Github Actions Generator logo

Github Actions Generator

Community
akin-ozer
github-actions-generator

Create, generate, or scaffold GitHub Actions workflows, action.yml, or .github/workflows CI/CD pipelines.

Overview

Publisherakin-ozer
Repositorycc-devops-skills
Skill namegithub-actions-generator
Stars
326
Forks
39
Bundled files
30
LicenseApache-2.0
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.

  • 30 bundled files

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

  • Open source

    Published by akin-ozer on GitHub. Read the source before you install it.

Installation

Install the Github Actions Generator 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/akin-ozer/cc-devops-skills/tree/main/devops-skills-plugin/skills/github-actions-generator
  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/akin-ozer/cc-devops-skills.git /tmp/cc-devops-skills
mkdir -p .claude/skills
cp -r /tmp/cc-devops-skills/devops-skills-plugin/skills/github-actions-generator .claude/skills/github-actions-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github Actions Generator 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 Generator 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 Generator 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 Generator

Generate production-ready GitHub Actions workflows and custom actions following current best practices, security standards, and naming conventions. All generated resources are automatically validated using the devops-skills:github-actions-validator skill.

Quick Reference

CapabilityWhen to UseReference
WorkflowsCI/CD, automation, testingreferences/best-practices.md
Composite ActionsReusable step combinationsreferences/custom-actions.md
Docker ActionsCustom environments/toolsreferences/custom-actions.md
JavaScript ActionsAPI interactions, complex logicreferences/custom-actions.md
Reusable WorkflowsShared patterns across reposreferences/advanced-triggers.md
Security ScanningDependency review, SBOMreferences/best-practices.md
Modern FeaturesSummaries, environmentsreferences/modern-features.md

Trigger Decision Tree

Route every request through this decision tree before reading references or generating files:

  1. If the user asks for .github/workflows/*.yml CI/CD automation, choose Workflow Generation.
  2. If the user asks for action.yml or a reusable step package, choose Custom Action Generation.
  3. If the user asks for workflow_call or shared pipelines across repositories, choose Reusable Workflow Generation.
  4. If the request includes security-only scanning (dependency review, SBOM, CodeQL), stay on Workflow Generation with the security pattern.
  5. If intent is ambiguous, ask one disambiguation question: "Do you want a workflow, a custom action, or a reusable workflow?"

Progressive Disclosure Route

Load only what is needed for the selected route, in this order:

RouteLoad First (required)Load Next (only if needed)Primary Template
Workflow Generationreferences/best-practices.mdreferences/common-actions.md, references/expressions-and-contexts.md, references/modern-features.mdassets/templates/workflow/basic_workflow.yml
Custom Action Generationreferences/custom-actions.mdreferences/best-practices.mdassets/templates/action/composite/action.yml, assets/templates/action/docker/, assets/templates/action/javascript/
Reusable Workflow Generationreferences/advanced-triggers.mdreferences/best-practices.md, references/common-actions.mdassets/templates/workflow/reusable_workflow.yml

If a required reference/template is unavailable, continue with the closest available reference and report the fallback explicitly in output.


Core Capabilities

1. Generate Workflows

Triggers: "Create a workflow for...", "Build a CI/CD pipeline..."

Process:

  1. Understand requirements (triggers, runners, dependencies)
  2. Define trust boundaries (internal branches vs fork PRs vs external triggers)
  3. Set default permissions to read-only, then elevate only per job when required
  4. Reference references/best-practices.md for patterns
  5. Reference references/common-actions.md for action versions
  6. Generate workflow with:
    • Semantic names, pinned actions (SHA), explicit permissions
    • Concurrency controls, caching, matrix strategies
    • Fork-safe PR handling (no secrets in untrusted contexts)
  7. Validate with devops-skills:github-actions-validator skill
  8. Fix issues and re-validate if needed

Minimal Example:

yaml
name: CI Pipeline

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]

permissions:
  contents: read

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
      - uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238 # v6.2.0
        with:
          node-version: '24'
          cache: 'npm'
      - run: npm ci
      - run: npm test

Untrusted PR Guardrail (required for secret-using jobs):

yaml
jobs:
  deploy:
    if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository

2. Generate Custom Actions

Triggers: "Create a composite action...", "Build a Docker action...", "Create a JavaScript action..."

Types:

  • Composite: Combine multiple steps → Fast startup
  • Docker: Custom environment/tools → Isolated
  • JavaScript: API access, complex logic → Fastest

Process:

  1. Use templates from assets/templates/action/
  2. Follow structure in references/custom-actions.md
  3. Include branding, inputs/outputs, documentation
  4. Validate with devops-skills:github-actions-validator skill

See references/custom-actions.md for:

  • Action metadata and branding
  • Directory structure patterns
  • Versioning and release workflows

3. Generate Reusable Workflows

Triggers: "Create a reusable workflow...", "Make this workflow callable..."

Key Elements:

  • workflow_call trigger with typed inputs
  • Explicit secrets (avoid secrets: inherit)
  • Explicit trusted-caller expectations (document org/repo boundaries)
  • Outputs mapped from job outputs
  • Minimal permissions
yaml
on:
  workflow_call:
    inputs:
      environment:
        required: true
        type: string
    secrets:
      deploy-token:
        required: false
    outputs:
      result:
        value: ${{ jobs.build.outputs.result }}

When secrets are required, pass only the exact secret names needed and prefer environment protection rules for deployment stages.

See references/advanced-triggers.md for complete patterns.

4. Generate Security Workflows

Triggers: "Add security scanning...", "Add dependency review...", "Generate SBOM..."

