skills

Created: May 13, 2026

Last commit: July 4, 2026

Shell53.7%

Python30.3%

JavaScript16.1%

README.md

skills

A collection of agent skills I use day-to-day with Claude Code, Codex, OpenCode, and other agent harnesses. Each skill is a self-contained folder with a SKILL.md (frontmatter + instructions) plus any supporting references, scripts, or templates.

Skills

Skills are grouped into category folders — review/, agent/, app-dev/, creative/, and platform/. Each skill is still a self-contained folder one level down (e.g. app-dev/chrome-cdp/), and the install loop below discovers them at any depth, so the runtime skill name is just the folder's basename regardless of which category it lives in.

Skill	What it does
`chrome-cdp`	Inspect, measure, and screenshot a running Chrome tab via the DevTools Protocol — useful for frontend debugging, computed-CSS inspection, and visual diffs.
`excalidraw-skill`	Programmatic canvas toolkit for creating and refining Excalidraw diagrams via MCP, with element-level CRUD and PNG/SVG export.
`hermesp-logs`	Locate, tail, and summarize Hermes personal-profile logs when debugging stuck sessions or reconstructing a chat.
`md-share`	Produce a standalone shareable HTML snapshot of a markdown doc using md-preview's UI (pan/zoom mermaid, TOC, fullscreen).
`mini-shai-hulud-scan`	Triage a Mac/Linux dev machine for compromise from the May 2026 Mini Shai-Hulud npm + PyPI supply-chain attack.
`nvim-config`	Read the user's Neovim configuration before answering questions about plugins, keybinds, or LSP setup.
`obsidian-excalidraw`	Create, edit, and debug Excalidraw diagrams inside an Obsidian vault. Handles the `.excalidraw.md` wrapper format and the Text-Elements-corruption gotcha.
`react-flow-v12`	Reference pack for `@xyflow/react` v12+: custom nodes/edges, handles, layouts, viewport state, migration from v11.
`skill-maker`	Scaffold and register a new local skill using a consistent symlink convention across Claude, agent, and OpenCode roots.

Install

Clone the repo anywhere, then symlink each skill into the runtime root your agent reads from. The clone path doesn't matter — skill-maker auto-detects the source root from its own location, and the loop below works off whatever REPO you set. Most agents look for skills under ~/.claude/skills/; some also read ~/.agents/skills/. Symlinking into both is fine — they'll both resolve to the same source.

REPO="$HOME/dev/skills"   # any path — skill-maker auto-detects its own location
git clone git@github.com:Volpestyle/skills.git "$REPO"
mkdir -p ~/.claude/skills ~/.agents/skills

# Skills live under category folders, so discover them by their SKILL.md
# (works at any depth) and symlink each by its folder basename.
find "$REPO" -name SKILL.md -not -path '*/.git/*' | while read -r f; do
  s="$(dirname "$f")"
  name="$(basename "$s")"
  ln -sfn "$s" ~/.claude/skills/"$name"
  ln -sfn "$s" ~/.agents/skills/"$name"
done

Some skills have additional setup (a running MCP server, a Chrome instance on a debug port, etc.) — each SKILL.md documents its prerequisites.

Authoring more skills

Use the skill-maker skill (or copy its scaffolding) to add a new skill. The convention enforced is:

Source of truth lives in this repo (or another versioned repo).
~/.claude/skills/<name> and ~/.agents/skills/<name> are always symlinks, never plain directories.
SKILL.md frontmatter includes name, description, and — for skills that should auto-trigger on keywords rather than be invoked by name — user-invocable: false.

License

MIT — see LICENSE.