Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Systematic audit and review by Referee 2. Two modes — "deck" reviews slide presentations for rhetoric, visual quality, and compile cleanliness; "code" performs cross-language replication and econometric audit of empirical pipelines. Use when reviewing slides, auditing code, or verifying replication.
Checks whether registered notebooks have current, stale, or missing outputs. Use before rendering or to verify freshness.
Generates robustness check code and formats results as a combined table. Use for sensitivity analysis.
Generates backend API integration tests for PwnDoc using Jest and supertest. Tests run against an ephemeral MongoDB instance via ./pwndoc-cli test --backend.
Generates Playwright E2E specs for PwnDoc. Tests run against the full stack (frontend + backend + MongoDB) with pre-authenticated browser sessions. Run with ./pwndoc-cli test --frontend-e2e.
Generates frontend unit tests for PwnDoc using Vitest and Vue Test Utils. Handles services (axios mock), components (mount with Quasar), pages (full setup), and Pinia stores. Run with ./pwndoc-cli test --frontend-unit.
Test orchestrator for PwnDoc. Analyzes a feature or the full project to determine test gaps across backend (Jest), frontend unit (Vitest), and frontend E2E (Playwright), then delegates to /test-backend, /test-frontend-unit, and /test-frontend-e2e skills.
This skill should be used when the user asks to "create an eval", "write an eval test", "add a new eval", "create a test case", "write a test for Holmes", or discusses LLM evaluation tests, eval fixtures, or test_case.yaml files for the HolmesGPT project.
Guide for investigating slow PostgreSQL queries
Python Application Memory Troubleshooting