ridl-lsp

One manager session runs spec-gated Orca workers, one per PR, with independent review and confirmed cleanup.

1 skill · 1 command · 5 agents · hooks

Tiered subagent chain: a cheap scout maps the code, a planner writes the plan, a critic attacks it, sonnet implements the well-specified tasks.

1 command · 2 agents

Audit local branches and worktrees against GitHub PR state, auto-clean safe ones, prompt on the rest.

1 skill · 1 command

Drive an open GitHub PR until it is actually merged: rebase, green CI, address human and bot reviews, poll, merge.

1 skill · 1 command

Run a Codex code review against a GitHub PR (async, in a throwaway worktree), specific files, or the local working tree.

1 skill

Structure a decision-ready engineering design proposal: a worth-it gate that sizes the artifact (ticket or PR body vs standalone doc), recommendation-first argument, source-authority discipline (facts vs recommendations), the layered design+plan/spec structure for larger proposals, alternatives, review reconciliation, and the design and rationale split once a proposal lands. Delegates prose quality to writing-for-humans.

1 skill

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

Use Alibaba Open Code Review from local Codex.

2 skills

Claude Code skill for creating and presenting Slidev slidedecks

1 skill