AI Agent Skills

Role 05 of the Phoenix Security spec pipeline. Red-teams normative requirements for Phoenix-specific failure modes: multi-tenant isolation gaps, vague integration surfac…

Role 07 of the Phoenix Security spec pipeline. Turns Phoenix Security requirements into precise implementable contracts: REST API endpoints with Phoenix auth patterns, t…

Role 08 of the Phoenix Security spec pipeline. Maps every MUST/MUST NOT to a concrete proof method using Phoenix's proof type hierarchy: unit-test, integration-test, con…

Provides CI/CD pipeline configuration using GitHub Actions for Golang projects. Covers testing, linting, SAST, security scanning, code coverage, Dependabot, Renovate, Go…

Enforce traceability from natural-language intent to machine predicates, final observables, evidence, and owner-readable acceptance. Use when conducting any audit, revie…

Repurpose existing content into a native Instagram post. Take a LinkedIn, blog, YouTube script, or X tweet or thread and rebuild it for Instagram: a long piece becomes a…

Guide for security-related Agent Skills including penetration testing, code auditing, threat hunting, and forensics skills.

WooCommerce extension code review for HPOS compatibility, payment gateway security, cart optimization, and template overrides. Use when reviewing WooCommerce extension c…

深入诊断 HotPlex Gateway、Worker、Session、日志或反馈链异常。普通 status/doctor/security/config 只读检查属于 hotplex-cli；安装、更新、重启、配置写入和 Admin 变更属于 hotplex-operator。

A Metabase AI-governance coach, covering the *controls and rollout* side of AI: who may use Metabot, what it can see, what it costs, where the model runs, and the audit…

A Metabase AI-readiness coach, covering the *data groundwork* that makes AI answers trustworthy: modeling with Transforms, table and field metadata, the Glossary, saved…

Implement a GitHub issue end-to-end when Vigilante dispatches work for a Ruby repository with Bundler, test, lint, and security guidance.

Decide what the system should become before /spec commits an implementation plan. Runs inline in the active coding-agent session, grounds every claim in current reposito…

Weighs each attack path's effort against its likely impact, pursuing the highest-value surfaces first to find the most important weakness with the least wasted effort it…

Documents the current state of an active pentest engagement so the next agent session can continue without losing context, covering findings, coverage, next steps, and o…

Audit source code for vulnerabilities and dangerous API patterns