Release Aur logo

Release Aur

Community
Firstp1ck
release-aur

Use when creating, updating, reviewing, or publishing Arch User Repository (AUR) packages. Runs /release-aur plan first, reviews PKGBUILD/.SRCINFO/build/namcap evidence, and only recommends /release-aur publish after a GO decision.

Overview

PublisherFirstp1ck
Repositorypi-coding-agent-forge
Skill namerelease-aur
Stars
93
Forks
22
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Firstp1ck on GitHub. Read the source before you install it.

Installation

Install the Release Aur 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/Firstp1ck/pi-coding-agent-forge/tree/main/pi-extension-release-aur/skills/release-aur
  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/Firstp1ck/pi-coding-agent-forge.git /tmp/pi-coding-agent-forge
mkdir -p .claude/skills
cp -r /tmp/pi-coding-agent-forge/pi-extension-release-aur/skills/release-aur .claude/skills/release-aur
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Release Aur 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 Release Aur 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 Release Aur 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.

Release AUR

Use this skill for AUR package creation, updates, release readiness reviews, publishing decisions, and /release-aur-setup prerequisite workflows.

Mandatory workflow

  1. Start with /release-aur plan <target> unless the user explicitly asks only to create a repo.
  2. Review the generated preflight output and inspect files when needed:
    • PKGBUILD
    • .SRCINFO
    • git status --porcelain=v1
    • git diff -- PKGBUILD .SRCINFO
    • git diff --cached if anything is staged
  3. Confirm these gates before GO:
    • makepkg --printsrcinfo succeeds.
    • .SRCINFO is present or will be regenerated by publish mode.
    • makepkg --verifysource succeeds.
    • full makepkg build/check/package succeeds.
    • no namcap E: findings unless the user explicitly accepts a justified exception.
    • no build artifacts, secrets, or unrelated files are staged or likely to be auto-staged.
    • dependencies are direct and explicit, not merely transitive.
    • latest-release update check ran against the configured source (global/per-package/auto) or was explicitly skipped with justification.
    • pkgver matches upstream and pkgrel is reset to 1 when upstream pkgver is bumped.
    • checksum arrays were refreshed with updpkgsums after a version bump.
    • VCS packages are not committed for a mere upstream pkgver bump.
  4. Return GO only when publish is appropriate. Include the exact command:
    text
    /release-aur publish <target>
  5. Return NO-GO with exact fixes when any blocker remains.
  6. Never push manually with raw git push unless the user explicitly bypasses the package workflow. Prefer /release-aur publish because it regenerates .SRCINFO, stages conservatively, commits, and pushes to AUR master.

Setup flow

Use /release-aur-setup when the user needs AUR release workflow prerequisites prepared. The setup workflows are:

text
/release-aur-setup dir [path-to-aur-repos]
/release-aur-setup source [global <source>|package <pkgbase> <source>|clear <pkgbase>|status]
/release-aur-setup ssh

The extension should use native Pi UI to prompt for the directory where the user stores AUR package repos. Persist it in ~/.pi/agent/release-aur/config.json; bare /release-aur should use it to list repos and prompt where the release should run. If no directory is configured, current-directory discovery is the fallback.

For upstream release checks, the setup flow should use native Pi UI to configure a global release source and optional per-package overrides in the same config file. auto means detect GitHub from PKGBUILD; custom sources may be github:owner/repo, GitHub URLs, git:<clone-url>, or git clone URLs. Per-package overrides must win over the global source.

For SSH access, the extension should use native Pi UI, follow ArchWiki AUR authentication guidance, check ~/.ssh/config first for an existing Host aur.archlinux.org block, directly test that existing connection before creating keys or editing config, make /release-aur-setup status run local file/config checks, release source status, and the AUR SSH connection test, create/configure only under ~/.ssh after confirmation when setup is still needed, prefer a dedicated ~/.ssh/aur key, show/copy the public key for the user to add in AUR My Account, and test SSH auth only after the user confirms the public key was added. Do not claim remote AUR auth is complete until the SSH test succeeds.

Create flow

For a new or partially prepared AUR package repo:

text
/release-aur create <pkgbase>

create is convergent: it handles a missing/empty directory, an existing git repo, or an existing non-git directory containing PKGBUILD. It sets up the AUR remote, generates .SRCINFO when possible, then runs plan checks and queues review.

If PKGBUILD is missing, the extension must use Pi native UI to ask whether the user wants the agent to create it, copy it from a path, create a bundled Python/Rust/Go GitHub-source template via template selector, or add it later.

For a single command that continues to push after setup and checks, use only with explicit user intent:

text
/release-aur create <pkgbase> --push

This still requires interactive confirmation before the commit/push. Only recommend --push after a GO review or when the user explicitly accepts the risk.

Evidence standard

Cite observed local command output and local ArchWiki guidance when making release decisions. Relevant local ArchWiki sections include:

  • /usr/share/doc/arch-wiki/html/en/AUR_submission_guidelines.html — Authentication
  • /usr/share/doc/arch-wiki/html/en/AUR_submission_guidelines.html — Creating package repositories
  • /usr/share/doc/arch-wiki/html/en/AUR_submission_guidelines.html — Publishing new package content
  • /usr/share/doc/arch-wiki/html/en/.SRCINFO.html — .SRCINFO
  • /usr/share/doc/arch-wiki/html/en/Creating_packages.html — Testing the PKGBUILD and package
  • /usr/share/doc/arch-wiki/html/en/Creating_packages.html — Checking package sanity
  • /usr/share/doc/arch-wiki/html/en/Arch_package_guidelines.html — Reproducible builds
  • /usr/share/doc/arch-wiki/html/en/SSH_keys.html — Generating an SSH key pair
  • /usr/share/doc/arch-wiki/html/en/SSH_keys.html — Choosing the key location and passphrase

Decision format

markdown
## AUR Release Review — <target>

Verdict: GO / NO-GO
Confidence: NN/100

Checks:
- latest release update check: PASS/WARN/FAIL/SKIPPED
- makepkg --printsrcinfo: PASS/FAIL
- .SRCINFO sync: PASS/WARN/FAIL
- makepkg --verifysource: PASS/FAIL
- makepkg build/check/package: PASS/FAIL
- namcap: PASS/WARN/FAIL/SKIPPED
- git staging safety: PASS/FAIL
- versioning policy: PASS/FAIL

Decision:
- If GO: `/release-aur publish <target>`
- If NO-GO: blocking fixes in order

Frequently asked questions

What does the Release Aur AI skill do?

Use when creating, updating, reviewing, or publishing Arch User Repository (AUR) packages. Runs /release-aur plan first, reviews PKGBUILD/.SRCINFO/build/namcap evidence, and only recommends /release-aur publish after a GO decision.

Why use Release Aur on TypingMind?

Because you install it once and use it with any model. Release Aur 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 Release Aur in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Firstp1ck/pi-coding-agent-forge/tree/main/pi-extension-release-aur/skills/release-aur. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Release Aur?

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 Release Aur?

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

Is the Release Aur AI skill free?

Yes. It is published on GitHub by Firstp1ck 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 👇