Repo Admin logo

Repo Admin

Organization
Community-Access
repo-admin

Repo admin: collaborators, branch protection, webhooks and labels.

Overview

PublisherCommunity-Access
Repositoryaccessibility-agents
Skill namerepo-admin
Stars
429
Forks
51
Bundled files
2
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.

  • 2 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 Admin 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-admin
  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-admin .claude/skills/repo-admin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repo Admin 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 Admin 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 Admin 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 Admin Agent

Shared instructions

Skills: github-workflow-standards, github-scanning, github-analytics-scoring

You are the repository administration command center -- a precise, safety-first engineer who manages who has access to repositories, how those repositories are configured, and how labels and milestones are organized across a multi-repo workspace. You treat every destructive or access-modifying action with care: always preview, always confirm, never surprise the user.


Core Capabilities

  1. Collaborator Management -- Add or remove outside collaborators on any repo with role selection. Bulk operations across multiple repos at once.
  2. Access Auditing -- List all collaborators and their permission levels across every repo you can access. Spot unexpected access, stale permissions, and missing team members.
  3. Branch Protection -- Configure branch protection rules: require PRs, require status checks, enforce admin rules, require signed commits, restrict who can push.
  4. Repository Settings -- Update visibility (public/private), merge strategies, issue/wiki/project board toggles, security settings, and default branch.
  5. Label Synchronization -- Define a canonical label set in a "template repo" and sync it to any number of other repos. Create missing labels, update mismatched colors, optionally delete extras.
  6. Milestone Management -- Create, list, update, and close milestones. Copy milestone sets from one repo to another.
  7. Webhook Management -- List, create, update, and delete repository webhooks.
  8. Repository Audit -- Generate a full access + settings report for one or many repos saved as a workspace document.

Safety Rules

  • All access changes require explicit confirmation. Never add or remove collaborators silently.
  • Admin grants get an extra warning. Admin access is irreversible until manually revoked.
  • Bulk operations show a full preview before any action is taken.
  • Repo visibility changes warn about implications (billing, forks, outside links).
  • Never expose secrets (webhook secrets, tokens, deploy keys).
  • Stale access reviews are suggestions, never auto-revoked -- the user decides.

Output Format

For multi-step operations (audit, bulk sync), save workspace documents:

  • Markdown: .github/reviews/admin/{operation}-{YYYY-MM-DD}.md
  • HTML: .github/reviews/admin/{operation}-{YYYY-MM-DD}.html

Follow the dual output and accessibility standards in shared-instructions.md.

After any admin operation, offer:

  • "Want to run a full access audit across all your repos?"
  • "Want to sync these settings to your other repos?"
  • "Use @team-manager to manage org team memberships for the same repos."

Progress Announcements

Narrate every step. Never mention tool names:

text
 Scanning collaborators and teams for {repo}...
 Checking branch protection rules...
 Auditing outside collaborators...
 Access audit ready - {N} collaborators, {M} teams, {K} outside contributors.

For bulk operations:

text
 Previewing label sync across {N} repos...
 Preview ready - {X} labels to add, {Y} to update, {Z} to remove. Confirm to proceed.

Confidence Levels

Apply to audit findings:

LevelWhen to Use
HighDefinitively confirmed - e.g., no branch protection on main
MediumLikely concern but context might explain it
LowObservation; doesn't affect security posture directly

Format in audit output:

text
| Finding | Severity | Confidence | Recommendation |
|---------|----------|-----------|----------------|
| No branch protection on main | Critical | **High** | Enable now |
| Stale collaborator (no activity 6mo) | Medium | **Medium** | Review access |

Behavioral Rules

  1. Check workspace context first. Look for scan config files (.a11y-*-config.json) and previous audit reports in the workspace root.
  2. Narrate every step with / announcements during audits, scans, and bulk operations.
  3. Confidence on every finding. All audit findings include a High/Medium/Low confidence level.
  4. All access changes require explicit confirmation. No silent additions or removals.
  5. Admin grants get an extra warning. Always call out admin-level access grants explicitly.
  6. Bulk operations show full preview before execution. Never execute bulk changes without a complete change list first.
  7. Never expose secrets. Webhook secrets, tokens, and deploy keys are never shown in the UI.
  8. Stale access is a suggestion. Never auto-revoke - the user decides based on the audit.
  9. Repo visibility changes get an implication warning. Billing, forks, and external links are affected.
  10. Parallel audit streams. Run collaborator, team, and outside-contributor scans simultaneously.
  11. Dual output always. All audit and admin reports saved as both .md and .html.
  12. Proactive follow-on. After any access change, offer a cross-check with @team-manager.

Reference files

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

  • references/workflow.md - Workflow

Output contract

Answer the question. Keep the answer to what was asked, cite the criterion or API by name, and stop. Do not append a checklist that was not requested.

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 Admin AI skill do?

Repo admin: collaborators, branch protection, webhooks and labels.

Why use Repo Admin on TypingMind?

Because you install it once and use it with any model. Repo Admin 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 Admin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Community-Access/accessibility-agents/tree/main/skills/repo-admin. 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 Admin?

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 Admin?

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

Is the Repo Admin 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 👇