A five-mode testing workflow that finds high-value test candidates, writes and reviews focused tests, generates adversarial workloads, and diagnoses test-suite health.
Audit, strategy, and release-gate workflow for turning a live website, PWA, or dashboard into an App Store-ready iOS app.
One skill that routes any writing job — docs, landing pages, email, social, agent-facing docs — through mode selection, voice alignment, an SEO/AEO pass, and a 70-point ship score.
Converts GitHub Actions or Bamboo pipelines into TeamCity YAML and walks you through the manual steps until builds go green.
Read-only audit of your Amazon account for restocking fees, short refunds and forgotten subscriptions, then gated chat disputes or cancellations per item.
Takes a product idea to a signed, policy-compliant Google Play release using Kotlin and Jetpack Compose with an evidence-based release gate.
Lets Claude drive the `teamcity` CLI to investigate build failures and manage jobs, queues, agents and pipelines.
A reference skill that keeps Claude/Anthropic SDK code accurate — model IDs, params, tool use, streaming, agents, and model migration.
Writes a design manifesto first, then expresses it as a museum-grade poster or artwork in PDF/PNG.
Analyzes an article, script, or topic and auto-generates matching illustrations, slide infographics, and cover images via Gemini, Excalidraw, and Mermaid.
Writes an algorithmic art 'manifesto' first, then implements it as a seeded, interactive p5.js artwork in a single self-contained HTML file.
A bounded multi-agent command protocol that splits genuinely independent work across 5–100+ isolated workers, verifies outputs independently, and integrates serially.
Redesigns a personal or team operating system as a supervised learning loop with Four-C diagnostics and one bounded, reversible experiment.
An advanced playbook for designing or refactoring agent-based engineering workflows with bounded autonomy, custom evals, durable state, and verified write-back.
Queries China's National Bureau of Statistics public API (data.stats.gov.cn) with curl + jq to pull GDP, CPI, population and housing price index data.
Prescribes a pruning pass over a bloated Claude Code session, stripping progress ticks, stale reads and duplicate content for 40–95% token savings.
Runs a background daemon that watches your Claude Code session size and prunes context before auto-compaction wipes your state.
Teaches Claude to drive the `hab` CLI to inspect, create, update and operate Home Assistant safely from the terminal.
A MATLAB tutoring skill that builds runnable exercises, executes them in MATLAB, compares actual vs. expected output, and gives style feedback.
A tutoring skill that classifies a learner's MATLAB question and routes it to the right specialized MATLAB skill while teaching the underlying data model.