yorky
Skill0 starsChanged 40 days agoMITView on GitHub
Yorkie v1.1 is the short callable name for yorkshire-pudding: translate prose, jokes, READMEs, long accurate documents, comments, docstrings, and code into authentic Yorkshire dialect at three gravy levels without breaking code. Use for Yorkshire speak, "yorkshirify", yorky, or Yorkie requests.
In this repository10 other files it gives its agents.
- dom-ttsSkill
- mommSkill
- multi-llm-reviewSkill
- myautonessSkill
- myrepoSkill
- myskillsSkill
- mytravelSkill
- myvoiceSkill
- promptus-clone-voiceSkill
- yorkshire-puddingSkill
The file
Files
Yorkie v1.1 → yorkshire-pudding
yorky is the short, callable name for the yorkshire-pudding skill, publicly presented as Yorkie v1.1. Follow that skill's full protocol — it is the canonical source.
The zero-dependency translator lives in the canonical skill. Resolve its path from the installed skills directory (not relative to your current working directory, which varies):
node <skills-dir>/yorkshire-pudding/scripts/yorkshirify.mjs --level proper --input <file>On a standard install that is ~/.agents/skills/yorkshire-pudding/scripts/yorkshirify.mjs (Codex/Agent Skills) or ~/.claude/skills/yorkshire-pudding/scripts/yorkshirify.mjs (Claude Code). Text can also be piped on stdin instead of using --input.
Safety rules (non-negotiable, from the canonical skill): identifiers, keys, URLs, placeholders, imports, and program logic are never touched — only human-readable prose is translated. Three gravy levels: mild, proper, broad.
For international or academic readers and extremely long documents, also follow the canonical long-form guide. See yorkshire-pudding/SKILL.md for the complete dialect guide, zone rules, and examples.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.