Updated 2mo ago
by Jakeschincariol
claude-illegal-codes
Five Claude Code skills that feel illegal to know: /china-maxing, /aura-farming, /67, /crash-out, /larp
32 GitHub stars (32)
+11 in 5 days
| Period | New stars |
|---|---|
| Oct 12 | +1 |
| Oct 13 | +1 |
| Oct 14 | +3 |
| Oct 15 | +2 |
| Oct 16 | +4 |
- 5 skills (5 skills found in its SKILL.md files)
- 12 forks (12 forks)
- 2mo ago last update (Last updated 2mo ago)
Install
Skills CLI
npx skills add Jakeschincariol/claude-illegal-codes
Asks which skills and agents to install. Just one: npx skills add Jakeschincariol/claude-illegal-codes --skill 67 — add -g for every project.
Claude Code
git clone https://github.com/Jakeschincariol/claude-illegal-codescp -r "claude-illegal-codes/67" ~/.claude/skills/
Copies the 67 skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Jakeschincariol/claude-illegal-codes
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
67
Runs the task through six agents in parallel, each locked to a different strategy, then a seventh judge ranks the six attempts and synthesizes a final answer that steals the strongest part of each; invoke via /67 for high-stakes or open-ended work where a single attempt would leave quality on the table.
67/SKILL.md on GitHub (opens in a new tab) -
aura-farming
Maximum-aesthetic mode for any visual deliverable (Meta ads, slide decks, landing pages, social graphics, posters, UI) that bans every AI-slop tell, forces a real design direction, and audits the result before shipping; invoke via /aura-farming whenever a visual is being created and it needs to look like a designer made it.
aura-farming/SKILL.md on GitHub (opens in a new tab) -
china-maxing
Session mode that translates every sub-agent prompt into Mandarin before dispatch (more meaning per character, fewer tokens) while keeping code, identifiers, and all user-facing output in English; invoke via /china-maxing at the start of any session that will fan out sub-agents and the token bill matters.
china-maxing/SKILL.md on GitHub (opens in a new tab) -
crash-out
Anti-hallucination mode where Claude drafts an answer and then becomes obsessed with proving itself wrong, attacking every claim with tools and counter-evidence and shipping only what survives; invoke via /crash-out on factual questions, debugging, research, or any answer where confident-and-wrong is expensive.
crash-out/SKILL.md on GitHub (opens in a new tab) -
larp
Startup idea analyzer that channels a 24-year-old founder with Euro Summer photos and a $100M raise for a ChatGPT wrapper, runs the idea through a rigorous teardown underneath the bit, and assembles the strongest possible business model and pitch; invoke via /larp when the user shares a business, app, or product idea worth pressure-testing.
larp/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.