Mr. ED
Community@edheltzel · ❤︎ Midwest USA
"One finds limits by pushing them." – Herbert Simon
Agent Skills by Mr. ED
Showing 143 vetted skills indexed across 3 GitHub repositories.
do-teach-me
Creates a stateful teaching workspace with HTML lessons, learning records, and curated resources.
do-recipe-diagrams
Convert recipes into high-resolution Cooking for Engineers-style PNG process-flow diagrams.
do-first-principles
Deconstructs problems to fundamental truths, classifies constraints, and reconstructs solutions from first principles.
do-agents-md
Write concise AGENTS.md files that give coding agents repository context and commands.
do-behavioral-testing
Write behavior-focused tests that assert user-observable outcomes instead of implementation details.
do-agent-context-layer
Structure repository documentation so AI agents navigate context through pointers and catalogues.
do-simplify
Simplifies recently modified code for clarity without changing behavior.
do-adversarial-review
Hunt correctness bugs and regressions in a code diff using adversarial review.
do-agent-first-repo
Structure repositories and documentation so AI coding agents can work autonomously.
do-red-team
Stress-tests ideas and plans using parallel adversarial agents producing steelman and counter-argument reports.
do-architecture-md
Generate an ARCHITECTURE.md codemap documenting a codebase's modules, boundaries, and invariants.
do-illo
Generates editorial illustrations with a recurring mascot character across seventeen print-style looks.
do-art
Generates static visual content across 20+ formats using Flux, Nano Banana Pro, and GPT-Image-2.
do-browser
Automates Chrome browser navigation, interaction, and inspection through the chrome-devtools-axi CLI.
do-interceptor
Drive real Chrome and macOS apps for browser automation, visual verification, and computer use.
do-delegation
Orchestrates parallel agent dispatch, background execution, and worktree-isolated edits with coordinator verification.
do-context-search
Searches prior project work and session history through Recall MCP tools.
do-bitter-pill
Audits AI instruction sets for over-prompting and classifies each rule for removal or retention.
do-writing-great-skills
Provides vocabulary and principles for writing predictable AI agent skills.
do-review-skill
Reviews pull requests that add or modify Agent Skills for structural validity and design quality.
do-distill-to-skill
Distills articles, repos, and documents into structured agent skill files.
do-humanize
Rewrites AI-generated developer text by applying safe and interactive fixes from review findings.
do-huh
Restate the last AI message in plain jargon-free language.
do-review-ai-writing
Detect AI-generated writing patterns in docs, docstrings, commit messages, and PR descriptions.
Frequently Asked Questions About Mr. ED
FAQPage SchemaWhat tasks can I accomplish with edheltzel's skill registry?▼
You can run polyglot code reviews (Go, Rust, Python, Elixir, Swift, TypeScript/React), author and audit SKILL.md and AGENTS.md files, manage GitHub Projects boards and stacked PRs, generate diagrams and editorial illustrations, and apply reasoning frameworks like first-principles decomposition and red-team adversarial analysis.
Who is the target audience for these skills?▼
Software engineers and technical leads working with coding agents in real repositories. The registry targets backend developers (Go, Rust, Python/FastAPI, Elixir/Phoenix), frontend engineers (Remix v2, React Router v7, shadcn/ui, Tailwind v4), Apple platform developers (SwiftUI, AppKit, watchOS), and maintainers standardizing agent context documentation.
How do I install and run these skills?▼
Skills are invoked inside a compatible coding-agent environment by name or trigger phrase; many are user-invocable with argument hints. Some require runtime dependencies: do-recipe-diagrams needs Python 3 and ImageMagick, do-illo requires python3 on macOS or Linux, and GitHub skills rely on the gh CLI with Bash access.
Are these skills open source and what do they cost?▼
The skills are free to use; several carry explicit MIT licenses (do-illo, do-astro) and link to public upstream repositories such as github.com/tmchow/illo-skill and astrolicious/agent-skills. No paid tier or subscription is indicated anywhere in the manifest.
What prerequisites or dependencies do the skills require?▼
Most skills are self-contained Markdown instruction sets. Noted dependencies include Python 3 and ImageMagick for recipe diagrams, python3 for illustration rendering, the gh CLI for GitHub Projects and PR triage, GitButler or gh stack for stacked PRs, and chrome-devtools-axi for browser automation.