My Skills

Generates a structured evaluation framework—test cases, scoring rubrics, and metrics—for assessing whether an AI skill is working as intended. Use this when you've built or are designing an AI skill and need a rigorous way to measure its quality, consistency, and edge case handling. Trigger phrases: 'How do I know if my skill is working?', 'Help me build test cases for my skill', 'Create an evaluation framework for my AI skill', 'What metrics should I track for this skill?', 'I need a rubric to grade my skill outputs'. Not intended for general software QA or non-AI product testing.

Build modular AI video pipelines that turn creative concepts into polished video assets faster and cheaper than traditional production.

Generate persuasive marketing copy using the proven Attention-Interest-Desire-Action framework — tailored to your product, audience, and channel.

Get 3 personalized bike routes with turn-by-turn directions, elevation profiles, and downloadable GPX files for your GPS device

Build a custom investment portfolio like a BlackRock senior strategist — delivers exact asset allocation, specific ETF picks, expected return ranges, drawdown estimates, rebalancing rules, and an optional investment policy statement.

Generate a structured, SEO-friendly blog post outline with headings, key points, and suggested word counts.

Generate a Blue Ocean Strategy canvas with eliminate-reduce-raise-create analysis, new value curve, non-customer mapping, and implementation roadmap — strategy workshop deliverable format.

Applies Anthropic's official brand colors and typography to any artifact that may benefit from Anthropic's look-and-feel, including presentations, documents, and visual designs.

Assess your investment portfolio like a Bridgewater risk analyst — delivers correlation analysis, sector concentration, stress testing, liquidity ratings, tail risk scenarios, and hedging strategies using Ray Dalio's principles.

Identifies skills that require multi-step reasoning but lack explicit reasoning scaffolding. Flags instructions that ask the AI to jump to conclusions without intermediate steps.

Analyzes skill instructions for ambiguous language, vague qualifiers, and instructions with multiple valid interpretations. Returns findings with specific rewrite suggestions.

Generates a cold email using the Compliment-Case Study-Call to Action framework to land a first client even without prior experience or a portfolio.

Design the complete trigger-to-outcome comment funnel flow — the structural blueprint for your automation tool.

Generates structured, professional git commit messages following Conventional Commits standards

Generate sales-ready battle cards with competitive positioning, objection handling, win/loss analysis, and talk tracks — powered by live competitive research.

Maps your competitive landscape using Bain's structured framework to identify market positioning, key rivals, and strategic whitespace.

Produce a rigorous competitive moat assessment with moat scoring across five dimensions, trajectory analysis, vulnerability mapping, and a 5-year durability forecast — investment thesis memo format.

Conversational search assistant that helps users find information on any website through natural dialogue

Identifies missing edge cases, undefined failure modes, under-specified inputs, and missing Critical Rules. Returns findings for gaps that will cause inconsistent or broken outputs at the edges.

Build a rigorous customer segmentation and competitive battleground analysis — 5–7 distinct segments with competitive ownership, battleground identification, switching triggers, and prioritised go-to-market allocation.