SEO Programmatic
sickn33/agentic-awesome-skills
Plan and audit programmatic SEO pages generated at scale from structured data.
Interact with Sculptor programmatically using the sculpt CLI.
MITAuto-check passed
Install Sculpt CLI
$ npx skills add imbue-ai/sculptor --skill sculpt-cli -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install imbue-ai/sculptor sculpt-cli --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/imbue-ai/sculptor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/sculptor/sculptor-plugin/skills/sculpt-cli .claude/skills/sculpt-cli && 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 "sculpt-cli" agent skill from https://github.com/imbue-ai/sculptor/tree/main/sculptor/sculptor-plugin/skills/sculpt-cli into .claude/skills/sculpt-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sculpt-cli", 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/imbue-ai/sculptor/tree/main/sculptor/sculptor-plugin/skills/sculpt-cliType 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 imbue-ai/sculptor --skill sculpt-cli -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install imbue-ai/sculptor sculpt-cli --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/imbue-ai/sculptor.git skills-src && mkdir -p .agents/skills && cp -r skills-src/sculptor/sculptor-plugin/skills/sculpt-cli .agents/skills/sculpt-cli && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sculpt-cli" agent skill from https://github.com/imbue-ai/sculptor/tree/main/sculptor/sculptor-plugin/skills/sculpt-cli into .agents/skills/sculpt-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sculpt-cli", 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 imbue-ai/sculptor --skill sculpt-cli -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install imbue-ai/sculptor sculpt-cli --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/imbue-ai/sculptor.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/sculptor/sculptor-plugin/skills/sculpt-cli .cursor/skills/sculpt-cli && 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 "sculpt-cli" agent skill from https://github.com/imbue-ai/sculptor/tree/main/sculptor/sculptor-plugin/skills/sculpt-cli into .cursor/skills/sculpt-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sculpt-cli", 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/imbue-ai/sculptor.git --path sculptor/sculptor-plugin/skills/sculpt-cli--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 imbue-ai/sculptor --skill sculpt-cli -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install imbue-ai/sculptor sculpt-cli --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/imbue-ai/sculptor.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/sculptor/sculptor-plugin/skills/sculpt-cli .gemini/skills/sculpt-cli && 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 "sculpt-cli" agent skill from https://github.com/imbue-ai/sculptor/tree/main/sculptor/sculptor-plugin/skills/sculpt-cli into .gemini/skills/sculpt-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sculpt-cli", 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 imbue-ai/sculptor sculpt-cliInstalls 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 imbue-ai/sculptor --skill sculpt-cli -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/imbue-ai/sculptor.git skills-src && mkdir -p .github/skills && cp -r skills-src/sculptor/sculptor-plugin/skills/sculpt-cli .github/skills/sculpt-cli && 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 "sculpt-cli" agent skill from https://github.com/imbue-ai/sculptor/tree/main/sculptor/sculptor-plugin/skills/sculpt-cli into .github/skills/sculpt-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sculpt-cli", 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 imbue-ai/sculptor --skill sculpt-cli -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install imbue-ai/sculptor sculpt-cli --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/imbue-ai/sculptor.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/sculptor/sculptor-plugin/skills/sculpt-cli .opencode/skills/sculpt-cli && 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 "sculpt-cli" agent skill from https://github.com/imbue-ai/sculptor/tree/main/sculptor/sculptor-plugin/skills/sculpt-cli into .opencode/skills/sculpt-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sculpt-cli", 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
sculpt-cli- GitHub stars
- 237
- Token cost
- ~1.8k tokens
- SKILL.md length
- 661 words
- Files
- 1
- Skills in repo
- 29
- Repo updated
- First seen
- Licence
- MIT
At a glance
Interact with Sculptor programmatically using the sculpt CLI.
