Run pre-mortem stress tests, simulate first-time user onboarding, and audit product naming and identity to strengthen design clarity and emotional coherence
This skill should be used when the user wants to pressure-test a feature, flow, or product idea by generating emotionally concrete future failure artifacts such as support tickets, angry emails, user complaints, one-star reviews, or postmortem fragments. Responds to "what could go wrong", "stress test this", "write a pre-mortem", "show me how this fails", "what would the support tickets look like", "pressure test this flow", or any request to make abstract risk viscerally real before or during design.
This skill should be used when the user wants a first-time user simulation — a cold-start walkthrough from the perspective of someone with zero context, zero author knowledge, and zero sympathy for what the builders intended. Responds to "pretend you're a new user", "do a first-contact pass", "test the onboarding", "is this obvious to a newcomer", "what would a stranger see here", "ghost user this", or any request to check whether the product relies on inside knowledge.
This skill should be used when the user wants to define a project's identity, build a lorebook, articulate what a product believes and refuses to become, or capture the implicit rules a project lives by. Responds to "what is this project trying to be", "the product is drifting", "write down the project values", "give this project a spine", "build a lorebook", or any moment when naming, tone, scope, or product identity feel undefined or are starting to drift.
This skill should be used when the user wants to audit, clean up, or redesign the naming in a product, workflow, or system — treating names as structural design decisions, not editorial polish. Responds to "the naming is a mess", "we call the same thing three different names", "clean up the terminology", "what should we call this", "the API and UI use different words", or any situation where muddy, overlapping, or conflicting names are distorting the user's mental model.
This skill should be used when the user wants to understand why a product, interface, writing style, or codebase feels unusually good, or to extract the hidden governing rules behind a reference. Responds to "I like this but I can't explain why", "what makes this work", "extract the design principles", "distill the taste", "what rules is this obeying", or any request to learn from a reference without copying it.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A small, sharp marketplace of Claude Code skills that punch above their weight.
Instead of shipping a pile of half-maintained bundles, this repo now centers one curated plugin with a few high-leverage skills.
A curated Claude Code plugin built from a handful of high-leverage skills designed to unlock capabilities you didn't know you needed. The goal is to turn Claude from a generic assistant into a sharper specialist for research, creation, and execution.
The goal: Make you (and Claude) limitless.
| Plugin | What It Does |
|---|---|
| limitless | A curated Pyro skill pack: article generation, research, surface-first prototyping, and privacy-respecting web search. |
| after-hours | A calm, high-taste plugin for project identity, subtraction, naming, coherence, and first-contact honesty. |
In Claude Code, run:
/plugin marketplace add pyros-projects/limitless
/plugin # Browse available plugins
/plugin install limitless@limitless # Curated Pyro skill pack
/plugin install after-hours@limitless # Calm, wholesome product-intelligence skills
/plugin enable limitless@limitless # Enable
/plugin enable after-hours@limitless # Enable
/plugin disable limitless@limitless # Disable
/plugin disable after-hours@limitless # Disable
/plugin uninstall limitless@limitless # Uninstall
/plugin uninstall after-hours@limitless # Uninstall
"I don't have delusions of grandeur, I have an accurate assessment of my own abilities." — Eddie Morra, Limitless
These plugins embody:
The roadmap includes future skills or plugin branches for:
See docs/brainstorm/plugin-ideas.md for the full idea backlog.
MIT — see LICENSE.
"What would you do if you could do anything?"
npx claudepluginhub pyros-projects/limitless --plugin after-hoursPyro Kit — 17-skill creative lifecycle toolkit for solo developers. Idea excavation, design exploration, prototyping, contract derivation, vertical-slice building, momentum tracking, scope management, and anti-abandonment composting across a complete 7-phase project lifecycle.
Pyro's curated Claude Code skill pack: article-pack, Codies Research, Surface-First Development, SFD v2 (docket-emitting contract handoff), SearXNG, Suno Pack (lyric craft, inspiration audits, rendering, experiment lanes, saga-synced journals), Hivemind, Dojo, and James. A small set of high-leverage skills for research, prototyping, publishing, web search, AI music, verified skill authoring, and restartable planning docs.
File-based two-tier memory system for AI agents. Agent-namespaced vaults with promotion pipelines, trust levels, CLI write commands, and explicit _general read mode for vault-less notes. Gives any agent persistent memory across sessions.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.