template-project-creator
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
Create a fresh state-0 repository from this PARK checkout with the Python project generator. Use only from an unconfigured PARK template checkout, not inside a generated project.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- agent-workboardSkill
- clear-writingSkill
- documentation-impactSkill
- github-state-auditSkill
- gitignore-auditSkill
- milestone-deliverySkill
- repository-checkSkill
- repository-delivery-gateSkill
- repository-orientationSkill
- resumable-worktree-runSkill
- security-reviewSkill
- session-usage-auditSkill
- agent-workboardSkill
- clear-writingSkill
- documentation-impactSkill
- github-state-auditSkill
- gitignore-auditSkill
- milestone-deliverySkill
- repository-checkSkill
- repository-delivery-gateSkill
- repository-orientationSkill
- resumable-worktree-runSkill
- security-reviewSkill
- session-usage-auditSkill
- template-project-creatorSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Create a new, configured PARK project by running the repository's Python generator.
- Distinctive: line 15
Before running the generator, obtain or infer only these values:
- Very specific: line 31
Run the generator from the PARK checkout with python3 and explicit arguments:
- Very specific: line 40
Add --github-owner, --slug, --copyright-holder, or --default-branch only when selected.
- Very specific: line 47
Run make check in the generated directory.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Template project creator
Create a new, configured PARK project by running the repository's Python generator. A state-0 project is the generated baseline: it has its selected identity and license rendered, but no product-specific implementation or history unless the user asks to initialize Git.
Required decisions
Before running the generator, obtain or infer only these values:
- destination: an absolute path that does not exist or is an empty directory;
- name and concise description;
- license:
mit,apache-2.0, ornone.
Accept an optional GitHub owner, project slug, copyright holder, and default
branch. Do not invent an owner or license. Default the branch to main only
when the user has not selected another branch.
Create the project
Confirm this checkout contains scripts/create_project.py and
.portable-agent-template; otherwise, explain that this is already a generated
project and cannot generate another project through this skill.
Run the generator from the PARK checkout with python3 and explicit arguments:
python3 scripts/create_project.py /absolute/path/to/project \
--name "Project Name" \
--description "What the project does" \
--license mitAdd --github-owner, --slug, --copyright-holder, or --default-branch
only when selected. Add --init-git only when the user requests a newly
initialized local Git repository. Never work around the generator's empty-target
check, merge into an existing project, or delete destination contents.
Verify and hand off
Run make check in the generated directory. Report the destination, chosen
configuration, whether Git was initialized, and the validation result. The new
project should have no .portable-agent-template, no generator-only assets, and
no product-specific code until its owner adds them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

