oaustegard

Guidance for asking clarifying questions when user requests are ambiguous, have multiple valid approaches, or require critical decisions. Use when implementation choices exist that could significantly affect outcomes.

Generates a pre-change blast-radius report for a symbol or file, identifying affected sites by feature or package. It scans references and non-parsed files, useful before refactoring, renaming, or deleting in external repositories.

Browse Bluesky content via API and firehose, including searching posts, fetching user activity, and analyzing accounts. It supports authenticated access for personalized feeds, ideal for research, monitoring, and trend analysis.

Generates progressive disclosure indexes for GitHub repositories, to be used as Claude project knowledge. Use when setting up projects referencing external documentation, creating searchable indexes of technical blogs or knowledge bases, combining multiple repos into one index, or when the user mentions index, github repo, project knowledge, or documentation reference.

Generates progressive disclosure indexes for GitHub repositories to use as Claude project knowledge. Use when setting up projects referencing external documentation, creating searchable indexes of technical blogs or knowledge bases, combining multiple repos into one index, or when user mentions "index", "github repo", "project knowledge", or "documentation reference".

Cross-context adversarial review for deliverables before shipping. Use when producing blog posts, technical recommendations, analysis briefs, code, or any artifact where accuracy matters more than speed.

Create interactive data visualizations using Vega-Lite's declarative JSON grammar, supporting over 20 chart types like bar, line, and scatter plots via templates and programmatic builders. It's ideal for charting user-uploaded data, specific chart requests, or general visualization needs, producing portable JSON specs.

Select the appropriate Python charting library (seaborn, matplotlib, graphviz) to create publication-quality static visualizations. This skill is used for generating charts, plots, graphs, diagrams, heatmaps, and various data visualizations, including network diagrams, flowcharts, and entity-relationship diagrams.

Closes a GitHub issue with a synthesis comment as a flowing graph, validating it, posting the comment, and then running a detached pluggable callback. Use this when closing an issue should capture learning, not just diffs, and post-close work shouldn't block the close acknowledgment.

Develop and run Mojo code in Claude.ai containers, handling installation, compilation, and execution. Use this skill for writing Mojo, benchmarking against Python, or when discussing Mojo, Modular, or MAX, routing to official Modular skills for language-specific corrections.

Composes single-file HTML artifacts (like reports, presentations, and flowcharts) from a JSON spec, replacing manual HTML/CSS/JS. Use to compare options side-by-side, request HTML versions of documents, or create flows.

Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files.

Build and cache a personalized container environment from a Dockerfile-like spec, supporting both single-layer and multi-layer composition with independent layer caching.

Generates optimized instructions for Claude (Project instructions, Skills, or standalone prompts). Use when users request creating project setups, writing effective prompts, building Skills, or need guidance on instruction types for Claude.ai.

Creates production-ready MCP servers using FastMCP v2. Use when building MCP servers, optimizing tool descriptions for context efficiency, implementing progressive disclosure for multiple capabilities, or packaging servers for distribution.

Creates Skills for Claude. Use when users request creating or updating skills, need skill structure guidance, or mention extending Claude's capabilities through custom skills.

Specialized Preact development skill for standards-based web applications with native-first architecture and minimal dependency footprint. Use when building Preact projects, particularly those involving data visualization, interactive applications, single-page apps with HTM syntax, Web Components integration, CSV/JSON data parsing, WebGL shader visualizations, or zero-build solutions with vendored.

Distills Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet), generating explicit, procedural prompts with n-shot examples to maximize smaller model performance on a given task.

This skill provides a first-encounter codebase orientation, chaining structural inventory and feature synthesis into an EDA workflow for unfamiliar repositories. Use it to quickly understand a new codebase, especially when asked to explore or understand a recently cloned repository.

Performs exploratory data analysis using ydata-profiling on .csv/.xlsx/.json/.parquet files, generating interactive HTML or JSON reports with statistics, visualizations, correlations, and quality alerts.

Extracts keywords from documents using the YAKE algorithm, supporting 34 languages from Arabic to Chinese. It's ideal for keyword extraction, topic identification, content summarization, and document analysis, including domain-specific stopwords and an optional deeper extraction mode.

This skill generates hierarchical _FEATURES.md files that describe a codebase's functionality from a user perspective, anchored to source symbols. It supports large, complex codebases through feature-driven decomposition and a multi-pass synthesis process.

Retrieves clean markdown from URLs when web_fetch fails, converting pages via Jina AI reader service with automatic retry, useful for 403, blocked, paywall, timeout, JavaScript-rendering errors, empty content, or when explicitly suggested.

