Lunora Quickstart
anolilab/lunora
Creates a new Lunora project or adds Lunora to an existing app, then gets the first schema + query/mutation round-trip running.
Collects your feedback on a running feature, typed or spoken and drawn in the browser, and turns it into focused UX fixes saved as local commits.
Install Live UX Polish
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install EveryInc/compound-engineering-plugin ce-polish --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ce-polish .claude/skills/ce-polish && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ce-polish" agent skill from https://github.com/EveryInc/compound-engineering-plugin/tree/main/skills/ce-polish into .claude/skills/ce-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ce-polish", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/EveryInc/compound-engineering-plugin/tree/main/skills/ce-polishType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install EveryInc/compound-engineering-plugin ce-polish --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ce-polish .agents/skills/ce-polish && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ce-polish" agent skill from https://github.com/EveryInc/compound-engineering-plugin/tree/main/skills/ce-polish into .agents/skills/ce-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ce-polish", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install EveryInc/compound-engineering-plugin ce-polish --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ce-polish .cursor/skills/ce-polish && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ce-polish" agent skill from https://github.com/EveryInc/compound-engineering-plugin/tree/main/skills/ce-polish into .cursor/skills/ce-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ce-polish", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/EveryInc/compound-engineering-plugin.git --path skills/ce-polish--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install EveryInc/compound-engineering-plugin ce-polish --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ce-polish .gemini/skills/ce-polish && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ce-polish" agent skill from https://github.com/EveryInc/compound-engineering-plugin/tree/main/skills/ce-polish into .gemini/skills/ce-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ce-polish", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install EveryInc/compound-engineering-plugin ce-polishInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ce-polish .github/skills/ce-polish && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ce-polish" agent skill from https://github.com/EveryInc/compound-engineering-plugin/tree/main/skills/ce-polish into .github/skills/ce-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ce-polish", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install EveryInc/compound-engineering-plugin ce-polish --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/EveryInc/compound-engineering-plugin.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ce-polish .opencode/skills/ce-polish && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ce-polish" agent skill from https://github.com/EveryInc/compound-engineering-plugin/tree/main/skills/ce-polish into .opencode/skills/ce-polish/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ce-polish", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ce-polish- GitHub stars
- 25k
- Token cost
- ~777 tokens
- SKILL.md length
- 469 words
- Files
- 25 (incl. scripts, references)
- Skills in repo
- 37
- Repo updated
- First seen
- Licence
- MIT
At a glance
Collects your feedback on a running feature, typed or spoken and drawn in the browser, and turns it into focused UX fixes saved as local commits.
- Works in 5 steps: Ask live or traditional. Ask once,… → Get the live page ready. Read… → Wait for observations. Tell the user… → …
- A feature works but needs UX refinement before it ships
- Gathering spoken and drawn feedback on a page running locally
- Applying a series of small interface fixes you spot while browsing the app
What it does
Polish starts the dev server for a feature that already works and puts the page in front of you, then turns what you notice into small UX fixes on the running page. You pick one of two ways to give feedback: typing what could be better, or a live mode where you talk and draw on the page while a voice interviewer turns your speech into units the agent acts on at checkpoints.
The agent only works on what you point at. It does not invent its own checklist or widen the pass into general QA, it refuses to work on the repository's default branch, and it saves changes as local commits without pushing or opening a pull request. Reference files cover dev-server discovery for Astro, Next, Nuxt, Rails, Remix, SvelteKit, Vite and Procfile-based apps.
Live mode needs an OpenAI key in the environment, streams the session to a local endpoint that the skill runs, and may add the riffrec dependency and a provider mount as a setup commit that stays on your branch. When the session ends you get a list of feedback that was not applied, plus the path of the session log.
When your agent uses it
- A feature works but needs UX refinement before it ships
- Gathering spoken and drawn feedback on a page running locally
- Applying a series of small interface fixes you spot while browsing the app
Example prompts
- “Polish the new checkout page. I'll type what looks off as I click through it.”
- “Start a live polish session on the settings screen so I can talk through the changes.”
- “Run polish on the dashboard branch and commit each fix locally.”
Requirements
- A web app that can run a local dev server
- An OpenAI API key for live voice mode
- A git branch other than the default branch
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Ask live or traditional. Ask once, before any server starts. Include this disclosure with the question: live mode needs an OpenAI key in…
- Get the live page ready. Read references/run.md before resolving the requested ref or starting anything. It owns existing-worktree safety…
- Wait for observations. Tell the user where the server is running and ask what could be better. Do not start a review pass while they browse.
