All skills

Installs a macOS menu bar icon that shows whether NanoClaw is running, with Start, Stop and Restart controls.

A guided, re-run-safe setup that wires Karpathy's LLM Wiki pattern into a NanoClaw group as a persistent knowledge base.

A setup skill that walks through installing claude-mem on Grok Bot via local worker, host-login observer, or remote cmem.ai.

A concise skill for installing and configuring the claude-mem memory layer on Cursor with either a local or remote worker.

Configures and verifies claude-mem cloud sync against a cmem.ai Pro SyncHub connection.

Searches scientific literature through the BGPT MCP server and returns 25+ structured fields extracted from full-text papers.

A playbook for decomposing complex work into parallel units, designing dependency graphs, writing precise task specs, and balancing workload across agent teams.

A Clean Code review skill that scores your code 0-10 on naming, function size, error handling and tests, then lists the exact fixes to reach 10/10.

Turns half-baked ideas into a structured, stress-tested concept brief using multi-turn clarifying questions and seven parallel critique lenses.

Audits every design doc or README against the actual codebase and writes a dated, differences-only drift report.

A hands-on guide for validating web accessibility with VoiceOver, NVDA, JAWS, and TalkBack.

A playbook for splitting a large feature across multiple implementer agents using file ownership, interface contracts, and integration patterns.

A read-only analysis skill that inspects and summarizes codebases, checks service health, and supports decisions via ADR consultation, weighted scoring, and multi-persona critique.

Automate Benchling registry entities, inventory, ELN entries, workflows, Apps, and Data Warehouse queries with the Python SDK or v2 REST API.

An adversarial design review that renders your UI in a clean forked context, screenshots it, and argues the case for rejection.

Answers questions about your codebase by selectively grepping a pre-built knowledge graph instead of loading it all.

Turns your project's knowledge graph into a complete onboarding document covering architecture, file map, and complexity hotspots.

Interviews you, designs a custom claude-mem memory mode, installs it, wires optional Telegram alerts, and verifies it is actually active.

An LLM-first SEO audit skill that inspects websites, blog posts, and GitHub repos, then ships a prioritized report plus action plan.

Turns messy competitor material — sites, pricing pages, reviews — into a decision-ready product strategy report with a positioning map, feature matrix and opportunity windows.