All authors
Claude Skills by markphelps
github.com/markphelps13 skills1 installs57 views
- Context File TuneupA `CLAUDE.md` or `AGENTS.md` file is loaded into an agent's context on every task. Different agents and repos use different filenames, and some repos keep one as a symlink or compatibility alias to the other. Treat them as the same class of file: high-leverage repo instructions for coding agents. A good one silently prevents whole classes of mistakes; a bloated or vague one wastes the context budget and gets ignored. This skill audits the target context file against a known-good structure, de...Votes: 0GitHub stars: 5
- Cli DesignDesign, 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 behavior, adding JSON or plain output modes, improving error messages, making destructive operations safer, or asking whether a CLI feels good, scriptable, discoverable, or Unix-friendly.Votes: 0GitHub stars: 5
- Github Pr FixupFix review feedback and CI failures on an existing GitHub pull request. Work on the PR's source branch. Do not open a new PR.Votes: 0GitHub stars: 5
- Oss MarketingA README is a landing page, not documentation. Most visitors give it about ten seconds before deciding to scroll past, star it, or actually try it. The job of this pass is to make sure that in those ten seconds, a developer who has never heard of the project understands three things — **what is this, why does it exist, how do I try it** — and can act on the third one immediately. Everything else is secondary. This draws on patterns from repos that consistently convert well: Vite, shadcn/ui, t...Votes: 0GitHub stars: 5
- Oss Repo ReadinessGetting a repo "open source ready" isn't about the license — that's a five-minute checkbox. It's about DevEx: whether a developer who has never talked to the maintainer can understand the project, run it, and land a contribution without having to ask a question first. Every piece of friction you remove here is a contributor you don't lose. This skill audits a repo against that bar, using patterns pulled from repos that are genuinely good at this (Vite, shadcn/ui, tRPC, Sentry, Supabase, Rust,...Votes: 0GitHub stars: 5
- Session Log AuditAudit 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 wants to find rough edges in their own tool or project, asks "what's annoying about X," wants to know why they keep working around their own software, is preparing a UX or DX pass on something they use daily, or wants to turn a week of agen...Votes: 0GitHub stars: 5
- Context File TuneupA `CLAUDE.md` or `AGENTS.md` file is loaded into an agent's context on every task. Different agents and repos use different filenames, and some repos keep one as a symlink or compatibility alias to the other. Treat them as the same class of file: high-leverage repo instructions for coding agents. A good one silently prevents whole classes of mistakes; a bloated or vague one wastes the context budget and gets ignored. This skill audits the target context file against a known-good structure, de...Votes: 0GitHub stars: 5
- Codebase Landing CopyLanding copy fails in two opposite ways: it's vague ("the modern platform for teams") so nobody gets what the product is, or it's aspirational ("AI-powered insights") and promises things the code doesn't do. This skill avoids both by treating the codebase as the source of truth and the visitor's first 10 seconds as the target. The code decides _what_ can be said; marketing craft decides _how_ it's said.Votes: 0GitHub stars: 5
- Decision RecordsA records directory is a repository's durable registry for decisions and implementation plans. A record explains what the team decided, why, and what follows from that decision. Records are historical evidence: they are appended to and amended, not rewritten. Do not use a record for a routine code change, a temporary task, a release note, or an investigation without a durable outcome.Votes: 0GitHub stars: 5
- Github Self Hosted RunnerCreate one isolated runner instance per repository or organization registration. Detect the operating system first and use the matching service manager: systemd on Linux or launchd on macOS. Determine the account that should own and run the runner instead of assuming a fixed username or home directory. On Linux, resolve the account and paths with: ```bash RUNNER_USER="${RUNNER_USER:-${SUDO_USER:-$USER}}" RUNNER_GROUP="$(id -gn "$RUNNER_USER")" RUNNER_HOME="$(getent passwd "$RUNNER_USER" | cut...Votes: 0GitHub stars: 5
- Feature MapGive agents a sitemap of the app they're changing, so they can verify their work without rediscovering how to reach and drive each feature every time. The idea comes from Lauren Tan's (@poteto) workflow: a set of short markdown files inside a verification skill, one per feature, each saying what exists, how a user gets there, how to drive it, and what trips people up. This skill is the **builder**. It writes a **generated skill** into the repo, and that generated skill is what agents use day ...Votes: 0GitHub stars: 5
- Verify BugTurn claimed bugs into verdicts you can act on. A claim is a lead, not a fact: code that looks wrong is often protected by validation in another file, a framework guarantee, a lock, a type, or configuration. And real bugs described vaguely get dismissed. This skill gives every claim a fair hearing with an advocate on each side, then records the verdict with its evidence.Votes: 0GitHub stars: 5
- WhiteboardHelp the user pass the whiteboard defense on a codebase: if someone pulls them aside and asks how a system works, why it was built this way instead of another way, where it fails, or what happens when an actor misbehaves, they can answer confidently. Line-level recall is not the goal. A high-level, defensible mental model is. The skill has two halves that feed each other: 1. **Map.** Explore the repo and write a layered architecture map with receipts for every claim about _why_. 2. **Defend.*...Votes: 0GitHub stars: 5