Run Nx Generator
nrwl/nx
Run Nx generators with prioritization for workspace-plugin generators.
Discover and create a new application from a scaffold-mcp boilerplate.
Install Create Project
$ npx skills add AgiFlow/aicode-toolkit --skill create-project -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AgiFlow/aicode-toolkit create-project --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/AgiFlow/aicode-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/aicode-bootstrap/skills/create-project .claude/skills/create-project && 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 "create-project" agent skill from https://github.com/AgiFlow/aicode-toolkit/tree/main/plugins/aicode-bootstrap/skills/create-project into .claude/skills/create-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-project", 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/AgiFlow/aicode-toolkit/tree/main/plugins/aicode-bootstrap/skills/create-projectType 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 AgiFlow/aicode-toolkit --skill create-project -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AgiFlow/aicode-toolkit create-project --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgiFlow/aicode-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/aicode-bootstrap/skills/create-project .agents/skills/create-project && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "create-project" agent skill from https://github.com/AgiFlow/aicode-toolkit/tree/main/plugins/aicode-bootstrap/skills/create-project into .agents/skills/create-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-project", 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 AgiFlow/aicode-toolkit --skill create-project -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AgiFlow/aicode-toolkit create-project --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgiFlow/aicode-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/aicode-bootstrap/skills/create-project .cursor/skills/create-project && 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 "create-project" agent skill from https://github.com/AgiFlow/aicode-toolkit/tree/main/plugins/aicode-bootstrap/skills/create-project into .cursor/skills/create-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-project", 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/AgiFlow/aicode-toolkit.git --path plugins/aicode-bootstrap/skills/create-project--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 AgiFlow/aicode-toolkit --skill create-project -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AgiFlow/aicode-toolkit create-project --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgiFlow/aicode-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/aicode-bootstrap/skills/create-project .gemini/skills/create-project && 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 "create-project" agent skill from https://github.com/AgiFlow/aicode-toolkit/tree/main/plugins/aicode-bootstrap/skills/create-project into .gemini/skills/create-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-project", 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 AgiFlow/aicode-toolkit create-projectInstalls 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 AgiFlow/aicode-toolkit --skill create-project -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AgiFlow/aicode-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/aicode-bootstrap/skills/create-project .github/skills/create-project && 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 "create-project" agent skill from https://github.com/AgiFlow/aicode-toolkit/tree/main/plugins/aicode-bootstrap/skills/create-project into .github/skills/create-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-project", 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 AgiFlow/aicode-toolkit --skill create-project -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AgiFlow/aicode-toolkit create-project --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AgiFlow/aicode-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/aicode-bootstrap/skills/create-project .opencode/skills/create-project && 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 "create-project" agent skill from https://github.com/AgiFlow/aicode-toolkit/tree/main/plugins/aicode-bootstrap/skills/create-project into .opencode/skills/create-project/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-project", 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
create-project- GitHub stars
- 161
- Token cost
- ~255 tokens
- SKILL.md length
- 113 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Discover and create a new application from a scaffold-mcp boilerplate.
- Works in 4 steps: Confirm the consumer workspace has… → Call list-boilerplates and read the… → Confirm the output directory, template,… → …
- Requests to start a new project
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Adding a feature to an existing project
What it does
Create Project is an agent skill from AgiFlow/aicode-toolkit. Discover and create a new application from a scaffold-mcp boilerplate. Trigger for requests to start a new project. Do not trigger when adding a feature to an existing project.
Its SKILL.md is about 260 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Project scaffolding. It works with Model Context Protocol. The repository describes itself as: Toolkit for Coding Agents to work reliably with repo of any size. The licence is AGPL-3.0.
When your agent uses it
- Requests to start a new project
- Adding a feature to an existing project
Example prompts
- “/create-project”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Confirm the consumer workspace has templates and a configured toolkit; if not, follow initialize-workspace before activating scaffold MCP…
- Call list-boilerplates and read the returned variable schema. Never guess a template name or required variables.
- Confirm the output directory, template, values and existing-file overwrite risk with the user before calling use-boilerplate. Use the…
- Inspect generated files and project template metadata, run the generated project's relevant checks, and report results and remaining…
What it can do on your machine
Read from SKILL.md and the folder at commit d8debed. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Create Project loads about 255 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 113 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 AgiFlow/aicode-toolkit at commit d8debed, republished under its AGPL-3.0 licence (© AgiFlow). 113 words, ~255 tokens.
Download SKILL.mdSave it as
.claude/skills/create-project/SKILL.md (or your agent's skills folder).- name
- create-project
- description
- Discover and create a new application from a scaffold-mcp boilerplate. Trigger for requests to start a new project. Do not trigger when adding a feature to an existing project.
