Security & Testing Agent Skills for HTTP / API

Full performance audit cycle — dispatch the sibling performance-audit skill (parallel perf lanes + execution-cost map), cross-validate…

Design performance test cases and test data specifications for an entire system — from raw system documentation (BRD, FRD, use cases…

Conducts red team operations using the Covenant C2 framework for authorized

Organizes and sorts permission allowlists for AI agents, tools, and services hierarchically without altering rule definitions.

Persona Auditor audits AI-generated code from the perspective of real users, surfacing the errors you would only discover through costly…

Write Playwright E2E tests for the Phoenix AI observability platform.

Write, extend, and debug PXI Playwright E2E tests for Phoenix.

Spin up a live local Omnigent server + runner and exercise the native Pi TUI harness (pi-native) end-to-end — launch the real `pi` CLI via…

Review one research paper for nine LLM-security methodological pitfalls (data poisoning, label inaccuracy, data leakage, model collapse…

Use when adding or extending real mobile-device coverage to a Playwright suite — touch/tap specs, Pixel or iPhone device descriptors…

Create maintainable and reusable Page Object Models (POMs) for Playwright tests.

Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.

Use when hardening a PLDI paper's measurements against the SIGPLAN Empirical Evaluation Guidelines — warmup and steady-state discipline…

Reverse Engineering Skill

Demonstrate Poisoned Pipeline Execution (PPE / CICD-SEC-4) during an authorized assessment — injecting attacker-controlled build steps…

Enforce access via Policies and Gates; use authorize() and authorizeResource() to standardize controller protections

Audit the allow/deny/ask rules across the user, project and local settings scopes, then dedupe them and promote read-only rules up the…

End-to-end test the polly multi-agent coding orchestrator's critical user journeys (CUJs).

Convert Postman collections to automated tests with environment preservation

Pre-commit review: security scan, quality gates, auto-fix.

Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk.