Agent Native

help

This skill fetches the latest Sculptor documentation from GitHub and answers user questions about how to use Sculptor's features, including workspaces…

by ImbueOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (imbue-ai)

Agents
Claude Code
License
MIT (permissive)
Pin
f847102pinned Oct 9, 2026
Context cost
about 880 tokenswhen the skill loads
GitHub stars
236on imbue-ai/sculptor
Scripts
None found

What it does

“Ask any question about Sculptor.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill fetches the latest Sculptor documentation from GitHub and answers user questions about how to use Sculptor's features, including workspaces, agents, code review, and other functionality. It detects the current docs layout and retrieves raw markdown files to provide accurate, up-to-date information based on live documentation rather than training data.

When to use it

  • User asks how Sculptor works or how to use a specific feature
  • User is new to Sculptor and needs an introductory overview
  • User has questions about workspaces, agents, code review, or slash commands

When not to

  • User needs help with issues outside Sculptor's documentation scope
  • Agent should rely on its training knowledge instead of live docs

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add imbue-ai/sculptor --skill help

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install imbue-ai/sculptor help@f847102ada1d6896bf6a3a5eccde996760526d9e

Installs the commit we checked (f847102).

Copy by hand

Download the folder at f847102 and put it in .claude/skills/help for Claude Code and in .agents/skills/help for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at f847102

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "help" by Imbue.

Source, pinned to commit f847102ada1d6896bf6a3a5eccde996760526d9e:
https://github.com/imbue-ai/sculptor/tree/f847102ada1d6896bf6a3a5eccde996760526d9e/sculptor/sculptor-plugin/skills/help

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/help/ for Claude Code and .agents/skills/help/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/imbue/help

SKILL.md at the pin

---
name: help
description: Ask any question about Sculptor.
when_to_use: |
  Invoke when the user asks how Sculptor works, how to use a Sculptor feature
  (workspaces, agents, code review, actions, slash commands), or a general
  "what is Sculptor" question. Fetches the latest docs from
  github.com/imbue-ai/sculptor rather than relying on training data.
user_invocable: true
---

# Sculptor Help

ARGUMENTS: $ARGUMENTS

The docs live in `imbue-ai/sculptor`. This skill ships inside the Sculptor app
and fetches the docs at runtime, so always pull the live files (with `curl`, not
WebFetch — we need the raw markdown, not an AI summary) and answer from them.

## Step 1 — detect the docs layout

The repo's layout changed when Sculptor was open-sourced: the help docs moved
from the repo root into `docs/help/`. Detect which layout is live before
fetching, so this skill keeps working across that transition:

```bash
curl -s -o /dev/null -w '%{http_code}' \
  https://raw.githubusercontent.com/imbue-ai/sculptor/main/docs/help/README.md
```

- `200` → **current layout**: index and pages live under `docs/help/`.
- anything else → **legacy layout**: index at the repo root, pages under `docs/`.

| | Current layout (`docs/help/`) | Legacy layout (flat) |
|---|---|---|
| Index (TOC) | `docs/help/README.md` | `SUMMARY.md` |
| Page | `docs/help/<page>.md` | `docs/<page>.md` |

## Step 2 — fetch and answer

Fetch the index, then the relevant page(s) at the matching base path. For
example, in the current layout:

```bash
curl -fsSL https://raw.githubusercontent.com/imbue-ai/sculptor/main/docs/help/README.md
curl -fsSL https://raw.githubusercontent.com/imbue-ai/sculptor/main/docs/help/<page>.md
```

The index lists each page by its relative path — mostly bare filenames like
`workspaces.md`, though some live in subfolders (e.g. `experimental/`). Resolve
each against the base path you chose in Step 1. Answer the user's question from
the page contents. If the docs don't cover it, link to the
[full docs](https://github.com/imbue-ai/sculptor/tree/main/docs/help).

