All skills

A guided, re-runnable setup skill that wires a Microsoft Teams bot channel into a self-hosted NanoClaw assistant.

Runs six Article-cited forcing questions to pressure-test an AI system's readiness for the EU market.

Installs NanoClaw's native Baileys WhatsApp channel with a mandatory number-safety gate, QR/pairing-code linking, and explicit .env configuration.

An operating spec that forces Claude to build, retrieve, and correct evidence-grounded local person profiles using only Distilly's exact five MCP tools.

A skill for querying and analyzing DepMap CRISPR gene dependency and drug sensitivity data to validate cancer-specific targets.

Delegate tasks to the OpenAI codex CLI non-interactively from Claude Code, with hardened rules for timeouts and session recovery.

A staged pipeline that deconstructs long web novels into golden-first-chapters analysis, per-chapter digests, plot, emotion, rhythm, characters, settings and a style profile.

An end-to-end malware workflow for static/dynamic analysis, YARA rule authoring, and safe sandbox setup.

A fan-out audit pipeline that runs every analysis skill in parallel and produces a unified health dashboard in Markdown and HTML.

A rigorous workflow skill for creating, changing, reviewing, and major-version-upgrading reusable Terraform modules from real provider schemas.

A DDD skill that guides Claude in evolving aggregates, value objects and domain events safely in Spring Boot 3 codebases.

Adds token usage, latency, cost attribution, and prompt audit telemetry to Spring AI apps using the correct 1.0 GA APIs.

Guides Claude through the complete PyMC 5 Bayesian workflow — priors, NUTS sampling, convergence diagnostics, LOO model comparison, and prediction.

Drives GUI-only macOS apps that have no API or CLI without stealing your focus, and leaves a reproducible screenshot trail for every step.

An orchestration skill that improves an existing app using its code, product contract, work history and competitor evidence — then implements authorized changes and verifies the real user result.

Locates babysitter processes and committed runs in an external public repo and writes an evidence-backed retrospective with concrete improvement suggestions.

A skill that guides Claude in packaging Spring Boot 3 apps as hardened OCI images or GraalVM native executables.

Enforces where Compose Multiplatform code lives — commonMain vs expect/actual vs interface + DI — and validates iOS/Swift, desktop and web targets.

Generates and runs reproducible Python/R analyses for medical research and outputs publication-ready tables, figures and manuscript text.

Designs and reviews repositories, data sources and mapping for Compose / Compose Multiplatform apps under strict boundary rules.