Agent skills for Claude Desktop

Universal behavioral discipline for every human-facing agent in the pack.

Integrate Core ML models in iOS apps for on-device machine learning inference.

Use when planning new projects, onboarding, or reviewing architectural decisions.

Read and write NFC tags using CoreNFC. Use when scanning NDEF tags, reading ISO7816/ISO15693/FeliCa/MIFARE tags, writing NDEF messages…

When the user wants to plan, design, or implement an A/B test or experiment.

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any…

Write B2B cold emails and follow-up sequences that get replies.

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program.

Use when planning or producing Instagram content — feed aesthetic, captions, Reels, Stories, carousels, content calendars, or growing an…

This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging

Law firm or plugin developer defines the visual appearance of the deal copilot: calm elegant blue-silver, warm orange for...

Corporate cowork design: defines the visual interface for partners, counsel, and associates.

Report on research corpus health, completeness, and integrity

Capture durable knowledge into the corpus after a task, discussion, incident, spec or implementation.

Run deterministic checks on the application corpus and turn the results into concrete maintenance actions.

Establish and maintain durable AI agent collaboration using bounded work orders, separated execution and acceptance, minimum-sufficient…

Auto-routing skill loaded by the prompt filter hook.

Use when AI inference costs are growing unexpectedly, when comparing model choices by cost/quality ratio, or when optimizing token usage…

Audit cloud infrastructure costs and produce a concrete optimization plan with specific changes and estimated savings.

Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table

Wrap getTokenOptimizer().getCompactContext() to retrieve compacted ReasoningBank context for cost-analysis queries; report bridge-reported…