菜单
Use for evidence-based Zscaler architecture reviews involving capacity, scaling, sizing, topology, growth forecasts, structural risk, resilience, single points of failure, or design recommendations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Answer questions about the Zscaler portfolio — full operational depth (T1, with SDK / TF / OneAPI exposure) on ZIA, ZPA (including AppProtection inline WAF/IPS sub-component and Browser Access), ZCC (Client Connector), ZDX (Digital Experience — T1 borderline, observability layer per 2026-05-04 verification gate), ZIdentity (unified identity + OneAPI authentication + step-up auth), and Cloud & Branch Connector (ZTW/ZTC — VM-based traffic forwarding for cloud workloads and branch offices); programmable-but-shallow (T2) on ZBI (Zero Trust Browser / Cloud Browser Isolation) and ZWA (Workflow Automation — DLP incident lifecycle); plus extended awareness with reasoning docs (T3, portal-only / no SDK) on Deception (decoys/honeypots for post-perimeter detection), Risk360 (cyber risk quantification / Monte Carlo / CISO board reporting), the AI Security family (AI Guard runtime guardrails for LLM prompt-injection / jailbreak / sensitive-data / toxicity / refusal detection plus AI Red Teaming / AI Guardrails / four-pill
Use when setting up or repairing this repo's runtime-data mount (default _data, configurable via the root or a downstream-selected runtime config), including mounting a user-supplied data repository or local directory with local setup config, choosing setup-data-mount mode, verifying the public data contract, or configuring a private work mirror that intentionally tracks runtime data.
Use for read-only editorial, structural, hygiene, drift, reference-quality, diff, and release-readiness audits of this Zscaler skill, its reference corpus, code changes, or supplied tenant configuration when an evidence-backed audit register is required.
Use when expanding or correcting Zscaler reference content from vendor sources, including citation-backed documentation, SDK or provider divergence analysis, source mining, reference drift, and verification passes.
Use for journal-first Zscaler incident retrospectives and postmortems when an existing investigation journal or case directory is available and the task needs a warning ledger, evidence map, lessons, or proceed/stop decision.
Use for grounded ad-hoc Zscaler questions about product behavior, policy evaluation, matching semantics, APIs, terminology, coverage boundaries, or tenant observations that do not require a procedural investigation or review.
| name | zscaler-architect |
| description | Use for evidence-based Zscaler architecture reviews involving capacity, scaling, sizing, topology, growth forecasts, structural risk, resilience, single points of failure, or design recommendations. |
Load and follow ../../../agents/architect/workflow.md.
The canonical workflow is the source of truth. This skill is only a portable runtime entrypoint.
