Discover Development skills, compare source repositories and read the instructions for each workflow.
Iteratively refine implementation plans using the "Convexity" pattern. Simulates a multi-round architectural critique to converge on a secure, robust specification. Use when you have a draft plan that needs dee...
Safe Beads workflow helper (warning-only). Use before bd sync/close/create to avoid JSONL conflicts. Ensures you are on a feature branch, up to date with origin/master, and stages Beads files cleanly with Featu...
Coordinator playbook for running multi‑repo, multi‑VM work in parallel without relying on humans copy/pasting long checklists.
Dispatch Beads tasks to Claude Code on remote VMs via SSH. Use when: "dispatch to hive", "run on VM", "assign to runner", "send to host".
Check and fix lockfile drift across Poetry (Python) and pnpm (Node.js) projects.
Safe recovery procedure for dirty/WIP repositories. This skill provides a standardized workflow for: - Snapshotting uncommitted work to a WIP branch
Dispatches work to Jules agents via the CLI. Automatically generates context-rich prompts from Beads issues and spawns async sessions. Use when user says "send to jules", "assign to jules", "dispatch task", or...
Beads issue tracking and workflow management with automatic git branch creation. MUST BE USED for Beads operations. Handles full epic→branch→work lifecycle, dependencies, and ready task queries. Use when creati...
Coding Agent Session Search (CASS) for semantic search over past agent sessions. Use when looking for how something was solved before, finding past solutions, or searching conversation history. Keywords: search...
**Tags:** #tools #cli #railway #github #env
Validate that the current VM has the right `agent-skills` installed for the repo you’re working in.
Run project verification checks using standard Makefile targets. Use when user says "verify pipeline", "check my work", "run tests", or "validate changes". Wraps `make verify-pipeline` (E2E), `make verify-analy...
Guide for installing and using MCP Agent Mail across heterogeneous agent tools/VMs.
Destructive Command Guard (DCG) safety hook for all AI coding agents. Rust-based PreToolUse hook that blocks dangerous git and filesystem commands. Use when agent attempts destructive operations, safety verific...
Validate Python toolchain alignment between mise, Poetry, and pyproject. Use when changing Python versions, editing pyproject.toml, or seeing Poetry/mise version solver errors. Invokes /toolchain-health to chec...
Beads Viewer (BV) integration for visual task management and smart task selection. Use for Kanban views, dependency graphs, and the robot-plan API for auto-selecting next tasks. Keywords: beads, viewer, kanban,...
Lightweight “news wire” implemented **via Agent Mail threads**, not a separate bespoke system.
Guide for creating companion ebooks for The Quantum Templ™ system. Use when creating sourcing guides, practical action guides, or companion materials for any of the eight Quantum Templ gates. The skill covers b...
Assists in writing ebooks 2-8 of The Quantum Templ™ System, maintaining consistency with Gate I's established voice, structure, and philosophy. Use when creating new Gate ebooks, drafting sections, or ensuring...
Testing patterns for GoGoJap project. Use when writing tests, creating mocks, or following TDD workflow.
激活首席架构师模式。用于项目初期，负责将模糊需求转化为精确的技术规格说明书、接口定义和测试计划。
激活高级开发工程师模式。用于设计完成后，根据设计契约进行纯代码实现。
激活 QA 工程师模式，主导测试编写、执行与故障回归。
Analyzes and optimizes CLAUDE.md files following Anthropic's official best practices. Use when reviewing existing CLAUDE.md for improvements, or when user mentions CLAUDE.md is too long or ineffective.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.