Updated 2w ago
by Vesely
skills
My personal collection of Claude Code skills
28 GitHub stars (28)
Steady at 28 stars — no new stars in the 16 days since Sep 30.
- 24 skills (24 skills found in its SKILL.md files)
- 4 forks (4 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add Vesely/skills
Asks which skills and agents to install. Just one: npx skills add Vesely/skills --skill ai-gateway — add -g for every project.
Claude Code
git clone https://github.com/Vesely/skillscp -r "skills/ai-gateway" ~/.claude/skills/
Copies the ai-gateway skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Vesely/skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
ai-gateway
Generate text, images, and video from the CLI via the Vercel AI Gateway (one key, hundreds of models).
ai-gateway/SKILL.md on GitHub (opens in a new tab) -
code-style
Align recently written or changed code so it matches the surrounding project's established conventions — formatting, naming, imports, comments, and idioms — learned from the codebase itself, then apply the fixes. Use this whenever the user wants their changes to "match the codebase / our conventions / the rest of the app", asks to make a diff or PR style-consistent, wants a style pass or style re…
code-style/SKILL.md on GitHub (opens in a new tab) -
context-audit
Audit your Claude Code setup for token waste and context bloat. Use when the user says "audit my context", "check my settings", "why is Claude so slow", "token optimization", "context audit", or runs /context-audit. Starts by running /context to see real overhead, then audits MCP servers, CLAUDE.md rules, skills, settings, and file permissions. Returns a health score with specific fixes.
context-audit/SKILL.md on GitHub (opens in a new tab) -
cursor-agent
Delegate a task to Cursor's CLI agent (code review, Q&A, planning) for a second opinion from a non-Claude model
cursor-agent/SKILL.md on GitHub (opens in a new tab) -
dynamic-agents
Orchestrate a large task across multiple agents with cost-aware model routing — session model for judgment-heavy work, Sonnet for mechanical work, Fable or GPT-5.6-sol-and-newer via Codex CLI for the hardest nodes and cross-model review. Decomposes, routes, picks fan-out vs team topology, presents the plan, executes, and verifies. Use when the user invokes /dynamic-agents, says "dynamic agents" o…
dynamic-agents/SKILL.md on GitHub (opens in a new tab) -
gh-upload
Upload an image, GIF or video into a GitHub PR or issue body and get back a github.com/user-attachments URL. `gh` has no native command for this — this is the same endpoint the web UI's drag-and-drop uses, so the asset inherits the repo's visibility instead of sitting on a public host. Use when embedding a screenshot, before/after collage, screencast or UI proof into a PR description, an issue, o…
gh-upload/SKILL.md on GitHub (opens in a new tab) -
handoff-to-worktree
Packages the current chat (or one or more specific issues/topics) into self-contained handoff files and launches each in its own fresh `claude` session with a dedicated, meaningfully named git worktree — so work continues without manual context copy-paste. Each child claude inherits the CALLER session's permission mode (no hardcoded bypass). Requires cmux: by default each handoff opens as a new c…
handoff-to-worktree/SKILL.md on GitHub (opens in a new tab) -
handsfree
Hands-free voice loop for driving Claude by voice. Combines the say skill (Gemini TTS audio out), a focus-pull back to the caller's cmux prompt, Wispr Flow dictation (voice in), and an appendix-stop listener so the user ENDS and SUBMITS each turn by saying the word appendix. When active, every reply is spoken aloud and the mic is auto-armed, so the user answers and sends without touching the keyb…
handsfree/SKILL.md on GitHub (opens in a new tab) -
medium-research
Two-phase research workflow for Medium articles. Phase 1 discovers candidates via RSS tag feeds plus DuckDuckGo content search; Phase 2 spawns one subagent per selected article to fetch full content through the Freedium mirror (paywall bypass) and return a structured digest. Use whenever the user wants to research a topic on Medium, surface trending or recent articles, pull full text from member-…
medium-research/SKILL.md on GitHub (opens in a new tab) -
park-workspace
Free the RAM held by idle Claude sessions in cmux workspaces without closing the workspaces, so they stay visible as a TODO list. Parks a single workspace, a whole cmux window, or a named set — stopping the claude session plus its dev servers and test browsers — and restores the exact session later with full history. Use when the user says "zaparkuj tenhle workspace", "zaparkuj celé okno", "park…
park-workspace/SKILL.md on GitHub (opens in a new tab) -
pr-handoff
Generates annotated browser screenshots of every UI change as the primary PR deliverable — plus an optional GIF screencast for multi-step or animated flows — then writes a concise PR title and description ready to paste into GitHub, and optional data-model documentation notes. Reviews the current branch diff against the default branch, captures every affected user-facing surface with the agent-br…
pr-handoff/SKILL.md on GitHub (opens in a new tab) -
root-cause
Use when a defect's mechanism is known and the change you are about to ship may leave it intact — prompt/instruction tweaks, retries, warnings, post-hoc repair, fallbacks, guards downstream of the bad value — or when cost, risk, validation difficulty or scope is steering you toward a substitute. Fires on YOUR OWN reasoning, not just the user's words — "too risky to change", "hard to validate", "w…
root-cause/SKILL.md on GitHub (opens in a new tab) -
say
Summarize and simplify the last agent message, then speak it aloud via Gemini TTS (Vertex AI, voice Charon), in whatever language the user is using in the session. Falls back to sag/macOS say.