- Planning a workflow that would benefit from understanding the structural capabilities of sculpt (workspaces
- SKILL.md covers Identity: who am I?, Addressing agents in other…, Delegate-and-await: the core… and Models, plus 5 more sections
- Calls jq and git
- How code flows between them)
What it does
Sculpt CLI is an agent skill from imbue-ai/sculptor. Interact with Sculptor programmatically using the sculpt CLI. Use this skill when using sculpt, or when designing or planning a workflow that would benefit from understanding the structural capabilities of sculpt (workspaces, agents, isolation, and how code flows between them).
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Build product with grounded, parallel coding agents. The licence is MIT.
When your agent uses it
- Planning a workflow that would benefit from understanding the structural capabilities of sculpt (workspaces
- How code flows between them)
Example prompts
- “/sculpt-cli”
What it can do on your machine
Read from SKILL.md and the folder at commit f847102. 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
Shell commands in SKILL.md call:
jqgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Sculpt CLI loads about 1.8k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 661 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from imbue-ai/sculptor at commit f847102, republished under its MIT licence (© imbue-ai). 661 words, ~1,766 tokens.
Download SKILL.mdSave it as
.claude/skills/sculpt-cli/SKILL.md (or your agent's skills folder).- name
- sculpt-cli
- description
- Interact with Sculptor programmatically using the sculpt CLI. Use this skill when using `sculpt`, or when designing or planning a workflow that would benefit from understanding the structural capabilities of `sculpt` (workspaces, agents, isolation, and how code flows between them).
Sculpt CLI
CLI for interacting with the Sculptor API. Use sculpt --help for full documentation.
Identity: who am I?
Every Sculptor agent shell exports three env vars identifying the shell's own context:
| variable | meaning |
|---|---|
SCULPT_AGENT_ID | this shell's own agent (task) ID |
SCULPT_WORKSPACE_ID | this shell's workspace ID |
SCULPT_PROJECT_ID | the repo/project ID |
Commands default to them where it makes sense:
sculpt agent show # no argument: shows THIS shell's agent
sculpt agent status # ditto
sculpt workspace show # no argument: shows THIS shell's workspacesculpt agent list / sculpt workspace list mark your own row with *, and
their --json output includes an is_self field. Before reasoning about
other agents, check your own identity first — don't infer it from branch
names or workspace titles.
Addressing agents in other workspaces
Full agent IDs (and unambiguous prefixes) work from anywhere: send,
interrupt, rename, and delete resolve them across all workspaces.
SCULPT_WORKSPACE_ID only narrows ambiguous prefixes; when the agent lives
elsewhere a stderr note tells you which workspace it is in. An explicit
--workspace is authoritative — if the agent is not in that workspace, the
command errors instead of silently redirecting.
Delegate-and-await: the core orchestration pattern
--follow on run and agent send streams the reply and exits when the
turn ends, so it is a synchronous request/response primitive — prefer it
over polling:
# Create a workspace + agent, stream until its first turn finishes
sculpt run --model haiku --strategy clone --name "Experiment" "Try X and report" -f
# Send a follow-up and wait for the answer
sculpt agent send <agent-id> "And what about Y?" -fExit codes for --follow: 0 = turn completed, 2 = the agent stopped to
ask a question (WAITING). For polling instead, call the single-shot
sculpt agent status <id> --json in your own loop.
Models
agent send keeps the agent's current model unless you pass --model —
passing it switches the agent's model persistently for subsequent turns.
run / agent create default to opus; pick --model haiku/sonnet for
cheap disposable agents.
Agents waiting on a question
When an agent calls AskUserQuestion its status becomes WAITING, and
sculpt agent status shows the question and its options:
Status: WAITING
Waiting: Which color?
Options: Red | Blue(--json: waiting_detail + waiting_options.) Answering is reserved for
the human user in the Sculptor UI — there is deliberately no CLI answer
command. If you are orchestrating and must unblock the agent yourself,
sculpt agent interrupt <id> abandons the question, after which send works
again.