Discover and load skills on demand from /mnt/skills/user/. This tool helps you find capabilities, get full skill descriptions, or browse the catalog using 'list', 'search', and 'show' commands.

A DAG workflow runner that encodes control flow in code, not prose. It's designed for procedures with 3+ steps involving branching, retries, or enforced validation, using constructs like `when=`, `validate=`, and `retry_until=`, and supports parallel execution and checkpoint resume.

This skill performs zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference), activating when users provide time series data and request forecasts, predictions, or extrapolations, and supporting Reverso Small (550K params).

Generate and maintain lat.md knowledge graphs with bidirectional source code anchoring. Documentation links to code via wiki links, and code links back to docs via @lat: comments, with lat check validating both directions.

Break out of a locked problem frame by picking one disciplined move — reframe, provocation (Po), random stimulus, SCAMPER, inversion, perspective shift, or constraint play — and committing to it before evaluating. Use when stuck, when options feel narrow or obvious, when iterations produce variations of the same idea, or when the user asks to widen, break out, or think differently.

GitHub CLI (gh) installation and authenticated operations in Claude.ai containers. Use it to create issues, PRs, view repositories, or perform GitHub operations beyond raw API calls.

Delivers a static Hello World HTML demo page with a bookmarklet. Use when the user requests the hello demo, hello world demo, or demo page.

Converts raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use to vectorize, trace, or convert images to SVG, or to faithfully reproduce artwork as vector graphics.

Discovers and indexes Python code in skills, enabling cross-skill imports. Use when importing functions from other skills or analyzing skill codebases.

Installs skills from github.com/oaustegard/claude-skills into /mnt/skills/user. Use when the user mentions install, load, add, update, refresh skills, or references a skill not currently installed.

Install and drive Google's Antigravity CLI (agy) as a non-interactive sub-agent. Use when orchestrating agy, running Antigravity agents from a script or sandbox, delegating a task to Google's agent harness, or wanting a Gemini-backed peer agent alongside Claude.

Invokes Google Gemini models for structured outputs, image generation, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, structured JSON output, Google API integration, or cost-effective parallel processing.

Enables GitHub repository operations (read/write/commit/PR) for Claude.ai chat environments. Use for GitHub commits, repository updates, DEVLOG persistence, or cross-session state management via GitHub branches. Not needed in Claude Code.

Multi-conversation methodology for iterative stateful work with context accumulation. Use when users request work that spans multiple sessions (research, debugging, refactoring, feature development), need to build on past progress, explicitly mention iterative work, work logs, project knowledge, or cross-conversation learning.

Generates guardrailed UI from natural language. Claude emits constrained JSON, which the skill runtime renders via Preact.

Executes programs on a compiled transformer stack machine where every instruction fetch and memory read uses a parabolic attention head. It demonstrates that transformer attention + FF layers can implement a working computer.

Generates WAFFLES Declarations for social media posts, providing preemptive lists of what a post does NOT say. Use it to prevent misinterpretation, clarify posts, or add disclaimers for controversial/nuanced takes, especially when WAFFLES is mentioned.

Generates navigable code maps for unfamiliar codebases by extracting exports/imports via AST to create _MAP.md files, showing classes, functions, and methods with signatures and line numbers. Useful for exploring repositories, understanding project structure, or analyzing code before modifications.

Generates navigable semantic maps from PDF documents by extracting section structure via font analysis and running LLM extraction for page-anchored claims, symbols, and dependencies. It produces _MAP.md, .symbols.json, .anchors.json, and a _USAGE.md snippet, ideal for analyzing papers, specs, or legal documents.

This skill generates behavioral and feature documentation for web applications using code-first analysis. It reads source code and _MAP.md files to produce _FEATURES.md, with optional visual verification, useful for documenting app behavior or creating feature inventories.

This skill opens a GitHub Pull Request via API, managing the full workflow of branching, pushing, and PR creation, with structural protection against pushing to main branches. It's ideal for Claude Code or Claude.ai containers that need to land changes on GitHub without a git CLI, when the manual process becomes inconsistent.

This skill enables disciplined, validation-gated revision of existing skills, ensuring each edit is a measured improvement. It's used for tuning underperforming existing skills, not for authoring new ones.

Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, or complex task decomposition.

This skill provides skill-aware orchestration with context routing, decomposing complex tasks into skill-typed subtasks, executing subagents in parallel, and synthesizing results. It's ideal for tasks requiring multiple analytical perspectives or when context is large and subtasks only need portions.

This skill provides interactive codebase orientation for human learning, building user understanding through guided exercises grounded in learning science. It synthesizes interactive teaching via HTML artifacts and is triggered by "orient me to this repo".