say/SKILL.md on GitHub (opens in a new tab) -
screencast
Turn an agent-browser session into a polished product-demo video — fully local, free, no cloud upload. Records the browser to WebM while logging every action, then composites an MP4 with automatic zoom-to-click, a smooth animated cursor with trail, click ripples, a keystroke overlay (keycast), idle trimming, chapters (burned-in lower-thirds plus embedded MP4 chapters), and a gradient background w…
screencast/SKILL.md on GitHub (opens in a new tab) -
share-file
Upload a local file to private R2 temp storage and get back a public direct URL that auto-expires. Use when you need to host a screenshot, screencast, GIF, PDF, log or any artifact so it can be embedded in a PR description, pasted into Slack/Linear, or shared as a preview link — anything you would previously have sent to catbox, 0x0.st or an image host. Triggers on "upload this", "share this file…
share-file/SKILL.md on GitHub (opens in a new tab) -
skillify
Capture the current session's repeatable process into a reusable SKILL.md skill file. Use when the user wants to create a skill, save a workflow as a skill, turn a process into a reusable skill, or mentions "skillify", "create skill", "make a skill", "save as skill", "capture workflow", "turn this into a skill", "new skill", or wants to automate a repeatable process they just performed.
skillify/SKILL.md on GitHub (opens in a new tab) -
ssh-gui
Drive the graphical desktop of a remote macOS machine over plain ssh, with no VNC, no screen sharing and no agent installed on the far side. Gives you clicks, drags, keystrokes, text entry, menu navigation, window geometry and screenshots through cliclick, screencapture and the accessibility API, with a coordinate model that actually lines up on Retina displays and a preflight that tells you whic…
ssh-gui/SKILL.md on GitHub (opens in a new tab) -
supply-chain-protection
One-time setup of supply-chain protections for a project. Detects the package manager (npm, pnpm, Yarn, Bun), installs Socket Firewall (sfw), configures a 48-hour minimum package release age, and writes persistent dependency rules to CLAUDE.md. Use when the user mentions supply chain protection, dependency security, securing packages, malicious dependencies, typosquatting defense, "setup sfw", So…
supply-chain-protection/SKILL.md on GitHub (opens in a new tab) -
temp-email
Create and manage temporary/disposable email inboxes via tempmail.lol API (no dependencies, just curl). Use whenever the user needs a throwaway email — E2E testing, account registration, email verification, OTP confirmation, or any disposable inbox scenario. Triggers on: "temp email", "temporary email", "disposable email", "dočasný email", "dočasná schránka", "throwaway email", "fake email for te…
temp-email/SKILL.md on GitHub (opens in a new tab) -
tldr
Open with a short ✅/⚪ checklist of the milestones the thread actually hit, compress the whole thread — the problem or feature being worked on and how it was solved — into a single TL;DR line, then propose up to three terse next-step labels (≤8 words each, slash commands welcome) the user can take. Use whenever the user types `/tldr`, `/recap`, says "tldr", "tl;dr", "summarize and suggest next ste…
tldr/SKILL.md on GitHub (opens in a new tab) -
token-burn
Analyze recent Claude Code sessions and report where the most tokens (and estimated cost) were burned, with data-driven tips to cut usage and avoid rate limits. Scans ~/.claude/projects session logs over a window (default last 5h, configurable), ranks the heaviest sessions and projects, breaks down cache efficiency and model spend, and renders a minimalist report — in a cmux markdown panel when c…
token-burn/SKILL.md on GitHub (opens in a new tab) -
use-skill
Fetch and execute a remote skill on-the-fly without installing it permanently. Use when the user wants to try a skill once, run a skill from GitHub, use a remote skill without installing, or mentions "use-skill", "run remote skill", "try this skill", "fetch skill", "one-time skill", or provides a GitHub URL/shorthand pointing to a skill they want to execute. This is the go-to skill whenever someo…
use-skill/SKILL.md on GitHub (opens in a new tab) -
windows
Run a UTM Windows VM and control it via agent-browser over noVNC
windows/SKILL.md on GitHub (opens in a new tab) -
wispr
Control the Wispr Flow voice dictation app on macOS from the shell via its `wispr-flow://` URL scheme — lets an AI agent (e.g. Claude Code) turn Wispr Flow listening on and off for the user. Use when the user wants an agent to start or stop dictation programmatically, toggle hands-free listening, or switch the dictation microphone — e.g. "start dictation", "start wispr", "start listening", "turn…
wispr/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.