codex

Anti-AI Craft

Six reusable engineering skills plus a local evidence MCP with optional Graphify integration.

0 on GitHubby Zythenthv0.6.0updated 14 days agoProductivity

Plugin anti-ai-craft in Zythenth/anti-ai-craft. Commands read from the repo's manifest — 14 days ago.

What it installs

Skills (6)

  • anti-ai-audit

    Audit interfaces, accessibility, responsiveness, code, architecture, tests, documentation, states, and actual behavior in strictly read-only mode. Use only when explicitly invoked with a repository, path, diff, screenshots, or running interface; hand off approved findings to anti-ai-remediate instea

  • anti-ai-code

    Review or implement scoped code changes, avoiding unverifiable, fragile, invented, verbose, or overengineered behavior. Use when the request involves modules, diffs, tests, fixes, refactoring, or implementation requirements; do not use for purely visual design, a broad read-only audit, application o

  • anti-ai-design-flow

    Orchestrate a complete, resumable product journey, from briefing through information architecture, visual system, build plan, authorized implementation, review, and finding handoff. Use only when explicitly invoked to conduct three or more phases, coordinate two or more Anti-AI skills, start a featu

  • anti-ai-design

    Research, create briefs, plan information architecture or tokens, review, implement, or refactor contextual, outcome-oriented interfaces without automatically resorting to generic composition or manipulative tactics. Use when the request involves screenshots, wireframes, frontend, visual components,

  • anti-ai-remediate

    Apply only confirmed audit findings that are approved by the user, reproducible, and within the current scope. Use only when explicitly invoked with IDs or an approved report and authorization to edit; do not use for open-ended review, speculative cleanup, or unapproved fixes. Read the target state

  • anti-ai-security

    Analyze or fix the security of applications, APIs, services, infrastructure, and code changes, looking for missing or incomplete controls such as object- and tenant-level authorization, rate limiting, resource limits, validation, secret protection, sessions, business flows, and adversarial tests. Us

View source on GitHub

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

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

Maintain Anti-AI Craft?

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 pluginslisted