- Iterate. For each requested change, inspect only as needed, edit the in-scope surface, and let hot reload update the page. When the user…
- Close locally. When the user says they are done, invoke ce-commit for the polish changes, then report the commit(s), the still-running…
What it can do on your machine
Read from SKILL.md and the folder at commit 67035e9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Live UX Polish loads about 777 tokens when it runs, and up to ~27k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 469 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from EveryInc/compound-engineering-plugin at commit 67035e9, republished under its MIT licence (© EveryInc). 469 words, ~777 tokens.
Download SKILL.mdSave it as
.claude/skills/ce-polish/SKILL.md (or your agent's skills folder). This skill also uses 24 other files; get the full folder from GitHub.- name
- ce-polish
- description
- Polish a working feature through user-directed live browser feedback. Use when a functional feature needs focused UX refinement before shipping.
- disable-model-invocation
- true
- argument-hint
- [PR number, branch name, or blank for current branch]
Polish
Put a working feature in front of the user and turn their live observations into focused UX fixes on the running page. Two ways to collect those observations: traditional, where the user types what could be better; and live, where they talk and draw on the page while a voice interviewer turns speech into units and you act on them at checkpoints.
Done: the user ends the polish loop, every requested fix is reflected in the live feature or reported as blocked, and the in-scope changes are saved in local commit(s). A live session also ends with a residual list of the units that were not applied and the path of its session log. A server or checkout blocker also ends the run when it is reported with the evidence needed to resume.
Boundaries: the user drives what to inspect and change; do not invent an autonomous checklist or expand into general QA. Never work on the repository's default branch. This workflow may edit and locally commit the requested polish, and in live mode the disclosed riffrec setup commit, but it never pushes or opens a PR.
Run
- Ask live or traditional. Ask once, before any server starts. Include this disclosure with the question: live mode needs an OpenAI key in the environment, runs a voice interviewer in the page that hears the user, is told what they click and draw on, and looks at their screen when they point at something or ask it to, streams the session to a local endpoint this skill runs, and, when riffrec is not yet in the app, adds the riffrec dependency and a provider mount as a setup commit on the current branch that stays after the session. Traditional continues with steps 2–5 unchanged. Live: read
references/live-start.md; it owns preconditions, install, the endpoint, and the URL handoff, applies the workspace and server rules ofreferences/run.mditself, then routes toreferences/live-loop.mdfor the session and its close. Steps 2–5 do not run for a live session. - Get the live page ready. Read
references/run.mdbefore resolving the requested ref or starting anything. It owns existing-worktree safety, dev-server discovery, the bundled-script calls, reachability, and the browser handoff. - Wait for observations. Tell the user where the server is running and ask what could be better. Do not start a review pass while they browse.
- Iterate. For each requested change, inspect only as needed, edit the in-scope surface, and let hot reload update the page. When the user asks you to inspect the result, use a browser capability available in the active harness; if none exists, ask them to describe what they see.
- Close locally. When the user says they are done, invoke
ce-commitfor the polish changes, then report the commit(s), the still-running server URL, and any residual blocker.
© EveryInc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 24 other files (scripts, references) in skills/ce-polish of EveryInc/compound-engineering-plugin.
- SKILL.md
- agents/openai.yaml
- references/dev-server-astro.md
- references/dev-server-detection.md
- references/dev-server-next.md
- references/dev-server-nuxt.md
- references/dev-server-procfile.md
- references/dev-server-rails.md
- references/dev-server-remix.md
- references/dev-server-sveltekit.md
- references/dev-server-vite.md
- references/install-riffrec.md
- references/launch-json-schema.md
- references/live-loop.md
- references/live-remote.md
- references/live-start.md
- references/live-stream-contract.md
- references/run.md
- scripts
- … and 6 more
Open the folder on GitHubat commit 67035e9
Compare with similar skills
Live UX Polish next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Live UX Polish this skillEveryInc/compound-engineering-plugin | 25k | — | ~777 | Automated safety check: Pass | MIT | |
| Lunora Quickstartanolilab/lunora | 283 | — | ~2.5k | Automated safety check: Pass | Custom licence | |
| Super UI UX Designsyahiidkamil/Software-Engineer-AI-Agent-Atlas | 401 | — | ~9k | Automated safety check: Pass | None | |
| Tabler Asset Pipelinetabler/tabler | 42k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Design LabNeverSight/learn-skills.dev | 216 | 1 repos | ~7.5k | Automated safety check: Pass | None | |
| GSAP in Vue, Nuxt and Sveltegreensock/gsap-skills | 16k | 4 repos | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Super UI UX Design
syahiidkamil/Software-Engineer-AI-Agent-Atlas
Complete UI/UX design capability — a wiki-style knowledge map of design theory (UX laws, Nielsen heuristics, usability, visual hierarchy, typography, contrast/WCAG, design systems…
Tabler Asset Pipeline
tabler/tabler
Explains which build step writes each asset directory in the Tabler repo and how to fix missing, stale or duplicated CSS and JS files.
