firefrost-gaming/antigravity-skills-reference

Files

Al-Garadi ef285b5c97 fix: sync upstream main with Windows validation and skill guidance cleanup (#457 )

* fix: stabilize validation and tests on Windows

* test: add Windows smoke coverage for skill activation

* refactor: make setup_web script CommonJS

* fix: repair aegisops-ai frontmatter

* docs: add when-to-use guidance to core skills

* docs: add when-to-use guidance to Apify skills

* docs: add when-to-use guidance to Google and Expo skills

* docs: add when-to-use guidance to Makepad skills

* docs: add when-to-use guidance to git workflow skills

* docs: add when-to-use guidance to fp-ts skills

* docs: add when-to-use guidance to Three.js skills

* docs: add when-to-use guidance to n8n skills

* docs: add when-to-use guidance to health analysis skills

* docs: add when-to-use guidance to writing and review skills

* meta: sync generated catalog metadata

* docs: add when-to-use guidance to Robius skills

* docs: add when-to-use guidance to review and workflow skills

* docs: add when-to-use guidance to science and data skills

* docs: add when-to-use guidance to tooling and automation skills

* docs: add when-to-use guidance to remaining skills

* fix: gate bundle helper execution in Windows activation

* chore: drop generated artifacts from contributor PR

* docs(maintenance): Record PR 457 sweep

Document the open issue triage, PR supersedence decision, local verification, and source-only cleanup that prepared PR #457 for re-running CI.

---------

Co-authored-by: sickn33 <sickn33@users.noreply.github.com>

2026-04-05 21:04:39 +02:00

4.9 KiB

Raw Blame History

name, description, risk, source, author, date_added

name	description	risk	source	author	date_added
aegisops-ai	Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.	safe	community	Champbreed	2026-03-24

/aegisops-ai — Autonomous Governance Orchestrator

AegisOps-AI is a professional-grade "Living Pipeline" that integrates advanced AI reasoning directly into the SDLC. It acts as an intelligent gatekeeper for systems-level security, cloud infrastructure costs, and Kubernetes compliance.

Goal

To automate high-stakes security and financial audits by:

Identifying logic-based vulnerabilities (UAF, Stale State) in Linux Kernel patches.
Detecting massive "Silent Disaster" cost drifts in Terraform plans.
Translating natural language security intent into hardened K8s manifests.

When to Use

Kernel Patch Review: Auditing raw C-based Git diffs for memory safety.
Pre-Apply IaC Audit: Analyzing terraform plan outputs to prevent bill spikes.
Cluster Hardening: Generating "Least Privilege" securityContexts for deployments.
CI/CD Quality Gating: Blocking non-compliant merges via GitHub Actions.

When Not to Use

Web App Logic: Do not use for standard web vulnerabilities (XSS, SQLi); use dedicated SAST scanners.
Non-C Memory Analysis: The patch analyzer is optimized for C-logic; avoid using it for high-level languages like Python or JS.
Direct Resource Mutation: This is an auditor, not a deployment tool. It does not execute terraform apply or kubectl apply.
Post-Mortem Analysis: For analyzing why a previous AI session failed, use /analyze-project instead.

🤖 Generative AI Integration

AegisOps-AI leverages the Google GenAI SDK to implement a "Reasoning Path" for autonomous security and financial audits:

Neural Patch Analysis: Performs semantic code reviews of Linux Kernel patches, moving beyond simple pattern matching to understand complex memory state logic.
Intelligent Cost Synthesis: Processes raw Terraform plan diffs through a financial reasoning model to detect high-risk resource escalations and "silent" fiscal drifts.
Natural Language Policy Mapping: Translates human security intent into syntactically correct, hardened Kubernetes securityContext configurations.

🧭 Core Modules

1. 🐧 Kernel Patch Reviewer (`patch_analyzer.py`)

Problem: Manual review of Linux Kernel memory safety is time-consuming and prone to human error.
Solution: Gemini 3 performs a "Deep Reasoning" audit on raw Git diffs to detect critical memory corruption vulnerabilities (UAF, Stale State) in seconds.
Key Output: analysis_results.json

2. 💰 FinOps & Cloud Auditor (`cost_auditor.py`)

Problem: Infrastructure-as-Code (IaC) changes can lead to accidental "Silent Disasters" and massive cloud bill spikes.
Solution: Analyzes terraform plan output to identify cost anomalies—such as accidental upgrades from t3.micro to high-performance GPU instances.
Key Output: infrastructure_audit_report.json

3. ☸️ K8s Policy Hardener (`k8s_policy_generator.py`)

Problem: Implementing "Least Privilege" security contexts in Kubernetes is complex and often neglected.
Solution: Translates natural language security requirements into production-ready, hardened YAML manifests (Read-only root FS, Non-root enforcement, etc.).
Key Output: hardened_deployment.yaml

🛠️ Setup & Environment

1. Clone the Repository

git clone https://github.com/Champbreed/AegisOps-AI.git
cd AegisOps-AI

2. Setup

python3 -m venv venv
source venv/bin/activate
pip install google-genai python-dotenv

3. API Configuration

Create a .env file in the root directory to securely store your credentials:

echo "GEMINI_API_KEY='your_api_key_here'" > .env

🏁 Operational Dashboard

To execute the full suite of agents in sequence and generate all security reports:

python3 main.py

Pattern: Over-Privileged Container

Indicators: allowPrivilegeEscalation: true or root user execution.
Investigation: Pass security intent (e.g., "non-root only") to the K8s Hardener module.

💡 Best Practices

Context is King: Provide at least 5 lines of context around Git diffs for more accurate neural reasoning.
Continuous Gating: Run the FinOps auditor before every infrastructure change, not after.
Manual Sign-off: Use AI findings as a high-fidelity signal, but maintain human-in-the-loop for kernel-level merges.

🔒 Security & Safety Notes

Key Management: Use CI/CD secrets for GEMINI_API_KEY in production.
Least Privilege: Test "Hardened" manifests in staging first to ensure no functional regressions.

4.9 KiB Raw Blame History