JSON output
All commands support --json for machine-readable output. JSON goes to
stdout, informational notes to stderr, and with --json errors are emitted to
stderr as {"error": ..., "detail": ...}. Discover each command's exact output
shape with the schema subcommand:
sculpt schema # list all available schemas
sculpt schema agent.status # JSON Schema for `sculpt agent status --json`Examples:
# Get workspace IDs
sculpt workspace list --all --json | jq '.[].id'
# Get running agents
sculpt agent list --all --json | jq '[.[] | select(.status == "RUNNING")]'
# Get agent progress
sculpt agent status <id> --json | jq '{status, progress: "\(.task_completed)/\(.task_total)"}'Examples
# List repos and workspaces
sculpt repo list --json
sculpt workspace list --all --json
# Create a workspace
sculpt workspace create --name "My workspace" --json
# Create a workspace + agent in one step
sculpt run --model opus --name "Fix bug" "Fix the login bug" --json
# Show workspace/agent details
sculpt workspace show <id> --json
sculpt agent show <id> --json
# Send a message to an agent (any workspace; keeps the agent's model)
sculpt agent send <agent-id> "Please also update the tests" --json
# Clean up (both prompt unless -y)
sculpt agent delete <agent-id> -y
sculpt workspace delete <workspace-id> -yConceptual model
A repo comprises workspaces (1:n). A workspace comprises agents (1:n).
Repo
A path on the user's machine pointing at a git repository. sculpt repo list
shows these. This is the source-of-truth git state; everything else derives
from it.
Show full SKILL.md (257 more words)Show less
Workspace
A working environment derived from a repo. The initialization strategy is fixed at creation and determines how the workspace's checkout relates to the user's repo:
| strategy | git relationship to user's repo | good for |
|---|---|---|
clone | Separate clone with shared git object store; remotes mirrored. Isolated. | disposable experiments, risky changes |
worktree | Real git worktree; .git shared. Commits land in user's repo instantly. | normal feature work (the default) |
in_place | None — agent edits the user's actual checkout. | coordination tasks on the live checkout |
Finding a workspace's files
Workspace directories on disk are named by opaque internal IDs that do NOT
match the ws_... API ID — never guess paths. Use the fields reported by
workspace show/list --json:
working_directory— the checkout directory (.../codefor clone/worktree, the repo path itself for in_place)current_branch— the branch checked out there right nowrepo_path— the user's original repo
Agent
A single coding agent running inside a workspace. Each agent has its own conversation, status, todos, state, and artifacts — but shares the workspace's checkout with every other agent in the same workspace.
What multiple agents in one workspace share
Shared: every tracked and untracked file in the checkout, and git state (HEAD, branches, working tree, index). There is no file locking between sibling agents.
Private to each agent: conversation history; TODOs, status, current activity; per-agent state and artifact directories.
Using sculpt from outside a Sculptor shell
sculpt talks to the local Sculptor app, defaulting to
http://localhost:5050. If the app serves a different port (it exports
SCULPT_API_PORT into its own shells), set that variable or pass
--base-url explicitly.
© imbue-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in sculptor/sculptor-plugin/skills/sculpt-cli of imbue-ai/sculptor.
Open the folder on GitHubat commit f847102
Compare with similar skills
Sculpt CLI 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 |
|---|---|---|---|---|---|---|
| Sculpt CLI this skillimbue-ai/sculptor | 237 | — | ~1.8k | Automated safety check: Pass | MIT | |
| SEO Programmaticsickn33/agentic-awesome-skills | 47k | 2 repos | ~2.4k | Automated safety check: Notes | MIT | |
| Remotion Interactivityremotion-dev/remotion | 63k | 5 repos | ~4.8k | Automated safety check: Pass | Custom licence | |
| Firecrawl Interact Integrationfirecrawl/firecrawl | 190k | 1 repos | ~731 | Automated safety check: Pass | ISC | |
| Interaction To Next Paintthedaviddias/Front-End-Checklist | 74k | — | ~441 | Automated safety check: Pass | MIT | |
| Create Issue Interaction UIpaperclipai/paperclip | 99k | — | ~3.4k | Automated safety check: Pass | MIT |
Similar skills
- Official
Remotion Interactivity
remotion-dev/remotion
Structure Remotion markup for interactivity. An agent skill from remotion-dev/remotion.
