2d โข Discussion ๐ค
I Tried 100+ Claude Code Skills. These 6 Are The Best
(all install paths will be in the comments)
๐. ๐๐ค๐ข๐ฅ๐ฅ ๐๐ซ๐๐๐ญ๐จ๐ซ
this is the factory that builds everything else.
describe what you want in plain english โ claude builds the skill, tests it, packages it. you never have to write a skill.md by hand again. drop in an SOP and it becomes a reusable skill instantly.
install: /plugin install skill-creator
๐. ๐๐ฎ๐ฉ๐๐ซ๐ฉ๐จ๐ฐ๐๐ซ๐ฌ
fixes the #1 failure in claude code: rushed, sloppy output.
forces claude to plan first, work in isolation, write tests before code, then review its own work twice. gets you from 60% โ 80% on the first pass. fewer debugging cycles = less time, lower token costs.
150k+ stars on GitHub btw
๐. ๐๐๐ (๐๐๐ญ ๐๐ญ๐ฎ๐๐ ๐๐จ๐ง๐)
fixes context rot.
you know when claude starts forgetting requirements halfway through a session and cutting corners? GSD spawns fresh sub-agents for each task so your main session stays clean and every task gets a full context window. also has an autonomous mode if you want to hand it a spec and walk away.
๐. /๐ซ๐๐ฏ๐ข๐๐ฐ ๐๐ง๐ /๐ฎ๐ฅ๐ญ๐ซ๐ ๐ซ๐๐ฏ๐ข๐๐ฐ
already built into claude code. most people aren't using it.
/review = fast structured code review after you build something. free beyond normal tokens.
/ultra review = uploads your branch to a cloud sandbox, spins up parallel reviewer agents, each attacking from a different angle. bugs have to be independently verified before they hit your list. no false positives.
need claude code 2.1.86+. costs $5โ20/run after 3 free ones on Pro/Max.
๐. ๐๐จ๐ง๐ญ๐๐ฑ๐ญ ๐๐จ๐๐
keeps garbage out of your context window.
raw tool outputs get routed through a sandbox. a 56kb playwright snapshot becomes 299 bytes. 315kb of session output becomes 5kb total. also tracks every file edit, decision, and error in a local SQL database so when claude compacts the conversation, it doesn't lose anything.
sessions that used to fall apart at 30 minutes now run 3 hours clean.
๐. ๐๐ฅ๐๐ฎ๐๐๐๐๐ฆ
carries knowledge across every future session.
claude normally starts from scratch every time. ClaudeMem hooks into the session lifecycle, captures what happened, compresses it into semantic summaries stored in a local SQLite db with vector search, then injects the relevant parts back in when you open a new session. also auto-generates and updates your CLAUDE.md files while you work.
if you're new though don't install all 6 at once! pick one, build something with it, and show a business owner the output. they don't care about your process. they care about their 10 hours back.
This was helpful!
I've heard of these before, give me something better...
0
1 comment
I Tried 100+ Claude Code Skills. These 6 Are The Best
powered by
skool.com/the-ai-entrepreneur-circle-5658
Join elite entrepreneurs using AI to build apps, automations, and operating systems to reach financial freedom.
Suggested communities
Powered by