Design Lab
NeverSight/learn-skills.dev
Conduct design interviews, generate five distinct UI variations in a temporary design lab, collect feedback, and produce implementation plans.
GSAP in Vue, Nuxt and Svelte
greensock/gsap-skills
Shows how to use GSAP in Vue, Nuxt, Svelte and other lifecycle-based frameworks: create after mount, scope selectors to the component, and revert on unmount.
Sanity Best Practices
robotostudio/turbo-start-sanity
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and…
More from EveryInc/compound-engineering-plugin
All 37 skills in this repoCompound Learning Writer
EveryInc/compound-engineering-plugin
Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.
Compound Learnings Refresh
EveryInc/compound-engineering-plugin
Audits a repo's stored learnings against the current codebase, fixes stale, overlapping or superseded docs and reports on every document.
Compound Engineering Prototype
EveryInc/compound-engineering-plugin
Builds a throwaway prototype at just the fidelity needed to settle a specific how-it-should-work-or-feel question, before committing to an approach other work will treat as fixed.
Compound Engineering Setup
EveryInc/compound-engineering-plugin
Checks Compound Engineering plugin health and repo-local config, or scaffolds a Compound Pack when you ask for one by id.
PR Babysitter
EveryInc/compound-engineering-plugin
Watches an open GitHub pull request over time, routing review comments and CI failures to other skills until the PR is ready to merge.
CE Brainstorm
EveryInc/compound-engineering-plugin
Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.
Related
Categories
Questions about Live UX Polish
What does Live UX Polish do?
Collects your feedback on a running feature, typed or spoken and drawn in the browser, and turns it into focused UX fixes saved as local commits. Polish starts the dev server for a feature that already works and puts the page in front of you, then turns what you notice into small UX fixes on the running page. You pick one of two ways to give feedback: typing what could be better, or a live mode where you talk and draw on the page while a voice interviewer turns your speech into units the agent acts on at checkpoints.
When should I use Live UX Polish?
Live UX Polish fits situations like: A feature works but needs UX refinement before it ships; gathering spoken and drawn feedback on a page running locally; applying a series of small interface fixes you spot while browsing the app.
How do I install Live UX Polish in Claude Code?
Run `npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a claude-code`. Or copy the skill folder (skills/ce-polish in EveryInc/compound-engineering-plugin) into .claude/skills/ce-polish in your project. Claude Code loads it when a task matches its description.
How do I install Live UX Polish in Codex?
Run `npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a codex`. Or copy the skill folder (skills/ce-polish in EveryInc/compound-engineering-plugin) into .agents/skills/ce-polish in your project. Codex loads it when a task matches its description.
Can I use Live UX Polish in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add EveryInc/compound-engineering-plugin --skill ce-polish -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ce-polish, .gemini/skills/ce-polish, .github/skills/ce-polish and .opencode/skills/ce-polish in your project.
What does Live UX Polish need to run?
SKILL.md names no scripts, command-line tools or credentials: Live UX Polish is instructions for the agent only. Our summary lists: A web app that can run a local dev server; An OpenAI API key for live voice mode; A git branch other than the default branch.
Does Live UX Polish access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Live UX Polish safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Live UX Polish use?
Live UX Polish is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Live UX Polish use?
About 777 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 26k tokens, read only when the agent opens those files.
What are the alternatives to Live UX Polish?
Skills that share tags, products or a category with Live UX Polish: Lunora Quickstart (anolilab/lunora, 283 stars), Super UI UX Design (syahiidkamil/Software-Engineer-AI-Agent-Atlas, 401 stars), Tabler Asset Pipeline (tabler/tabler, 42k stars) and Design Lab (NeverSight/learn-skills.dev, 216 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Live UX Polish?
EveryInc (a GitHub organization) maintains it in EveryInc/compound-engineering-plugin, which has 25,424 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on October 8, 2026.
Source: EveryInc/compound-engineering-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.