Firecrawl Interact Integration
firecrawl/firecrawl
Guides adding Firecrawl's /interact endpoint to product code for pages that need clicks, forms, pagination or logged-in flows beyond plain scraping.
Interaction To Next Paint
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Optimize interaction to next paint.
Create Issue Interaction UI
paperclipai/paperclip
Add a new Paperclip issue-thread interaction kind end-to-end.
Programmatic SEO Planning
AgriciDaniel/claude-seo
Plans and audits SEO pages generated at scale from data, covering data quality, templates, URL patterns and internal links while guarding against thin content and index bloat.
More from imbue-ai/sculptor
All 29 skills in this repoAuto QA Iphone
imbue-ai/sculptor
QA the Sculptor mobile web UI on a real iOS Simulator, driven headlessly from a Mac.
Measure React Renders
imbue-ai/sculptor
Compare React component render counts between origin/main and the current branch during a user-defined UI scenario (e.g.
Post PR To Slack
imbue-ai/sculptor
Post a one-line PR announcement to a Slack channel, and mark it :merged: when the PR merges.
Batch Claude Runner
imbue-ai/sculptor
Run Claude programmatically against collections of files in the codebase.
Build Sculptor Extension
imbue-ai/sculptor
Build or modify a Sculptor extension — a runtime ESM module loaded into the Sculptor UI.
Code Review Checklist
imbue-ai/sculptor
Review a set of code changes against Sculptor's review categories and produce a markdown findings table.
Questions about Sculpt CLI
What does Sculpt CLI do?
Interact with Sculptor programmatically using the sculpt CLI. Sculpt CLI is an agent skill from imbue-ai/sculptor. Interact with Sculptor programmatically using the sculpt CLI.
When should I use Sculpt CLI?
Sculpt CLI fits situations like: planning a workflow that would benefit from understanding the structural capabilities of sculpt (workspaces; how code flows between them).
How do I install Sculpt CLI in Claude Code?
Run `npx skills add imbue-ai/sculptor --skill sculpt-cli -a claude-code`. Or copy the skill folder (sculptor/sculptor-plugin/skills/sculpt-cli in imbue-ai/sculptor) into .claude/skills/sculpt-cli in your project. Claude Code loads it when a task matches its description.
How do I install Sculpt CLI in Codex?
Run `npx skills add imbue-ai/sculptor --skill sculpt-cli -a codex`. Or copy the skill folder (sculptor/sculptor-plugin/skills/sculpt-cli in imbue-ai/sculptor) into .agents/skills/sculpt-cli in your project. Codex loads it when a task matches its description.
Can I use Sculpt CLI 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 imbue-ai/sculptor --skill sculpt-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sculpt-cli, .gemini/skills/sculpt-cli, .github/skills/sculpt-cli and .opencode/skills/sculpt-cli in your project.
What does Sculpt CLI need to run?
Going by SKILL.md and its folder, Sculpt CLI needs the command-line tools its instructions call (jq and git).
Does Sculpt CLI access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Sculpt CLI 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. Review the folder before installing.
What licence does Sculpt CLI use?
Sculpt CLI 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 Sculpt CLI use?
About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Sculpt CLI?
Skills that share tags, products or a category with Sculpt CLI: SEO Programmatic (sickn33/agentic-awesome-skills, 47k stars), Remotion Interactivity (remotion-dev/remotion, 63k stars), Firecrawl Interact Integration (firecrawl/firecrawl, 190k stars) and Interaction To Next Paint (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sculpt CLI?
imbue-ai (a GitHub organization) maintains it in imbue-ai/sculptor, which has 237 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 8, 2026.
Source: imbue-ai/sculptor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.