Create a project from a boilerplate
- Confirm the consumer workspace has templates and a configured toolkit; if not, follow
initialize-workspacebefore activating scaffold MCP. Monolith mode may hide the boilerplate tools. - Call
list-boilerplatesand read the returned variable schema. Never guess a template name or required variables. - Confirm the output directory, template, values and existing-file overwrite risk with the user before calling
use-boilerplate. Use the tool's discovered input schema and the consumer workspace as the working directory. - Inspect generated files and project template metadata, run the generated project's relevant checks, and report results and remaining setup. Never report a successful project creation from a failed or unavailable tool call.
© AgiFlow, AGPL-3.0. 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 plugins/aicode-bootstrap/skills/create-project of AgiFlow/aicode-toolkit.
Open the folder on GitHubat commit d8debed
Compare with similar skills
Create Project 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 |
|---|---|---|---|---|---|---|
| Create Project this skillAgiFlow/aicode-toolkit | 161 | — | ~255 | Automated safety check: Pass | AGPL-3.0 | |
| Run Nx Generatornrwl/nx | 29k | 2 repos | ~592 | Automated safety check: Notes | MIT | |
| Tsed CLItsedio/tsed | 3.1k | — | ~2.7k | Automated safety check: Pass | MIT | |
| Trellis Spec Bootstarpanjiemo/SunnyBeach | 178 | 7 repos | ~740 | Automated safety check: Pass | Apache-2.0 | |
| Better FullstackMarve10s/Better-Fullstack | 752 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Compare Harnessesruvnet/metaharness | 690 | — | ~1k | Automated safety check: Pass | MIT |
Similar skills
Tsed CLI
tsedio/tsed
Scaffolds Ts.ED v8 projects and generates files with the Ts.ED CLI v7, through its MCP server (tools set-workspace, init-project, list-templates, get-template, generate-file) or the tsed binary…
Trellis Spec Bootstarp
anjiemo/SunnyBeach
Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow.
Better Fullstack
Marve10s/Better-Fullstack
Scaffold, plan, or extend Better Fullstack projects with the generator, CLI, or MCP server.
Compare Harnesses
ruvnet/metaharness
Diff two scaffolded harnesses (ADR-031). An agent skill from ruvnet/metaharness.
Diag Harness
ruvnet/metaharness
Kernel-version skew check (ADR-027). An agent skill from ruvnet/metaharness.
More from AgiFlow/aicode-toolkit
All 9 skills in this repoPlaywriter
AgiFlow/aicode-toolkit
Control the user own Chrome browser via Playwriter extension with Playwright code snippets in a stateful local js sandbox via playwriter cli.
Author Templates
AgiFlow/aicode-toolkit
Create or update reusable toolkit boilerplate templates and feature scaffolds.
Develop Feature
AgiFlow/aicode-toolkit
Add or edit a feature in a toolkit-configured project using scaffold methods and file-specific design patterns.
Discover Design System
AgiFlow/aicode-toolkit
Discover existing project themes, supported CSS classes and reusable UI components.
Initialize Workspace
AgiFlow/aicode-toolkit
Set up toolkit templates and project metadata in a consumer workspace.
Manage Patterns And Rules
AgiFlow/aicode-toolkit
Author project design patterns and coding rules with architect-mcp admin tools.
Related
Works with
Categories
Questions about Create Project
What does Create Project do?
Discover and create a new application from a scaffold-mcp boilerplate. Create Project is an agent skill from AgiFlow/aicode-toolkit. Discover and create a new application from a scaffold-mcp boilerplate.
When should I use Create Project?
Create Project fits situations like: requests to start a new project; adding a feature to an existing project.
How do I install Create Project in Claude Code?
Run `npx skills add AgiFlow/aicode-toolkit --skill create-project -a claude-code`. Or copy the skill folder (plugins/aicode-bootstrap/skills/create-project in AgiFlow/aicode-toolkit) into .claude/skills/create-project in your project. Claude Code loads it when a task matches its description.
How do I install Create Project in Codex?
Run `npx skills add AgiFlow/aicode-toolkit --skill create-project -a codex`. Or copy the skill folder (plugins/aicode-bootstrap/skills/create-project in AgiFlow/aicode-toolkit) into .agents/skills/create-project in your project. Codex loads it when a task matches its description.
Can I use Create Project 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 AgiFlow/aicode-toolkit --skill create-project -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-project, .gemini/skills/create-project, .github/skills/create-project and .opencode/skills/create-project in your project.
What does Create Project need to run?
SKILL.md names no scripts, command-line tools or credentials: Create Project is instructions for the agent only.
Does Create Project 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 Create Project 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 Create Project use?
Create Project is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Create Project use?
About 255 tokens (SKILL.md is roughly 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 Create Project?
Skills that share tags, products or a category with Create Project: Run Nx Generator (nrwl/nx, 29k stars), Tsed CLI (tsedio/tsed, 3.1k stars), Trellis Spec Bootstarp (anjiemo/SunnyBeach, 178 stars) and Better Fullstack (Marve10s/Better-Fullstack, 752 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Create Project?
AgiFlow (a GitHub organization) maintains it in AgiFlow/aicode-toolkit, which has 161 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 5, 2026.
Source: AgiFlow/aicode-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.