Design SASE and ZTNA access for private apps, SWG, and CASB. Use when replacing VPN, onboarding a connector, or reviewing Prisma / Zscaler / Netskope policy.
Scanned 9/5/2026
Install to Claude Code
Skills Directorynpx -y skills add gesh75/claude-skill-lint --skill sase-zero-trust --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Sase Zero Trust?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gesh75-sase-zero-trust)More formats (shields.io, HTML) on the badges page.
---
name: sase-zero-trust
description: Design SASE and ZTNA access for private apps, SWG, and CASB. Use when replacing VPN, onboarding a connector, or reviewing Prisma / Zscaler / Netskope policy.
argument-hint: "[app] [idp]"
allowed-tools: Read Grep
license: MIT
---
# SASE / Zero Trust
Do not use for branch SD-WAN underlay or classic remote-access IPsec. Not for NAC/802.1X (use campus-nac-dot1x).
## Procedure
1. Classify the app: public SaaS, private HTTP, or private TCP. Private TCP gets a connector, not a VPN pool.
2. Bind identity (IdP group + device posture) before network. No IP-only allow.
3. SWG: TLS decrypt with exceptions for health-care, banking, and pinned apps. Log to the SIEM.
4. Connector placement: two per site, inside the same security zone as the app, health-checked.
5. Verify with a user who is in-group and a user who is not. Confirm the deny is explicit.
```text
policy: payments-api
from: group=finance AND posture=compliant
to: app=payments.int.example
action: allow
inspect: tls
```
## Anti-patterns
- Never fall back to "any user on the corporate CIDR".
- Do not decrypt banking or healthcare destinations.
## Safety
Policy review is read-only. Connector install is a change-guarded write.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
