Github Actions

Organization

wendylabsinc

github-actions

Expert guidance on writing GitHub Actions workflows. Use when: (1) writing or editing any file under .github/workflows/, (2) choosing between an existing action and a shell script in CI, (3) picking action versions, (4) configuring workflow permissions or cloud authentication from CI, (5) reviewing a workflow in a PR.

Overview

Publisher	wendylabsinc
Repository	`claude-skills`
Skill name	`github-actions`
Stars	62
Forks	5
Bundled files	Instructions only
Links	Skill source Repository

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 wendylabsinc on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/wendylabsinc/claude-skills/tree/main/github-actions
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.

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/wendylabsinc/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/github-actions .claude/skills/github-actions

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github Actions 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 Github Actions 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 Github Actions 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.

GitHub Actions

Applies to every workflow — deploys, tests, releases, anything under .github/workflows/.

Rule 1: Prefer established actions over hand-rolled scripts

If a mature, maintained action covers the use case, use it. Hand-roll only when no action covers the case — and say so in the PR. Checking out code, docker login/build/push, cloud auth, uploading artifacts, releases: all covered by first-party or vendor actions (actions/*, docker/*, google-github-actions/*, pulumi/*).

Maturity check for third-party actions: maintained (recent releases), widely used, ideally from the vendor of the tool. Obscure single-maintainer actions holding credentials are worse than a script.

Rule 2: Verify versions at authoring time — never from memory

Your memory of "the current major" is stale. Proof, from a real baseline test (2026-07): a model confidently pinned actions/checkout@v4 and google-github-actions/auth@v2 as "current majors" — the actual latest were v7 and v3. Every version you remember is a version to verify.

The check takes seconds per action:

bash
gh api repos/actions/checkout/releases/latest --jq .tag_name

(or the releases page / marketplace). Do this for every action in the workflow you're writing, at the moment you're writing it. Writing a version without having run the check this session is the violation — "it was current last month" doesn't count.

Pin by major tag (@v7) normally; pin by commit SHA when supply-chain hygiene demands it (workflows with credentials touching prod).

Rule 3: Least privilege

Explicit permissions: block on every job: start from contents: read, add only what's needed (e.g. id-token: write for OIDC).
Cloud auth via OIDC federation only — no long-lived cloud secrets in GitHub. For GCP specifically, the wendy-gcp-deployment skill (references/github-oidc.md) is the authority; credentials_json / SA keys are forbidden, including as a fallback or stopgap.
Secrets that must exist in GitHub (e.g. a token for a SaaS with no OIDC) get environment-level scoping, not repo-wide, when environments are in play.

Quick checklist for any new workflow

Every step that could be an established action is one
Every action version verified this session (gh api .../releases/latest)
permissions: block present and minimal
Cloud auth is OIDC; no credentials_json, no key JSON in secrets
concurrency: group on deploy workflows (one deploy per ref at a time)
Deploy trigger split: default branch → dev, semver tags (v*) → prod

Rationalizations that don't fly

Excuse	Reality
"v4 is what I've always used"	That's the definition of answering from memory. Run the check.
"The major version barely matters"	Old majors lose runner compatibility and security fixes; some are deprecated outright.
"I'll leave a TODO to bump versions"	The TODO ships. Verify now — it's one command per action.
"A curl in a run: block is simpler than learning the action"	The action handles auth, retries, and edge cases the curl doesn't. Simpler today, pager duty later.
"credentials_json just until WIF is set up"	Keys outlive intentions. WIF bootstrap takes minutes; do it first.

Frequently asked questions

What does the Github Actions AI skill do?

Why use Github Actions on TypingMind?

Because you install it once and use it with any model. Github Actions 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 Github Actions in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wendylabsinc/claude-skills/tree/main/github-actions. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Github Actions?

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 Github Actions?

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

Is the Github Actions AI skill free?

It is published on GitHub by wendylabsinc. Check the repository for licensing terms. 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

Pinecone

NousResearch

OrganizationPopular

Managed vector DB for production RAG and search.

Qdrant

Vector search engine for production RAG systems.

Tensorrt Llm

High-throughput LLM inference on NVIDIA GPUs.

Internal Comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

GitHub Actions

Rule 1: Prefer established actions over hand-rolled scripts

Rule 2: Verify versions at authoring time — never from memory

Rule 3: Least privilege

Quick checklist for any new workflow

Rationalizations that don't fly

Frequently asked questions

Related AI Skills

Set up your own AI workspace now