Components:

  • Dependency Review: actions/dependency-review-action@v4
  • SBOM Attestations: actions/attest-sbom@v2
  • CodeQL Analysis: github/codeql-action

Permission Model: Use a read-only workflow-level baseline, then elevate only in the security job that requires write scopes.

yaml
permissions:
  contents: read

jobs:
  security-scan:
    permissions:
      contents: read
      security-events: write  # For CodeQL
      id-token: write         # For attestations
      attestations: write     # For attestations

See references/best-practices.md section on security.

5. Modern Features

Triggers: "Add job summaries...", "Use environments...", "Run in container..."

See references/modern-features.md for:

  • Job summaries ($GITHUB_STEP_SUMMARY)
  • Deployment environments with approvals
  • Container jobs with services
  • Workflow annotations

6. Third-Party Action Documentation and Citation

When using third-party actions (any uses: entry not in the same repository):

  1. Search for documentation:

    "[owner/repo] [version] github action documentation"
  2. Or use Context7 MCP:

    • mcp__context7__resolve-library-id to find action
    • mcp__context7__query-docs for documentation
  3. Pin to SHA with version comment:

    yaml
    - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
  4. Cite source and version in the response:

    • Action source (repository URL)
    • Version source (release/tag/changelog URL)
    • Selected commit SHA and human-readable version
    • Access date for the source used

See references/common-actions.md for pre-verified action versions.


Validation Workflow

CRITICAL: Every generated resource MUST be validated.

  1. Generate workflow/action file
  2. Invoke devops-skills:github-actions-validator skill
  3. If errors: fix and re-validate
  4. If success: present with usage instructions

Skip validation only for:

  • Partial code snippets
  • Documentation examples
  • User explicitly requests skip

Fallback Behavior (Tooling and Environment Constraints)

If required tooling or network access is unavailable, use this deterministic fallback order:

  1. If devops-skills:github-actions-validator is unavailable, run local fallback checks:
    • actionlint (if installed)
    • yamllint (if installed)
    • manual YAML/schema review with a clear "not tool-validated" note
  2. If Context7 or internet access is unavailable:
    • use references/common-actions.md for known action versions
    • state that external version verification could not be completed
  3. If a template path is missing:
    • generate from the closest template pattern in assets/templates/
    • document which template was substituted

Fallback usage must always be reported in the final output.


Mandatory Standards

All generated resources must follow:

StandardImplementation
SecurityPin to SHA, minimal permissions, mask secrets
PerformanceCaching, concurrency, shallow checkout
NamingDescriptive names, lowercase-hyphen files
Error HandlingTimeouts, cleanup with if: always()

See references/best-practices.md for complete guidelines.


Resources

Reference Documents

DocumentContentWhen to Use
references/best-practices.mdSecurity, performance, patternsEvery workflow
references/common-actions.mdAction versions, inputs, outputsPublic action usage
references/expressions-and-contexts.md${{ }} syntax, contexts, functionsComplex conditionals
references/advanced-triggers.mdworkflow_run, dispatch, ChatOpsWorkflow orchestration
references/custom-actions.mdMetadata, structure, versioningCustom action creation
references/modern-features.mdSummaries, environments, containersEnhanced workflows

Templates

TemplateLocation
Basic Workflowassets/templates/workflow/basic_workflow.yml
Reusable Workflowassets/templates/workflow/reusable_workflow.yml
Composite Actionassets/templates/action/composite/action.yml
Docker Actionassets/templates/action/docker/
JavaScript Actionassets/templates/action/javascript/

Common Patterns

Matrix Testing

yaml
strategy:
  matrix:
    os: [ubuntu-latest, windows-latest]
    node: [18, 20, 22]
  fail-fast: false

Conditional Deployment

yaml
deploy:
  if: github.event_name == 'push' && github.ref == 'refs/heads/main'

Artifact Sharing

yaml
# Upload
- uses: actions/upload-artifact@5d5d22a31266ced268874388b861e4b58bb5c2f3 # v4.3.1
  with:
    name: build-${{ github.sha }}
    path: dist/

# Download (in dependent job)
- uses: actions/download-artifact@c850b930e6ba138125429b7e5c93fc707a7f8427 # v4.1.4
  with:
    name: build-${{ github.sha }}

Third-Party Action Citation Block

text
Third-party action citations:
- actions/checkout: https://github.com/actions/checkout (version: v6.0.2, sha: de0fac2e4500dabe0009e67214ff5f5447ce83dd, accessed: 2026-02-28)

Done Criteria

The task is complete only when all checks below pass:

  1. The request route was selected using the trigger decision tree.
  2. Only the minimum required references/templates were loaded first.
  3. Every third-party action is pinned to a commit SHA and has source/version citation.
  4. Validation was run, or a skip exception/fallback path was explicitly documented.
  5. Output includes assumptions, security-sensitive decisions (permissions/secrets), and generated file paths.

Workflow Summary

  1. Route the request using the trigger decision tree
  2. Load the minimum references/templates for that route
  3. Generate using mandatory security and naming standards
  4. Cite and pin third-party actions (source, version, SHA)
  5. Validate with devops-skills:github-actions-validator (or documented fallback)
  6. Fix and re-validate until clean
  7. Present validated output with citations, assumptions, and file paths

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 Github Actions Generator AI skill do?

Create, generate, or scaffold GitHub Actions workflows, action.yml, or .github/workflows CI/CD pipelines.

Why use Github Actions Generator on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/akin-ozer/cc-devops-skills/tree/main/devops-skills-plugin/skills/github-actions-generator. 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 Github Actions Generator?

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 Generator?

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

Is the Github Actions Generator AI skill free?

Yes. It is published on GitHub by akin-ozer under the Apache-2.0 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 👇