Enables persistent memory for Claude Code across sessions using a file-based two-tier vault system with agent-namespaced storage, promotion pipelines, trust levels, and CLI write commands.
This skill should be used at session start, when entering a new project, or when the user says 'wake up', 'load memory', 'boot', 'memory-boot'. Assembles identity, procedural knowledge, project context, and recent session state into a boot packet from the agent's vault.
This skill should be used when the agent needs to save something to memory — observations, lessons, decisions, reflections, dreams, or past memories from external sources. Responds to 'remember this', 'capture', 'save to memory', 'I learned', 'note this down', or any request to persist information across sessions.
This skill should be used at end of session, when wrapping up work, or when the user says 'close session', 'end session', 'session summary', 'sign off'. Writes session summary, enforces inbox aging, evaluates pending promotions, and updates active context.
This skill should be used when the agent needs a reminder of what the memory system can do, what commands are available, or how the memory system works. Responds to 'memory help', 'what memory commands exist', 'how does my memory work', 'what can I remember', or any confusion about the memory system's capabilities. Also invoked by memory-boot after first boot to teach the agent the system.
This skill should be used when the agent needs to evaluate or promote memory records through the trust pipeline. Responds to 'promote', 'evaluate inbox', 'elevate trust', 'promote to global', or when inbox items have accumulated and need triage. Converts inbox items to threads/lessons, elevates trust levels, promotes project knowledge to global.
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.
A curated collection of Claude Code plugins — from research and content generation to full creative lifecycle management.
A curated Claude Code plugin marketplace with high-leverage skills designed to unlock capabilities you didn't know you needed. Four plugins covering research, content creation, product intelligence, creative lifecycle management, and persistent agent memory.
The goal: Make you (and Claude) limitless.
| Plugin | Skills | What It Does |
|---|---|---|
| limitless | 8 | Article generation, research, surface-first prototyping, privacy-respecting web search, Suno music packs with real rendering + experiment lanes, collective-brain search across social/GitHub/web/papers with saved sweep configs (hivemind), verified skill authoring (dojo), and persistent constrained review with recipes + review chains for self-contained planning docs (James). |
| after-hours | 7 | Calm, high-taste product intelligence: identity, subtraction, naming, coherence, and first-contact honesty. |
| pyro-kit | 17 | Complete 7-phase creative lifecycle: idea excavation, design exploration, prototyping, contracts, building, momentum tracking, and anti-abandonment composting. |
| codies-memory | 4 | Persistent agent memory with agent-namespaced vaults, promotion pipelines, trust levels, CLI write commands, and explicit _general read mode for vault-less notes. Requires uv sync setup — see INSTALL.md. |
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 install pyro-kit@limitless # Full creative lifecycle toolkit
/plugin install codies-memory@limitless # Persistent agent memory (requires uv sync)
/plugin enable limitless@limitless # Enable
/plugin enable after-hours@limitless # Enable
/plugin enable pyro-kit@limitless # Enable
/plugin enable codies-memory@limitless # Enable
/plugin disable limitless@limitless # Disable
/plugin disable after-hours@limitless # Disable
/plugin disable pyro-kit@limitless # Disable
/plugin disable codies-memory@limitless # Disable
/plugin uninstall limitless@limitless # Uninstall
/plugin uninstall after-hours@limitless # Uninstall
/plugin uninstall pyro-kit@limitless # Uninstall
/plugin uninstall codies-memory@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 codies-memoryPyro 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.
A calm, high-taste Claude Code plugin for clarity, coherence, subtraction, naming, project identity, and first-contact honesty.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems