Agent skills for Cursor

Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last).

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY…

Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or…

REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting…

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.

Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running ralph loop.

Safety guardrails for destructive commands. (gstack)

Decision guide for delegating to caveman-style subagents.

Quick-reference card for all caveman modes, skills, and commands.

Allows you to view the user''s screen as well as several hours of history.

Formats Python code using the black formatter

Use when a configured codebase-memory-mcp server can assist with graph-backed code discovery, architecture orientation, symbol lookup…

Run, configure, and troubleshoot OpenAI Codex CLI in non-interactive headless environments.

MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude…

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review.

Build comparable-company valuation workbooks in Excel.

Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions.

Connect an administrator-enabled SaaS app for a user with a one-time OAuth consent link.

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.