Project Creator
CheckedGenerates basic project structures & files based on user prompts, streamlining initial setup and accelerating development workflows.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add itechmeat/llm-code --skill project-creator -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
itechmeat
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned itechmeat/llm-code at 7ae8a00524.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 7ae8a00524
- Manifest
- skills/project-creator/SKILL.md
- Scanned
- 12 files, 1,732 lines
About this skill
What it does
The Project Creator skill helps AI agents generate and maintain project documentation within a .project/ folder. It facilitates the creation of essential files like project overviews, technical specifications, architecture diagrams, and user stories, streamlining initial project setup and accelerating development workflows. The skill guides users through a structured process to create these documents based on templates and reference materials.
When to use it
- When starting a new software project and needing to establish foundational documentation.
- To generate or update the
.project/directory's contents, including overviews, specifications, architecture diagrams, and user stories. - During project planning phases when defining user stories is required.
Key capabilities
- Generates project documentation files within a
.project/folder. - Utilizes templates from an
assets/folder for creating documents like "about," "specs," "architecture," "context," and individual user stories. - Provides reference guides in the
references/folder to guide content creation with questions and criteria. - Follows a structured workflow: loads guides, assesses existing documents, creates/updates using templates, interviews users, drafts content, presents for feedback, iterates, and progresses through dependent documentation files (about -> specs -> architecture -> project-context -> stories).
Example prompts
- "Create the initial project structure with all default
.project/files." - "Generate a draft of the 'specs.md' document based on the available template and guide."
- "Help me plan out user stories for this project, starting with a master list in
stories/stories.md."
Tips & gotchas
- The skill follows a specific workflow; understanding this sequence (load guide -> assess existing -> create/update -> interview -> draft -> feedback -> iterate) is crucial for effective use.
- Documentation dependencies exist: the order of creation is suggested as about -> specs -> architecture -> project-context -> stories.