## Response guidelines

### First-time user intro

If the user's prompt matches any of these patterns:

- "I just set up Sculptor for the first time"
- "What should I know to get started?"
- "Tell me about Sculptor"
- No arguments / empty prompt
- First message in a fresh conversation
- Any phrasing that suggests the user is new to Sculptor

Then respond with a **short, welcoming intro** (fits on one screen — no
scrolling). Use the live docs you fetched to fill in accurate details, but follow
this structure:

1. **One-line welcome.** Say what Sculptor is in a sentence.
2. **Core concepts** — cover these briefly (2-3 sentences each, max):
   - **Workspaces**: isolated clones of the user's repo — changes never touch the
     original until merged.
   - **Agents**: AI coding assistants that run inside workspaces. Multiple can run
     in parallel, but they share the workspace filesystem.
   - **Code review**: how to review and merge agent changes back (PRs, push/pull).
3. **Follow-up prompt**: tell the user — Want to learn more? Run `/sculptor:help`
   and ask a question.
4. **One link**: point to the full docs at
   `https://github.com/imbue-ai/sculptor/tree/main/docs/help`.

Constraints:

- **Keep it short.** The entire response must fit on one screen without
  scrolling. Aim for ~150-200 words.
- **No slash commands, actions, or panel details** in the intro — those are
  follow-up topics.
- **Only one link** (the docs). All sub-pages are reachable from there.
- **Do NOT reproduce this template verbatim.** Use the live docs to fill in
  current, accurate details. The structure above is a guideline, not a script.

### All other questions

For any other question, fetch the relevant page(s) listed in the index and answer
based on the docs. Keep answers concise and link to the docs if the user wants to
read more.

From imbue-ai/sculptor at f847102, shown as plain text under its license: MIT (permissive). The license text is in LICENSE.md.

View SKILL.md on GitHub at f847102

Files

1 file, 3.9 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at f847102
All 50 skills from Imbue

More from Imbue

  • architect

    Generates an architecture document for a feature by reading the existing spec, analyzing the codebase deeply, and conducting guided Q&A with the user to…

    Claude Code · about 4K tokens · pinned 6 days ago

  • build

    This skill executes a multi-step implementation plan by working through task files sequentially.

    Claude Code · about 1.1K tokens · pinned 6 days ago

  • build-sculptor-extension

    Build or modify Sculptor extensions, which are runtime ES modules that add panels, overlays, widgets, home views, or settings UI to the Sculptor frontend.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3.3K tokens · pinned 6 days ago

  • fix-bug

    Fixes bugs using test-driven development with an interactive or autonomous workflow.

    Claude Code · about 9.8K tokens · pinned 6 days ago

  • handoff

    This skill hands off ongoing work to a fresh agent, either in the same workspace or a new isolated workspace, while preserving context through a synthesized…

    Claude Code · about 1.1K tokens · pinned 6 days ago

  • mock

    Creates interactive HTML mocks for features through guided iteration with users in exploration mode (generating 3+ variants to explore ideas) or confirmation…

    Claude Code · about 3K tokens · pinned 6 days ago

All Coding workflow skills
  • planning

    This skill orchestrates multi-workflow projects with dependencies and shared data tables by creating a task graph in the orchestrator via the create-tasks tool.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 2.4K tokens · pinned 6 days ago

  • progressive-building

    This skill implements incremental workflow development for agents building or extending workflows.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 1.4K tokens · pinned 6 days ago

  • workflow-builder

    Builds and edits n8n workflows using the TypeScript SDK.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 14.2K tokens · pinned 6 days ago

  • remotion-upgrade

    This skill upgrades Remotion and its related packages to the latest stable version.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 460 tokens · pinned 6 days ago

  • remotion-upgrade

    This skill upgrades Remotion and related packages across a project, automatically detecting the package manager and workspaces.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 460 tokens · pinned 6 days ago

  • final-release-review

    Audits Python SDK release candidates or plans against the previous release, comparing diffs for regressions, API changes, and version compatibility.

    by OpenAIOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 5.4K tokens · pinned 6 days ago

Open roles at Imbue

No open roles at Imbue on the Agent Native jobs board right now.

Browse the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use