Skills

Red-teams LLM applications for prompt injection, jailbreaks, and data exfiltration risks. Generates adversarial test cases for direct and indirect injection, system prompt leakage, tool-call abuse, and unsafe output handling, then reports findings with severity ratings and concrete mitigations such as input isolation, output filtering, and least-privilege tools.

Performs systematic threat modeling for software systems using frameworks like STRIDE, PASTA, and Attack Trees. Identifies potential security threats, attack vectors, and vulnerabilities in system architectures. Produces prioritized risk assessments with mitigation strategies and security controls.

Analyzes video content to extract insights, describe scenes, identify objects and actions, generate summaries, and create structured annotations. Supports temporal reasoning across frames, scene change detection, and content categorization. Works with educational videos, product demos, surveillance footage, and social media content.

Creates comprehensive design system documentation and component specifications from existing UI patterns or requirements. Generates design tokens, component APIs, usage guidelines, and accessibility specifications. Supports Figma-to-code workflows and produces consistent theming across platforms.

Designs and generates data pipeline configurations for ETL/ELT workflows. Supports Apache Airflow DAGs, dbt models, Spark jobs, and streaming pipelines with Kafka or Flink. Creates data quality checks, schema evolution strategies, and monitoring dashboards for pipeline health.

Analyzes legal and business contracts to extract key terms, identify risks, compare clauses against standard templates, and generate summaries. Highlights unusual provisions, missing protections, and negotiation points. Supports NDAs, SaaS agreements, employment contracts, and vendor agreements.

Generates production-ready infrastructure as code (IaC) configurations for cloud deployments. Supports Terraform, Pulumi, CloudFormation, and CDK. Creates modular, reusable infrastructure components with proper networking, security groups, IAM policies, and monitoring configurations.

Performs a comprehensive competitive intelligence analysis for mobile apps on the App Store and Google Play. Compares metadata, keyword gaps, creative strategy (screenshots, preview video, icon), ratings, monetization, and growth signals across up to 5 competitors, then delivers a prioritized opportunity map with quick wins and strategic recommendations.

Performs a full App Store Optimization health check across 10 weighted dimensions: title, subtitle, keyword field, description, screenshots, preview video, ratings and reviews, icon, keyword rankings, and conversion signals. Produces a scored ASO report card (0–100) with quick wins, high-impact changes, and strategic recommendations prioritized by effort and expected impact.

Assists with writing, structuring, and editing scientific manuscripts, grant proposals, and technical reports. Supports IMRaD structure, proper citation formatting, abstract writing, methods sections with reproducibility details, results interpretation, and response to reviewer comments. Adapts to journal-specific guidelines and word limits.

Conducts systematic literature reviews across scientific databases including PubMed, arXiv, bioRxiv, and Semantic Scholar. Synthesizes findings from multiple papers, identifies research gaps, maps citation networks, and produces structured review documents suitable for grant proposals or publication introductions.

Assists researchers in generating, refining, and evaluating scientific hypotheses. Analyzes existing literature and data to propose testable hypotheses, identifies confounding variables, suggests experimental designs, and evaluates feasibility. Supports structured frameworks like PICO for clinical research and helps formulate null/alternative hypotheses with appropriate statistical tests.

Performs cheminformatics and molecular property analysis using RDKit, PubChem, and ChEMBL. Supports SMILES/InChI parsing, molecular descriptor calculation, drug-likeness filtering (Lipinski, Veber), ADMET prediction, substructure search, and structure-activity relationship (SAR) analysis for drug discovery workflows.

Builds and executes bioinformatics analysis pipelines for genomics, transcriptomics, and proteomics data. Supports single-cell RNA-seq analysis with Scanpy, differential expression with PyDESeq2, sequence alignment, variant calling, gene ontology enrichment, and pathway analysis using KEGG and Reactome databases.

Assists with deploying applications to cloud platforms including AWS, GCP, Azure, and Vercel/Netlify. Generates infrastructure-as-code (Terraform, Pulumi, CDK), Dockerfiles, CI/CD pipelines, and deployment scripts. Handles environment configuration, secrets management, and production readiness checks.

Records learnings, mistakes, and corrections to enable continuous improvement of AI agent behavior. Maintains a structured memory of failures, user corrections, outdated knowledge, and discovered better approaches. Reviews past learnings before executing important tasks to avoid repeating mistakes.

Security-first AI agent skill auditing. Reviews skill definitions, SKILL.md files, and agent configurations for dangerous patterns, excessive permissions, data exfiltration risks, and suspicious behaviors before installation. Provides a safety score and actionable recommendations.

Builds and queries typed knowledge graphs for structured agent memory and composable skills. Creates entities (people, projects, tasks, events, documents), links related objects, enforces constraints, and plans multi-step actions as graph transformations. Enables persistent, queryable memory across agent sessions.

Helps architect scalable distributed systems by analyzing requirements and producing high-level architecture diagrams, component breakdowns, data flow descriptions, and technology recommendations. Covers load balancing, caching strategies, database selection, message queues, and failure handling patterns.

Designs and scaffolds AI agent architectures including tool definitions, system prompts, memory strategies, and orchestration logic. Supports multi-agent workflows, ReAct patterns, function calling schemas, and MCP server configurations. Helps structure agents that are reliable, observable, and easy to debug.

Analyzes SQL queries and database schemas to identify performance bottlenecks and suggest optimizations. Recommends index strategies, query rewrites, denormalization opportunities, and partitioning schemes. Explains EXPLAIN plans and provides before/after comparisons with expected performance improvements.