Skip to content
Back to skills

Create Github Action

ASecurity

Scaffolds a deterministic GitHub Actions CI/CD workflow YAML. NOT for scaffolding interactive agentic workflows (use `create-agentic-workflow`) and NOT for local event-driven hooks (use `create-hook`).

  • 7 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 2, 2026
ai-agentspythonbashgitci/cdsecurity

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned October 3, 2026

npx -y skills add richfrem/agent-plugins-skills --skill create-github-action --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Create Github Action?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Create Github Action
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/richfrem-create-github-action-agent-plugins-skills/badge)](https://www.skillsdirectory.com/skills/richfrem-create-github-action-agent-plugins-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: create-github-action
plugin: agent-scaffolders
description: >
  Scaffolds a deterministic GitHub Actions CI/CD workflow YAML. NOT for scaffolding interactive agentic workflows (use `create-agentic-workflow`) and NOT for local event-driven hooks (use `create-hook`).
argument-hint: "[workflow-type: test|build|deploy|lint|release|security]"
allowed-tools: Bash, Read, Write
---

# Create GitHub Action (create-github-action)

Scaffolds deterministic GitHub Actions CI/CD workflow configurations (`.github/workflows/<name>.yml`) without runtime AI orchestration.

## Contents
- [Critical Constraints](#critical-constraints)
- [Quick start](#quick-start)
- [Workflow](#workflow)
- [Verification](#verification)
- [References](#references)

## Critical Constraints
- **Deterministic Scope**: Traditional CI/CD only (no runtime LLMs). For agentic or prompt-driven automation, use `create-agentic-workflow`. For local tool hooks, use `create-hook`.
- **Least-Privilege Permissions**: Explicitly specify minimal `permissions:` blocks (e.g. `contents: read`) at workflow or job level; never omit or use broad write tokens.
- **Action Pinning & Timeouts**: Pin third-party actions to verified major versions or SHAs. Set explicit `timeout-minutes` on all jobs.
- **Secret Sanitization**: Reference secrets exclusively via `${{ secrets.NAME }}`; never hardcode sensitive values or log secret outputs.

## Quick start

```bash
# Seed discovery for a specific workflow type (test, build, deploy, lint, release)
python3 plugins/agent-scaffolders/scripts/scaffold.py \
  --type workflow \
  --name ci-pipeline \
  --path .github/workflows/ci.yml
```

## Workflow

1. **Phase 1: Pipeline Discovery**: Identify workflow trigger events (`push`, `pull_request`, `workflow_dispatch`), target runner environments (`ubuntu-latest`), matrix strategies, and dependencies.
2. **Phase 2: Scaffolding Generation**: Construct `.github/workflows/<name>.yml` with explicit triggers, concurrency controls, least-privilege permissions, and step caching.
3. **Phase 3: Secrets & Environment Setup**: Document required repository secrets and environment variables without logging actual secrets.
4. **Phase 4: Schema Validation**: Validate the generated YAML syntax and step structure against GitHub Actions schema standards.

## Verification

```bash
# Check YAML syntax and schema formatting
python3 -c "import yaml; yaml.safe_load(open('.github/workflows/<name>.yml'))"

# Audit skill compliance
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/agent-scaffolders/skills/create-github-action --mode source
```

## References
- [fallback-tree.md](references/fallback-tree.md) - Procedural fallbacks for generation failures.
- [references/action-types.md](references/action-types.md) - Supported GitHub Action pipeline archetypes.
- [acceptance-criteria.md](references/acceptance-criteria.md) - Quality gates for CI/CD workflows.

Files in this skill

  • SKILL.md1.4 KB
  • acceptance-criteria.md457 B
  • evals/evals.json923 B
  • evals/results.tsv417 B
  • fallback-tree.md1.4 KB
  • references/acceptance-criteria.md42 B
  • references/action-types.md35 B
  • references/fallback-tree.md36 B
  • references/hitl-interaction-design.md46 B
  • references/pattern-decision-matrix.md46 B
  • references/patterns/action-forcing-output-with-deadline-attribution.md82 B
  • references/patterns/adversarial-objectivity-constraint.md69 B
  • references/patterns/anti-pattern-vaccination.md59 B
  • references/patterns/anti-symptom-triage.md54 B
  • references/patterns/artifact-embedded-execution-audit-trail.md74 B
  • references/patterns/artifact-generation-xss-compliance-gate.md74 B
  • references/patterns/artifact-lifecycle.md53 B
  • references/patterns/artifact-state-interrogative-routing.md71 B
  • references/patterns/asynchronous-benchmark-metric-capture.md72 B
  • references/patterns/audience-segmented-information-filtering.md75 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.