Push Skills logo

Push Skills

CommunityPopular
davidondrej
push-skills

Push skills and global AGENTS.md to the private repo and verify the public mirror. Use only when the user explicitly invokes /push-skills.

Overview

Publisherdavidondrej
Repositoryskills
Skill namepush-skills
Stars
4.2K
Forks
610
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by davidondrej on GitHub. Read the source before you install it.

Installation

Install the Push Skills 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/davidondrej/skills/tree/main/skills/skill-authoring/push-skills
  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/davidondrej/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/skill-authoring/push-skills .claude/skills/push-skills
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Push Skills 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 Push Skills 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 Push Skills 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.

Push Skills

Canonical repo: AGENT_REPO. Private remote: PRIVATE_REPO. Pushing main triggers the sanitized mirror at PUBLIC_MIRROR_REPO; only the configured automation pushes there.

Only commit or push when the user requests it. Editing this skill is not permission to publish it. For distributed skill edits, follow distribute-skill-to-all-agents before pushing.

Always include global instructions

The user's standing scope for an authorized /push-skills run includes saved changes to GLOBAL_INSTRUCTIONS_FILE, unless they explicitly exclude that file. Check it on every run, even when the latest message names a skill. Preserve the conversation's original publishing objective through skill edits, renames, and other follow-up requests.

After fetching, compare saved global/AGENTS.md with origin/main:global/AGENTS.md. Local dirt may already be published; Git status alone cannot tell. Transfer new edits while preserving upstream changes.

Verify saved global instructions are committed privately and substantive updates appear in public root AGENTS.md. Report this separately; successful skill publication does not complete an AGENTS.md request.

Choose the source file

  • GLOBAL_INSTRUCTIONS_FILE should link to AGENT_REPO/global/AGENTS.md. Save the editor buffer and verify the link. If it differs, inspect both files before choosing; do not replace the link or overwrite either file. Public destination: root AGENTS.md.
  • AGENT_REPO/AGENTS.md is a separate, private repo-instruction file and stays excluded.
  • Updating global instructions needs no copy, skill allowlisting, or policy version bump.
  • Skills live under skills/<skill-name>/. Use publish-skill for newly public skills; include policy changes in the same commit.

Prepare without disturbing other work

Run Git in AGENT_REPO or the temporary worktree below. Check staged and unstaged changes:

bash
git status --short
git diff --cached --stat
git diff HEAD -- global/AGENTS.md
git remote -v
git fetch origin main

For skills, substitute the intended paths. Confirm origin is private. Review outgoing commits as well as files: every commit ahead of origin/main will push.

  • Clean checkout: fast-forward main with git merge --ff-only origin/main.
  • Only intended edits pending: commit, then rebase those commits onto origin/main.
  • Unrelated edits, staged files, or local commits: use git worktree add --detach <temporary-path> origin/main. Preserve the original checkout and index. Transfer approved changes as a patch against their original base, using three-way application when needed; copy approved new files separately. Preserve newer upstream edits instead of overwriting with an old copy. Resolve conflicts from both versions; ask only when intent is ambiguous.

Do not stash, reset, unstage, or commit someone else's work.

Commit and push

Stage only intended paths. Plain git commit includes all staged files regardless of the preceding git add; use an explicit path list:

bash
git add -- global/AGENTS.md
git commit --only -m "Update global agent instructions" -- global/AGENTS.md

Adapt paths and message for skills. Review git show --stat HEAD and git diff origin/main..HEAD before pushing. If nothing needs committing, check whether the intended state is already pushed, then verify it.

bash
git push origin HEAD:main
source_sha=$(git rev-parse HEAD)

If main advanced, fetch, rebase the isolated intended commits, review, and retry. Never force-push. Verify the remote contains the commit instead of relying on push-output labels. Report when a temporary worktree kept the original checkout untouched.

Verify public publication

Find the workflow for the pushed commit; a private push alone does not prove publication:

bash
gh run list --repo PRIVATE_REPO --workflow MIRROR_WORKFLOW \
  --commit "$source_sha" --json databaseId,headSha,status,conclusion,url
gh run watch <run-id> --repo PRIVATE_REPO --exit-status

Wait for the matching run. If superseded, verify the newer source contains your change. The workflow may add an automated sync commit, so public Source: can name a descendant of your commit. For failure, cancellation without replacement, or a stall, inspect status/logs and report incomplete publication with the run link. Do not rerun indefinitely.

Read the published file and confirm the intended update:

bash
gh api repos/PUBLIC_MIRROR_REPO/contents/AGENTS.md \
  -H 'Accept: application/vnd.github.raw'

Find skill categories from the committed policy and published tree, then check skills/<category>/<skill-name>/SKILL.md. Private-only skills need only private push verification.

The mirror may rewrite or omit content; green CI and file existence do not prove correctness. For missing or unexpected content, inspect the matching mirror-report artifact and the mirror tooling documentation. Report exclusions/failures accurately. Never bypass the sanitizer or add manual approval gates. Finish with the private commit, workflow result, and published file link.

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 Push Skills AI skill do?

Push skills and global AGENTS.md to the private repo and verify the public mirror. Use only when the user explicitly invokes /push-skills.

Why use Push Skills on TypingMind?

Because you install it once and use it with any model. Push Skills 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 Push Skills in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davidondrej/skills/tree/main/skills/skill-authoring/push-skills. 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 Push Skills?

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 Push Skills?

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

Is the Push Skills AI skill free?

Yes. It is published on GitHub by davidondrej 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 👇