to look at, and also let them look at the quantitative metrics
  • Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
  • Repeat until you're satisfied
  • Expand the test set and try again at larger scale

Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.

On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.

Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.

Then after the skill is done (but again, the order is flexible), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.

Cool? Cool.

Communicating with the user

Read the full file on GitHub · 486 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 486 lines · 66 tokens per session scan A 7e74454bbf90

Subscribe to this mod's changes

uw-skill-creator is a skill published in the GitHub repository devdavv/unity-ai-workflow (41 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 7,243 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to skill-creator, differing in 51 lines, and is treated as a copy.

Related

Other skills, from other repositories

game-ui-workflow

Orchestrates an end-to-end game UI workflow from game design (GDD), PRD, and UI interaction logic through design specification, screen-system extension, page image generation, component breakdown, sprite-sheet splitting, PNG ZIP packaging, atlas packing, engine JSON handoff, asset registration, and validation. Use…

guiguiyan930-source/game-ui-design-workflow · 94 tokens

game-ui-product-design

Writes and maintains game design docs (GDD), product requirements (PRD), and UI interaction logic before any page image generation. Use when users ask for 游戏策划方案、PRD、产品需求、UI交互逻辑、交互流程、状态机, or say to finish planning before generating UI visuals / 生图前先做策划.

guiguiyan930-source/game-ui-design-workflow · 78 tokens

game-ui-sprite-sheet-splitter

Splits a generated game UI sprite sheet or component board into individual transparent PNG elements, writes crop metadata, validates dimensions and alpha channels, and packages all PNG files into a ZIP archive. Use after component breakdown when users ask to cut a combined sprite sheet, isolate every…

guiguiyan930-source/game-ui-design-workflow · 85 tokens

game-ui-component-breakdown

Breaks an approved game UI page or visual style into reusable, individually generated component assets with clean edges, transparent backgrounds where appropriate, stable naming, states, dimensions, prompts, and traceable manifest records. Use for UI slicing, transparent buttons, icons, cards, modals, navigation…

guiguiyan930-source/game-ui-design-workflow · 79 tokens

game-ui-page-generator

Designs and generates one complete game UI page at a time using an approved style and screen contract, producing a page brief, reproducible image prompt, negative constraints, an actual visual asset when image generation is available, and a manifest entry. Use for home, task, ranking, shop, inventory, character…

guiguiyan930-source/game-ui-design-workflow · 84 tokens

game-ui-asset-pipeline

Packs semantically named transparent game UI PNG files into an atlas, preserves component states and reviewed 9-slice metadata, and exports deterministic JSON handoff manifests for Godot, Unity, Cocos, or generic consumers. Use after sprite-sheet splitting when users ask for atlas packing, nine-patch metadata, engine…

guiguiyan930-source/game-ui-design-workflow · 92 tokens