Orchestrate audited pi-worker DAGs on cmux using exact-base code worktrees, central-only SKILL.state, phase-pinned models, fresh audit…
Governance playbook for joint marketing programs, MDF, and performance
Use when publishing CocoaPods libraries to CocoaPods Trunk.
Use when organizing complex CocoaPods libraries into subspecs.
Use when adding automated tests to CocoaPods libraries using test specs.
Build/fix features with test-first development, review, and doc sync.
Bence's code style, tech stack, and workflow conventions
Find and eliminate code duplication with DRY refactoring strategies
Agent skill for reviewer - invoke with $agent-reviewer
Multi-agent code review with confidence-based filtering
Code style conventions for Output SDK workflow projects.
Use when exploring, understanding, or answering questions about a codebase that has Repowise indexed (a .repowise/ directory in the…
Enforces a deterministic build_runner codegen discipline: run one pinned `dart run build_runner build --delete-conflicting-outputs` pass…
Use when checking a repository's .coderabbit.yaml (or .coderabbit.yml) to determine whether inheritance: true is set
Use when building features with Codex (OpenAI Codex CLI) in any codebase and the work should go through a disciplined build → review →…
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated…
Routes requests to OpenAI GPT-6 (Astra/Sol/Luna) through the official Codex plugin for Claude Code — second opinions, hard problems, code…
Use when starting nontrivial repo work where route choice, scope, assumptions, or completion evidence could drift; defaults to a…
Optimize Cohere API performance with caching, batching, model selection,
Use when running LLM inference on Colab GPUs.
Write cold email sequences with copy constraints, spintax, and deliverability rules.