Top Agent Skills

Add scroll animations, micro-interactions, or page transitions to a component using GSAP, with reduced-motion support and performance best practices.

Pulls pathway, book, course, article, and content item records from a Supabase database for the alan-hirsch tenant, organizes them by portal, and exports the results as markdown files into a local docs repository.

Adds a new database table and generates all six layers of the platform codebase, from schema to UI, with validation at each step.

Organizes discovered pathway, portal, and theme content into a docs repository by copying new files, resolving duplicates, updating the README, and generating per-portal indexes.

Audits image usage across a project by comparing required image slots against available files, reporting matches, mismatches, missing assets, and broken references.

Iteratively builds websites with Stitch by reading a baton file, generating pages, integrating them, and passing the next task.

Scaffolds a new OpenAI Agents SDK agent with instructions, tools, API route, and bridge wiring, following existing project conventions.

Generate a visually consistent set of image assets using Nano Banana 2 for course covers, book headers, video thumbnails, and more.

Drafts a complete course week in Alan Hirsch's voice, grounded in corpus material and following a canonical transformation-loop structure.

Builds Google Stitch UI projects and generates screens from feature descriptions or export files by calling Stitch MCP tools directly, following Stitch prompting best practices.

Acquires a single verified headshot per named leader from official sources, with identity checks and a provenance manifest, avoiding bulk scraping.

Provides Git commands and workflows for commits, branches, rebases, merges, conflict resolution, history recovery, and team collaboration, with safety rules for force-pushing and destructive operations.

Guides reliable application deployment with CI/CD pipelines, zero-downtime strategies, rollback plans, and post-deploy monitoring.

Routes API calls to third-party services through Maton-managed connections, with read-only defaults and explicit user approval for any data-modifying operations.

Provides a structured code review checklist covering security, performance, correctness, maintainability, testing, accessibility, and documentation, with a three-pass review process and guidance on severity levels and anti-patterns.

Provides a safe strategy for writing and editing large files to avoid truncation, including size thresholds, verification steps, and fallback recovery methods.

Provides verified official legal references for business formation, labor, and privacy across the USA, Canada, and all 27 EU member states, with links to government portals and gazettes.

Creates, edits, and analyzes Excel spreadsheets with formulas, formatting, and data analysis, including financial modeling standards and formula recalculation.

Provides comprehensive guidance for symbolic mathematics in Python using SymPy, covering algebra, calculus, equation solving, linear algebra, physics, and code generation.

Creates interactive, publication-quality charts with hover, zoom, and pan, plus static exports and Dash integration.

Customize shadcn/ui themes by editing CSS variables, adding custom colors, and adjusting border radius.

Analyzes code directories to create C4 code-level documentation with function signatures, dependencies, and Mermaid diagrams.

Ingest, index, search, and edit video and live streams with timestamps, subtitles, overlays, and real-time alerts.

Writes and reviews defensive Bash scripts for automation, CI/CD, and system utilities, emphasizing safety, portability, and testability.

Provides a structured debugging workflow for diagnosing errors, test failures, and unexpected behavior, including root cause analysis and verification steps.

Create, analyze, and visualize complex networks and graphs in Python using NetworkX, including graph construction, algorithms, generators, I/O, and plotting.

Creates walkthrough videos from Stitch app designs using Remotion, with smooth transitions, zoom effects, and text overlays.

Guides a structured requirements pipeline from topic intake through brainstorming, spec writing, planning, user review, SRS generation, validation, and improvement reporting.

Flip core assumptions to reveal hidden constraints and alternative approaches by asking what if the opposite were true.

Provides a discovery stub for the Wren CLI, a semantic SQL layer over 22+ databases, with commands to install, set up, connect data sources, generate MDL projects, enrich context, and deploy GenBI dashboards.

Inspect and adjust the agent's runtime state, including model, context window, iteration limits, token usage, workspace configuration, subagent status, and request routing metadata.

Access 83 unified crypto data endpoints covering CEX/DEX markets, on-chain SQL across 80+ blockchain tables, wallet labels, prediction markets, social intelligence, news, and DeFi metrics via a local HTTP API with per-call billing.

Perform fast genomic interval operations (overlap, nearest, merge, coverage, cluster, complement, subtract, count-overlaps), multi-format bioinformatics I/O, DataFusion SQL, and pileup on Polars DataFrames via the polars-bio library, serving as a scalable alternative to bioframe and bedtools.

Convenes a multi-persona council of historical thinkers to deliberate on complex problems and synthesize a verdict.

Routes Composio work across Composio For You and Composio Platform, covering setup, SDK/MCP integration, CLI operation, migration, and troubleshooting.

Interact with GitHub using the `gh` CLI to check PR checks, list and view CI runs, and run advanced API queries with JSON output.

Establishes a three-layer knowledge distillation architecture for an Obsidian-based wiki, defining categories, projects, page templates, and operational workflows for maintaining a persistent knowledge base.

Plans a comprehensive app launch strategy, covering pre-launch ASO, press outreach, beta testing, launch-day activities, and post-launch optimization.

Search, install, update, and list agent skills from the ClawHub public registry using natural-language queries.

Generate or edit images through ClawRouter's local API, with automatic payment via x402 and support for multiple models.

Writes or updates a HANDOFF.md document to preserve context for the next agent, including goal, progress, what worked, what didn't, and next steps.

Launches a model evaluation batch with parameter collection, pre-flight checks, execution, and post-run analysis for interactive or foreground runs.

Conducts multi-source web research on any topic, cross-referencing claims and delivering a structured report with sources and recommendations.

Orchestrates structured experiments end-to-end: initialize, plan, run, and evolve with reproducibility tracking and hypothesis validation.

Verifies every bibliographic entry in a paper for existence, metadata accuracy, and contextual support using web/DBLP/arXiv lookups, flagging hallucinated authors, wrong years, fabricated venues, and misattributed citations.

Manages a persistent hypothesis tree in markdown, tracking falsifiable claims with linked evidence, timestamps, and next experiments for multi-step research investigations.

Verifies that every number, comparison, and scope claim in a research paper matches raw result files, using a fresh cross-model reviewer with no prior context to prevent confirmation bias.

Recommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.

Runs a structured multi-agent deliberation: four specialist agents write independent position papers, two cross-examiners debate them, and the orchestrator synthesizes a final recommendation with implementation plan and risk register.

Generates opinionated design systems with curated color palettes, font pairings, UI styles, product-type rules, and UX guidelines across multiple tech stacks.

Analyzes workflows to identify inefficiencies, bottlenecks, and optimization opportunities, providing a structured report with recommendations for eliminating, resequencing, parallelizing, and automating steps.

Guides technical verification of code review feedback before implementation, emphasizing reasoned pushback over performative agreement.

Delegates independent debugging tasks to parallel agents with isolated context, preserving the main session for coordination.

Write bash scripts for automation, system administration, and command-line productivity, covering variables, conditionals, loops, functions, argument parsing, error handling, and text processing with awk, sed, find, and xargs.

Applies Agile principles to software development, system design, and technical problem-solving, covering implementation, optimization, and best practices.

Scales AI and Python applications across clusters with distributed computing primitives for ML workloads.

Write idiomatic C# code using .NET features, async/await, LINQ, SOLID principles, dependency injection, and unit tests.

Provides guidance and best practices for working with CircleCI, covering setup, configuration, deployment, and troubleshooting.

Guides the implementation of ethical AI principles, including fairness auditing, bias mitigation, explainability, accountability, and privacy protection in machine learning systems.

Provides guidance and best practices for working with Cassandra, covering setup, configuration, development, deployment, and operations.