What does this skill do, and when should you use it?
claude-skins is a visual-theme (skin) manager skill for the Claude Code CLI. A single /skin command lists, switches, resets, or sets a permanent default skin. Each skin can change terminal colors, braille/ASCII banners, the status line, Claude's voice personality, and tool feedback sounds all at once. Nine ready-made skins ship with the project (Nebula, Mythos, Netrunner, Noir, and more), plus a template and SCHEMA.md for building your own. Skins change only look, sound, and feel — never core behavior.
Runs shell scripts under ~/.claude/skins/engine/ to perform the work: bare /skin calls skin-command-hook.sh to list skins and highlight the active one; /skin <name> calls activate.sh to apply OSC color sequences, banners, status-line theme and sounds, and reads personalities/<name>.md so Claude adopts that voice for the session; /skin reset calls deactivate.sh to restore terminal defaults; /skin default reads engine/current and writes the value into default_skin in config.yaml. Switching is instant, no restart needed.
- Developers who like to retheme their dark terminal and add some ritual to their dev environment
- Users who want Claude to speak in different voices per mood — Noir detective narration or Grimoire wizard codex
- macOS/Linux users who want audible feedback on file writes, commands, and errors
- Dotfiles enthusiasts managing terminal setup as reproducible configuration
- Terminal-theme hobbyists who want to design branded skins using template.yaml and SCHEMA.md
How do you install this skill?
- Installation requires manually editing ~/.claude/settings. to mount SessionStart/SessionEnd/PostToolUse hooks and the status line, expanding Claude Code session behavior — review before enabling.
- Scripts depend on jq and on repo files outside this assessed path (install.sh, SCHEMA.md, COMPATIBILITY.md); completeness is unverified.
- No tests or CI evidence; terminal escape-sequence compatibility and /tmp state-file safety are independently unverified.
- Publisher is not verified by the FollowSkills registry and identity is unknown; no versioning or changelog, upgrades require manual repo tracking.
- Sound and statusline features may silently degrade; core function depends entirely on the Claude Code CLI ecosystem and documentation is English-only.
- Shell / CLI
- Local filesystem
Claude Code CLIterminal with OSC sequence support (iTerm2, Kitty, WezTerm, Ghostty, Alacritty, Windows Terminal, Terminal.app)hooks entries in ~/.claude/settings.
Clone and run the installer: git clone https://github.com/basicScandal/claude-skins.git && cd claude-skins && ./install.sh. Manual route: copy skins/ and personalities/ to ~/.claude/skins/, copy engine/ to ~/.claude/skins/engine/, chmod +x ~/.claude/skins/engine/*.sh, then add SessionStart, SessionEnd, PostToolUse hooks and the statusLine entry to ~/.claude/settings., and create ~/.claude/skills/skin/SKILL.md from engine/SKILL.md.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/basicScandal/claude-skins.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/engine" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Inside a Claude Code session: /skin lists available skins; /skin nebula switches immediately; /skin reset deactivates and restores defaults; /skin default makes the current skin permanent. Switches take effect instantly with no restart.
What are this skill's strengths and limitations?
- A single /skin command switches themes instantly, no restart
- Covers five layers at once: colors, banner, status line, personality, sounds
- Nine varied ready-made skins plus a template and full SCHEMA for custom ones
- Missing values inherit from the default skin, so you only define differences
- MIT licensed; works with iTerm2, Kitty, WezTerm, Ghostty, Alacritty and more
- Tool sounds on Linux depend on PulseAudio/ALSA; Windows requires WSL
- Installation involves manually editing settings. for several hooks and the status line
- Voice personality applies only to the current session unless the skin is set as default
- No test suite shown in the repo; no automated cross-terminal verification evidence
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Claude Skins Terminal Themes this page | 56 · Use with care | ★ 19 | 5mo ago | MIT |
| cmux Diagnostics | 51 · Use with care | ★ 28k | 11d ago | NOASSERTION |
| cmux Settings Management Skill (cmux-settings) | 58 · Recommended | ★ 28k | 11d ago | NOASSERTION |
| CCM — Claude Code Manager | 55 · Use with care | ★ 29 | 2mo ago | MIT |
| SPARV Five-Phase Workflow | 55 · Use with care | ★ 2.8k | 5mo ago | AGPL-3.0 |
The README states the project is inspired by joeynyc/hermes-skins, with the Mythos and Netrunner banner art adapted from that project under MIT license.
How did FollowSkills review this skill?
Scripts operate only on local files (~/.claude/skins, output-styles symlinks, /tmp marker), no network access, no credential reading, no covert behavior; activate/reset both have rollback paths (OSC 110-112 resets, symlink cleanup, default restore). Deductions: restore state marker in a shared /tmp path is theoretically interferable; installation requires users to manually wire multiple hooks into settings. (blast radius beyond pure cosmetics) and the SKILL.md itself never discloses this to the user; writes to /dev/tty without verifying terminal capability. Overall risks are visible and controllable.
Scripts are largely self-consistent: argument defaults, skin-not-found listing with exit 1, set -euo pipefail, TTL-cached parses. Deductions: no tests or CI evidence covering key paths; SKILL.md depends on jq and repo-internal scripts without declaring prerequisites; skin-command-hook.sh pipes JSON through echo "$input", which can corrupt backslash sequences; statusline.sh caches ANSI escapes and mixes echo -e/printf semantics, cross-terminal behavior unverified; abnormal input (skin names with spaces) lacks diagnosable failure messages.
Trigger conditions are explicit (/skin, change skin, switch theme via USE WHEN description), four subcommands clearly defined, non-fit environments (no-OSC terminals) documented in README. Deductions: capability boundaries only partially disclosed (manual hook installation, hard Claude Code CLI dependency); no Chinese language support; core function entirely depends on the Claude Code ecosystem, which needs disclosure for mainland-China users; personality activation silently depends on files existing and on correct prior installation.
README is well-structured (quick start, manual install, gallery, hooks, customization), MIT license complete, banner adaptation from hermes-skins properly attributed. Deductions: no version number or changelog; SKILL.md requires manual copy with no version-sync mechanism; maintenance responsibility and update path only implied via Discussions; SCHEMA.md, CONTRIBUTING.md, and install.sh are referenced but outside the reviewed evidence, so key install assumptions are not statically verifiable.
The core task (switching colors, banners, status line, sounds) is self-consistent at script level, instant switching with clear rollback, clear marginal value over manually editing terminal themes. Deductions: static review cannot verify actual rendering; demo.gif is self-submitted; statusline escape output compatibility is unverified; sound features may silently degrade to silence on many Linux setups, so completeness of the promised experience is uncertain.
Evidence is primarily auditable primary source: SKILL.md, engine scripts, and README cross-corroborate (command names, paths, hook names align), and adaptation attribution to hermes-skins is explicit. Deductions: no test suite, no CI workflow, no third-party execution evidence; demo.gif and gallery page cannot be verified statically; referenced COMPATIBILITY.md and SCHEMA.md are not provided, so compatibility claims cannot be cross-checked. Static ceiling of 5 applies; 4 after coverage deduction.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →