myths-labs/muse

🌀 MUSE — Memory-Unified Skills & Execution. A pure-Markdown OS for AI pair programming with lossless cross-conversation context management.

This repository also configures its own agents. See what muse tells them →

32Stars on the repository
81Mods indexed here, across every type
5d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

planner-agent

49

myths-labs/muse

Skill Claude CodeCodex

Feature implementation planning agent. Transforms requirements into detailed implementation plans.

not rated 32 5d ago A 16 tokens original MIT

ralph-wiggum

50

myths-labs/muse

Skill Claude CodeCodex

Implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.

not rated 32 5d ago A SkillSpector: pass 0 tokens original MIT

myths-labs/muse

Skill Claude CodeCodex

Code review requires technical evaluation, not emotional performance.

not rated 32 5d ago A 9 tokens original MIT

myths-labs/muse

Skill Claude CodeCodex

Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

not rated 32 5d ago A 22 tokens copy · 81% MIT

sciomc

53

myths-labs/muse

Skill Claude Code

Orchestrate parallel scientist agents for comprehensive analysis with AUTO mode.

not rated 32 5d ago A SkillSpector: pass 17 tokens original MIT

security-review

54

myths-labs/muse

Skill Claude CodeCodex

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

not rated 32 5d ago A 36 tokens copy · 95% MIT

skill-creator

55

myths-labs/muse

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

not rated 32 5d ago A 45 tokens copy · 88% MIT

skills-updater

56

myths-labs/muse

Skill Claude Code

Check and update installed Claude Code skills from multiple sources (Claude plugins and npx skills). Scans for available updates, supports batch or individual updates with intelligent local change merging, and recommends popular skills from skillsmp.com and skills.sh marketplaces. Use when users want to update skills…

not rated 32 5d ago A SkillSpector: warn 75 tokens original MIT

myths-labs/muse

Skill Claude CodeCodex

Fast iteration with two-stage review (spec compliance, then code quality).

not rated 32 5d ago A SkillSpector: warn 19 tokens original MIT

myths-labs/muse

Skill Claude CodeCodex

4-phase root cause process + passive behavior auto-detection + L1→L4 pressure escalation (includes root-cause-tracing, defense-in-depth, condition-based-waiting techniques).

not rated 32 5d ago A SkillSpector: warn 43 tokens original MIT

tdd-workflow

59

myths-labs/muse

Skill Claude CodeCodex

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

not rated 32 5d ago A 43 tokens copy · 100% MIT

theme-factory

60

myths-labs/muse

Skill Claude CodeCodex

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

not rated 32 5d ago A 62 tokens copy · 100% MIT

trace

61

myths-labs/muse

Skill Claude CodeCodex

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode.

not rated 32 5d ago A 18 tokens copy · 84% MIT

ui-ux-pro-max

62

myths-labs/muse

Skill Claude CodeCodex needs its repo

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design…

not rated 32 5d ago B 238 tokens copy · 100% MIT

webapp-testing

64

myths-labs/muse

Skill Claude CodeCodex

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

not rated 32 5d ago A 35 tokens copy · 98% MIT

writing-plans

65

myths-labs/muse

Skill Claude CodeCodex

Use when you have a spec or requirements for a multi-step task, before touching code.

not rated 32 5d ago A 21 tokens copy · 100% MIT

muse-commands

66

myths-labs/muse

Skill Claude CodeCodex

Run MUSE /resume, /save and /bye for continuous work in Codex or Claude Code, preserving the selected role, Lane, decisions and source evidence across sessions.

not rated 32 5d ago A 40 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: