Loading the repository README…
github-self-hosted-runner installs and registers persistent GitHub Actions runners on a Linux or macOS host, replacing slow, expensive macOS CI with a systemd- or launchd-managed setup.
Showing 14 of 14 collected skills.
Turn photos or screenshots of a student's course notes (handwritten or typed) into detailed, source-checked study notes as a typeset PDF that anyone taking the course can use. The notes decide what is covered and emphasised; the book itself is standalone,…
Write a dense, book-length technical manual (print-ready PDF) about a file format, protocol, library, runtime or system, grounded in its actual spec and source code at a pinned version, with captured bytes and runs, measured numbers and many data-driven…
Install, register, namespace, verify, or remove one or more GitHub Actions self-hosted runners on a Linux or macOS host. Use when a user provides a GitHub repository or organization URL and wants a persistent runner managed by systemd on Linux or launchd on…
Map an existing codebase's architecture and the reasons behind its design, then quiz the user whiteboard-defense style until they can explain and defend it. Builds an evidence-tagged map in `docs/map/` (a high-altitude overview first, then one region at a…
Build and maintain a feature map for an app — short markdown files that tell agents what each user-facing feature is, how a user reaches it, how to drive it (selectors, commands, requests, accessibility identifiers), what result to observe, and the gotchas —…
Decide whether claimed bugs are real by running an adversarial hearing on each claim — a Prover argues it's reachable, a Skeptic hunts for what prevents it, and an independent Referee rules confirmed, refuted, or unclear — with an isolated repro test when…
Write or improve landing-page marketing copy for a product by reading its codebase, so every claim is backed by code that actually ships. Produces a scannable page (hero, how it works, features, who it's for) that lets a first-time visitor understand the…
Write or update decision and implementation-plan records in a repository's records directory (usually `docs/records/`, also known as ADRs, decision logs, or design docs). Use for architecture, product, design, privacy, security, dependency, delivery, or other…
Audit a project you build with AI agents by mining your own local agent session logs (Claude Code, Pi, Codex) for papercuts, bugs, and design flaws — the friction visible in what you actually typed rather than what the README claims. Use this when the user…
Run a marketing/positioning pass on an open source repo's README and public-facing docs so a developer landing on it for the first time immediately understands what it is, why it exists, and how to use it. Use this whenever the user wants to improve a repo's…
Audit and prepare a GitHub repo for open source release, with a focus on developer experience (DevEx) — the things that determine whether a stranger can go from "found this repo" to "opened a PR" without friction. Use this whenever the user wants to…
Design, build, or review command-line interfaces using the Command Line Interface Guidelines from clig.dev. Use this skill whenever the user is creating a new CLI, adding commands/subcommands/flags, designing help text, choosing stdout/stderr/exit-code…
{url} address comments left on a GitHub pull request. Use when a user wants review comments and CI failures fixed on an existing GitHub pull request without opening a new PR.
Audit, rewrite, and tighten a CLAUDE.md / AGENTS.md file so it actually helps a coding agent instead of bloating its context. Handles repos that use either file name, both names, nested AGENTS.md files, or one file symlinked/aliased to the other. Use this…
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/markphelps/skills.The repository README could not be loaded. You can still explore its Skills below.