CtrlK
BlogDocsLog inGet started
Tessl Logo

gh-actions-validator

Automatically validates and enforces GitHub Actions best practices for Vertex AI and Google Cloud deployments. Expert in Workload Identity Federation (WIF), Vertex AI Agent Engine deployment pipelines, security validation, and CI/CD automation. Triggers: "create github actions", "deploy vertex ai", "setup wif", "validate github workflow", "gcp deployment pipeline"

80

1.78x
Quality

72%

Does it follow best practices?

Impact

100%

1.78x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./backups/skills-batch-20251204-000554/plugins/devops/jeremy-github-actions-gcp/skills/gh-actions-validator/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

Deploy AI Chatbot to Google Cloud

WIF authentication and OIDC permissions

Criteria
Without context
With context

No credentials_json

100%

100%

WIF provider param

100%

100%

WIF service_account param

100%

100%

id-token write permission

100%

100%

contents read permission

100%

100%

Correct auth action version

100%

100%

Path-based trigger

100%

100%

workflow_dispatch trigger

100%

100%

Deployment notes explain WIF

100%

100%

Notes reject JSON keys

100%

100%

100%

93%

Vertex AI Agent Configuration Validator

Vertex AI agent config validation

Criteria
Without context
With context

Allowed model names

0%

100%

Code exec TTL range

0%

100%

Sandbox type SECURE_ISOLATED

0%

100%

Timeout range

28%

100%

Memory max_memories threshold

0%

100%

Memory indexing enabled

0%

100%

Memory auto_cleanup enabled

0%

100%

Model Armor required

0%

100%

VPC config required

0%

100%

min_instances >= 1

0%

100%

max_instances >= 3

0%

100%

Clear error messages

0%

100%

Passing config validates

100%

100%

100%

39%

GCP Security Audit Pipeline

Security scanning and IAM validation workflow

Criteria
Without context
With context

TruffleHog secrets scan

0%

100%

Trivy vulnerability scan

100%

100%

SA key file detection

30%

100%

credentials_json grep check

0%

100%

IAM owner/editor check

100%

100%

PR and push trigger

100%

100%

No credentials_json in new workflow

100%

100%

Trivy SARIF output

0%

100%

Security policy documents checks

100%

100%

Fail-fast on violations

100%

100%

Repository
jeremylongshore/claude-code-plugins-plus-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.