claude

core

Project-agnostic tools: /ai-workflow-analyzer, /ai-slop, /council, /design-system, /model-advisor, /prompt-engineer, /qa, /pr-review.

0 on GitHubv0.6.0updated 12 days agoproductivity
/

Plugin core from marketplace smasetic in seomasha/skills. Commands read from the repo's manifest — 12 days ago.

What it installs

Skills (8)

  • ai-slop

    Use when the user runs /ai-slop to check whether a website project looks vibe-coded or AI-generated instead of properly engineered (missing 404, privacy policy, robots.txt, OG image, template copy, default purple gradients, leftover placeholders).

  • ai-workflow-analyzer

    Use when the user runs /ai-workflow-analyzer to check whether their Claude Code setup (MCPs, agents, skills, hooks, CLAUDE.md, rules, plugins) is redundant, duplicated, mis-scoped, or under-used for the current project.

  • council

    Stress-test a business idea with a four-agent council (Believer, Skeptic, Investor argue in parallel, then a Judge rules). Triggers on: /council, "run the council", "council this idea", "should I build this", "stress-test my business idea".

  • design-system

    Use when the user wants a design-system.md documenting a company's website look, feel, UX and motion (e.g. "/design-system Apple", "extract Stripe's design tokens", "document how Linear's site feels").

  • model-advisor

    Reads an implementation plan and recommends the best LLM model for each task. Brutally honest — recommends local Ollama models when they can genuinely handle the task, Claude only when the task actually needs it. Triggers on: "/model-advisor", "which model should I use", "model recommendation", "wha

  • pr-review

    Use when the user asks to review a GitHub pull request — "/pr-review", "/pr-review 42", "review PR 42", "review this PR", "re-review", "check if they addressed the comments" — including follow-up runs on a PR already reviewed.

  • prompt-engineer

    Use when /prompt-engineer is invoked, or when the user wants to craft, improve, or review a prompt for any LLM or system (Claude, GPT, Gemini, CLAUDE.md, agent skills, commands, etc.)

  • qa

    Use when asked to QA, smoke-test, click through, or exercise a product/web app end-to-end like a real user in the browser — "/qa", "/qa <url>", "/qa <flow>", "test it like a user", "find bugs in the app". Not for unit/integration tests or code review.

View source on GitHub

More from seomasha/skills

All 2 plugins →

linear

claude

/ship-ticket — Linear ticket to merged PR. Enable per project that uses Linear.

1 skill

0

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain core?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins