Skills Explorer Add Skills

enhance-prompt

An agent skill by google-labs-code, from google-labs-code/stitch-skills. Tags: brainstorming, copy-editing, design, generative, stitch.

What it does

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add google-labs-code/stitch-skills --skill enhance-prompt

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/google-labs-code/stitch-skills
cp -r stitch-skills/plugins/stitch-utilities/skills/enhance-prompt ~/.claude/skills/enhance-prompt

Safety box score

Grade B, low risk: 16 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a text-only prompt reformulation skill: it reads the user prompt and optional local `DESIGN.md`, then returns or writes an enhanced prompt. The main risks are a dependency on remote Stitch documentation and optional file writes in the working directory; it does not request secrets, elevated privileges, or destructive actions.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution1 (low)The skill itself only uses `Read` and `Write`, but the shipped `README.md` includes an install command that runs `npx` from the registry: `npx skills add google-labs-code/stitch-skills --skill enhance-prompt --global`.
Network access1 (low)`SKILL.md` explicitly tells the agent to consult the remote Stitch guide at `https://stitch.withgoogle.com/docs/learn/prompting/`, so behavior can depend on network-fetched content.
Filesystem reach1 (low)It may read a local `DESIGN.md` and can write `next-prompt.md` or a user-chosen filename, but only within the workspace.
Secrets & credentials0 (none)No instructions reference tokens, passwords, keychains, browser sessions, or other secret stores.
Privilege & persistence0 (none)There is no sudo use, global system modification, service registration, or shell/OS settings change in the skill itself.
Instruction hijack surface1 (low)The skill tells the agent to follow external documentation for “latest best practices,” so remote content can influence output, but it does not ask to ignore higher-priority instructions or hide anything.
Irreversible actions0 (none)It only transforms prompts and optionally writes a local file; it does not post, deploy, pay, book, or delete anything.
Transparency0 (none)All shipped files are plain markdown; there are no binaries, generated blobs, or unreviewable installers in the skill bundle.

Before installing

Rated 2026-10-21 by an automated review of 3 files from the skill's repository.

Source

Repository
google-labs-code/stitch-skills (all skills from this repository)
Path
plugins/stitch-utilities/skills/enhance-prompt/SKILL.md
Branch
main
Collection
stitch-utilities
Updated
2026-09-19