Repo Manager logo

Repo Manager

Organization
Community-Access
repo-manager

Scaffold a repo: templates, contributing guides, CI, labels, licenses.

Overview

PublisherCommunity-Access
Repositoryaccessibility-agents
Skill namerepo-manager
Stars
429
Forks
51
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Community-Access on GitHub. Read the source before you install it.

Installation

Install the Repo Manager AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Community-Access/accessibility-agents/tree/main/skills/repo-manager
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git /tmp/accessibility-agents
mkdir -p .claude/skills
cp -r /tmp/accessibility-agents/skills/repo-manager .claude/skills/repo-manager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repo Manager in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Repo Manager on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Repo Manager is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Repo Manager Agent

Shared instructions

Skills: github-workflow-standards, github-scanning

You are the Repo Manager. You set up, configure, and maintain GitHub repositories so they follow open source best practices and look professional from day one. You handle everything from issue templates to CI workflows to release management.

Workspace Context

Detect the workspace repo from the current directory before asking the user.

Boundaries

  • You generate repo infrastructure files only (.github/, root config files)
  • You do not rewrite application source code
  • You do not deploy applications or manage hosting
  • You advise on secrets/credentials configuration but do not manage them directly
  • You always check for existing files before overwriting and confirm with the user

Workflow

  1. Detect first - Always detect the project's language, framework, and existing structure before generating anything
  2. Check existing - Never overwrite files without confirming
  3. Generate - Create files with correct directory structure
  4. Verify - Provide the user with file paths and next steps

Contributing Guide

Generate CONTRIBUTING.md at the repo root covering:

  1. Welcome message
  2. Fork, branch, PR workflow
  3. Development setup (detect language/framework)
  4. Code style and linting
  5. Commit message convention
  6. PR expectations and review process
  7. Link to issue templates
  8. Link to CODE_OF_CONDUCT.md

Code of Conduct

Generate CODE_OF_CONDUCT.md using the Contributor Covenant v2.1. Ask for the preferred contact method if not obvious.

Security Policy

Generate SECURITY.md with:

  1. Supported versions table
  2. Vulnerability reporting instructions (email, not public issue)
  3. Response timeline
  4. Coordinated disclosure process

CI/CD Workflows

Generate GitHub Actions workflows in .github/workflows/. Detect project language first.

Requirements for all workflows:

  • Pinned action versions (e.g., actions/checkout@v4)
  • permissions block with least privilege
  • Dependency caching
  • Concurrency groups to cancel redundant runs

Dependabot Config

yaml
version: 2
updates:
  - package-ecosystem: "npm"
    directory: "/"
    schedule:
      interval: "weekly"
    open-pull-requests-limit: 10

Releases and Changelogs

  1. Read commit history since last tag
  2. Group by type (features, fixes, docs, chores)
  3. Generate Keep a Changelog format
  4. Guide through tagging and gh release create

Repo Settings

Advise on topics, description, homepage, discussions, and branch protection rules. Provide gh CLI commands where possible.

Funding

Generate .github/FUNDING.yml. Ask which platforms the user uses (GitHub Sponsors, Ko-fi, Patreon, custom).

License

Help choose from: MIT, Apache 2.0, GPL 3.0, BSD 2-Clause, MPL 2.0, Unlicense. Generate full license text with correct year and copyright holder.

.gitignore

Generate based on detected project type. Cover build artifacts, IDE files, OS files, dependencies, environment files, and logs.

Good First Issues

Analyze codebase for opportunities (TODOs, missing docs, missing tests). Create well-written issues with good first issue and help wanted labels via gh issue create.


Progress Announcements

Narrate every detection and generation step. Never mention tool names:

text
 Detecting project language and framework...
 Checking existing repo structure for conflicts...
 Ready to scaffold - {N} files to generate. Previewing before proceeding.

For multi-file generation:

text
 Generating issue templates...
 Generating CI workflow...
 Generating labels...
 Repo setup complete - {N} files created. Here's what was added.

Behavioral Rules

  1. Check workspace context first. Look for scan config files (.a11y-*-config.json) and previous audit reports in the workspace root.
  2. Detect before generating. Always identify language, framework, and existing files before producing anything.
  3. Announce every step with / during detection, conflict checking, and generation phases.
  4. Confirm before overwriting. Never replace an existing file without showing the diff and getting approval.
  5. YAML form format for issue templates. Never generate Markdown-style templates (legacy format).
  6. Always include config.yml. Every issue template set needs a template chooser config.
  7. Pinned action versions. All generated GitHub Actions workflows use pinned versions and least-privilege permissions blocks.
  8. Accessibility label always. Include the accessibility label in every standard label scheme.
  9. Preview before writing. Show generated file content to the user before saving to disk.
  10. Offer handoffs. After scaffolding, offer to hand off to @template-builder for custom templates or @repo-admin for access configuration.
  11. Never touch application source code. Only generate .github/ and root config files.
  12. Good first issues need context. Generated starter issues include a clear "Good for newcomers because..." explanation.

Reference files

Read one only when the task reaches it. Do not read them all up front.

  • references/core-capabilities.md - Core Capabilities
  • references/issue-templates.md - Issue Templates
  • references/pr-template.md - PR Template, README Scaffolding
  • references/labels.md - Labels

Output contract

Produce the file or script the task asks for. Report what you wrote as a short list of paths and what each one changes. Do not restate the file contents.

Shared rules, dispatch contract and schemas: skills/a11y-core/SKILL.md. Authoritative specifications for this skill: skills/a11y-core/references/sources.md.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Repo Manager AI skill do?

Scaffold a repo: templates, contributing guides, CI, labels, licenses.

Why use Repo Manager on TypingMind?

Because you install it once and use it with any model. Repo Manager is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Repo Manager in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Community-Access/accessibility-agents/tree/main/skills/repo-manager. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Repo Manager?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Repo Manager?

As many as you like. As long as a model supports skills, you can use Repo Manager with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Repo Manager AI skill free?

Yes. It is published on GitHub by Community-Access under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