agentleFS
Luis85Luis85/agentic-workflow/.claude/skills/github-project-setup/SKILL.md

github-project-setup

Skill0 starsChanged 6 months agoMITView on GitHub

Scaffold a new GitHub repo as a project workspace — labels, milestones, baseline issues for vision, PRD, UX, architecture, traceability, P3.express kickoff. Triggers "prepare new repo", "scaffold project setup", "GitHub project setup".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to turn a blank or early GitHub repository into a manageable product/project workspace.

    line 9
  2. Distinctive:

    If the repo already has issues, list them first and avoid duplicating obvious existing setup work.

    line 23
  3. Distinctive:

    Use P3 when the project needs explicit sponsor/PM roles, kickoff, follow-up registers, risks, go/no-go gates, or stakeholder communication.

    line 31
  4. Very specific:

    Use --no-p3 only for very small internal experiments where the user explicitly does not want governance.

    line 32
  5. Distinctive:

    Read back created issues from GitHub:

    line 46
  6. Very specific:

    Do not run --execute against the wrong repository.

    line 78
  7. Distinctive:

    Do not create duplicate planning issues if the target repo already has equivalent issues.

    line 79
  8. Distinctive:

    Do not claim GitHub Projects fields/views were configured by the script.

    line 80
  9. Distinctive:

    Keep the setup backlog focused on readiness and product setup.

    line 81

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GitHub Project Setup

Use this skill to turn a blank or early GitHub repository into a manageable product/project workspace.

It creates a repeatable backlog baseline, not implementation code. The default setup includes:

  • GitHub/repo environment readiness.
  • Product setup: PRODUCT_VISION.md, PRDs, use cases, UX/design brief, architecture input, traceability.
  • P3.express initiation through kickoff.
  • Optional plugin-shell preparation for plugin products.

Preconditions

  • Resolve the target repository as owner/name.
  • Confirm gh auth status works.
  • Confirm the user expects GitHub writes. Label/milestone/issue creation is shared state.
  • If the repo already has issues, list them first and avoid duplicating obvious existing setup work.

Procedure

  1. Classify the project profile:
    • generic-product: default for apps, libraries, SaaS, services, and internal tools.
    • obsidian-plugin: use for Obsidian plugin work or similar plugin-shell setup where isolated UI, marketplace readiness, and host bridge concerns matter.
  2. Decide whether P3.express initiation applies:
    • Use P3 when the project needs explicit sponsor/PM roles, kickoff, follow-up registers, risks, go/no-go gates, or stakeholder communication.
    • Use --no-p3 only for very small internal experiments where the user explicitly does not want governance.
  3. Dry-run the plan:

    npm run project:setup:github -- --project-name "<Project Name>" --profile <generic-product|obsidian-plugin> --dry-run
  4. Review the plan with the user when the target repo is not empty or when there is any risk of duplicate public issues.
  5. Execute only after the plan is suitable:

    npm run project:setup:github -- --repo <owner/name> --project-name "<Project Name>" --profile <generic-product|obsidian-plugin> --execute
  6. Read back created issues from GitHub:

    gh issue list --repo <owner/name> --state open --limit 100 --json number,title,milestone,labels,url
  7. Summarize the created milestone structure and the recommended first issue to work.

What The Tool Creates

The tool creates:

  • Labels for setup, product, PRD, use cases, UX, architecture, traceability, CI, release, docs, and pages.
  • Milestones:
    • v1 repo setup
    • v1 product setup
    • v1 plugin shell for obsidian-plugin
    • P3 project initiation unless --no-p3
  • Issues covering:
    • README/license/docs and GitHub workflow.
    • CI, release, dependency, and branch-protection readiness.
    • GitHub Pages product page.
    • PRODUCT_VISION.md.
    • v1 PRD.
    • use case catalog.
    • UX/design and architecture handoff briefs.
    • traceability index.
    • plugin shell architecture when applicable.
    • P3 A01-A10 initiation and focused communication when enabled.

Guardrails

  • Do not run --execute against the wrong repository.
  • Do not create duplicate planning issues if the target repo already has equivalent issues; update existing issues or create a smaller gap-filling set instead.
  • Do not claim GitHub Projects fields/views were configured by the script. The tool creates labels, milestones, and issues. GitHub Project boards/views should be configured manually or by a future extension.
  • Keep the setup backlog focused on readiness and product setup. Feature implementation issues come after the product baseline.

References

  • Tool: scripts/github-project-setup.ts
  • Project management methodology: docs/project-track.md
  • Existing local project track skill: .claude/skills/project-run/SKILL.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.