Top Agent Skills

Structures company knowledge bases for business plan automation, defining a 7-category schema, completeness scoring, and storage layouts for Notion or local Markdown.

Guides go-to-market strategy with five motions, content pyramid, PESO channels, and 90-day execution plans.

Guides SaaS pricing strategy: selecting models, value metrics, packaging tiers, and applying psychology tactics to optimize revenue.

Guides founders through the fundraising lifecycle from pre-seed to Series B, covering stage benchmarks, an 8-week execution timeline, and preparation checklists for pitch decks, financial models, and data rooms.

Analyzes competitive landscapes using Porter's 5 Forces, positioning matrices, and battlecard generation to secure market position.

Enforces production-grade REST API design, distributed systems patterns, database design, and event-driven architecture at a principal-engineer level.

Query, filter, transform, and aggregate JSON data using jq, with practical patterns for shell pipelines and CLI integration.

Fetches any X/Twitter post as structured JSON via the ADHX API, including full article content, author info, and engagement metrics, without scraping or a browser.

Converts human-written CLAUDE.md files into a structured-label format that improves AI instruction compliance while reducing token usage.

Reference for building real-time voice and multimodal AI applications with Daily and Pipecat, covering pipeline architecture, AI service integrations, transports, and client SDKs.

Provides guidance for performing symbolic algebra, calculus, linear algebra, equation solving, physics calculations, and code generation using the SymPy Python library.

Build reactive backends with Convex: schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and deployment.

Guides users through creating, listing, and viewing GitHub issues using the gh CLI, with structured prompts for titles, descriptions, labels, and filters.

Build, optimize, and execute quantum circuits using Qiskit on simulators or real quantum hardware, with support for IBM Quantum, IonQ, and Amazon Braket.

Transforms rough sketches or text descriptions into high-fidelity 3D-like product renders using Vizcom's AI platform.

Builds interactive in-browser studios for tuning visual parameters or editing and annotating text and media, enabling direct manipulation instead of static comparisons.

Create publication-quality statistical graphics directly from tabular datasets, covering relational, distribution, categorical, regression, and matrix plots with minimal code.

Generates concise, Toss-inspired UX microcopy for buttons, empty states, errors, toasts, confirmations, and form guidance, with tone and localization notes.

Routes you to the right skill or flow for your situation, covering idea-to-ship, triage, codebase health, and cross-session handoffs.

Extracts clean markdown from web pages via the Defuddle CLI, removing navigation and clutter to reduce token usage for reading or analyzing URLs.

Practical patterns for using fp-ts with React, covering hooks, state management, form validation, and data fetching for React 18/19 and Next.js 14/15.

Instrument LLM applications with Langfuse for tracing, prompt versioning, evaluation, and dataset management across Python and JavaScript SDKs.

Guides the creation, optimization, and scaling of paid advertising campaigns across major platforms, covering strategy, structure, copy, and creative best practices.

Reviews pull request diffs for correctness, security, maintainability, and test coverage, providing severity-ranked findings and a close-out recommendation.

Creates a complete change proposal with design, specs, and tasks in one step, ready for implementation.

Query, filter, and transform JSON with expert jq patterns, including aggregation, string formatting, and shell pipeline integration.

Design, simulate, and run quantum circuits on simulators and quantum hardware using Google's Cirq framework.

Build content-focused websites with Astro, leveraging zero-JS islands architecture, multi-framework components, and Markdown/MDX support.

Drives a PRD-based persistence loop that iterates on a task until all user stories pass and are reviewer-verified, with automatic retry and progress tracking.

Creates commits following Sentry conventions with proper conventional commit format and issue references.

Generates images from text prompts using Google Gemini's image generation model, saving them as PNG files for use in UI, documentation, and design projects.

Process in-memory datasets with Polars' expression API, lazy evaluation, and parallel execution, including pandas migration patterns and I/O for CSV, Parquet, and JSON.

Analyzes code directories to produce C4 code-level documentation with function signatures, dependencies, and structure.

Design and implement production-grade GraphQL APIs with schema design, DataLoader for N+1 prevention, Apollo Client caching, and federation patterns.

Create publication-quality statistical graphics using Seaborn, with dataset-oriented plotting, multivariate analysis, automatic statistical estimation, and complex multi-panel figures.

Answers questions about a codebase by searching and reading source files, then synthesizing answers with inline citations and a key files table.

Extracts clean markdown content from web pages using the Defuddle CLI, removing navigation and clutter to reduce token usage. Prefer over WebFetch for reading or analyzing standard web pages.

Query free LLM APIs from OpenRouter, Groq, Cerebras, Google AI, and Mistral, with commands to compare models and check status.

Creates, manipulates, and analyzes complex networks and graphs using the NetworkX Python package, including graph algorithms, synthetic network generation, I/O, and visualization.

Provides expert guidance on modern Rust development, covering async patterns, advanced type system features, and production-ready systems programming.

Creates and maintains minimal, high-signal AGENTS.md files for AI coding agents, following research-backed best practices for concise agent documentation.

Turns a one-line objective into a step-by-step construction plan any coding agent can execute cold, with each step containing a self-contained context brief.

Converts text to speech and speech to text using fal.ai audio models.

Query, filter, transform, and aggregate JSON data using jq, with practical patterns for shell pipelines and integration with CLI tools.

Explains machine learning model predictions using SHAP values, covering feature importance, visualization plots, model debugging, bias analysis, and production deployment.

Routes quality reviews to specialized critic agents based on file type or flags, covering peer review, code review, and manuscript polish.

Create publication-quality statistical graphics in Python with dataset-oriented plotting, semantic mapping, and built-in statistical estimation.

Evaluates machine learning classifiers on their ability to distinguish signal from background in particle physics simulations, measuring how well algorithms rank signal events above background ones using the AUC metric.

Computes bibliometric indices for AI/NLP conferences, including QQE, average/median citations, and citation inequality, from annual publication and citation data.

Process large ML datasets in parallel across CPU or GPU clusters, with streaming execution, multi-format I/O, and integration with Ray Train, PyTorch, and TensorFlow for batch inference and preprocessing pipelines.

Evaluates geometric consistency in text-to-video generation by measuring structural and motion coherence across camera trajectories, detecting deformation and occlusion artifacts in static scenes.

Evaluates the throughput and resource allocation efficiency of RIS-aided mobile edge computing systems by measuring the total computation task bits successfully completed under varying network conditions.

Computes CIDEr and related metrics to score how well generated image descriptions align with human consensus, using reference sentences and triplet annotations.

Evaluates image captions by converting them into scene graphs and computing an F-score over semantic propositions, measuring how well a generated caption captures the meaning of an image compared to human references.

Pretrains large language models at scale using PyTorch-native torchtitan with 4D parallelism, Float8, and distributed checkpointing.

Benchmarks long-context language models across 20 sub-tasks spanning 3k–200k tokens, covering retrieval, reasoning, summarization, and instruction understanding, with exact-match accuracy as the primary metric.

Evaluates spatial realism and temporal flow consistency of AI-generated videos using embedding spaces and Fourier transforms, producing bounded STREAM-S and STREAM-T scores.

Benchmarks mobile GUI agents on multi-step tasks across 20 Android apps, measuring task completion and essential-state navigation with Task Success Rate and Essential State Achieved Rate.

Measures inference latency of binarized, 8-bit, and 32-bit convolutional layers on edge devices to evaluate the efficiency and speedup of the Larq Compute Engine framework compared to standard implementations.

Computes Theil's U (uncertainty coefficient) between predictions and ground truth using the torchmetrics implementation, handling categorical data and NaN strategies.