Skills for development with AI coding agents

Docs · Installation · User Guide

---

codevoyant is a collection of skills (slash commands) that give AI coding agents structured workflows for planning, development, and tooling. Works with Claude Code, OpenCode, and VS Code Copilot.

Skills

Workflows

	spec — plan and execute complex work Research requirements, generate proposals, create phase-by-phase implementation plans, and execute them step-by-step or hand off to a background agent.
	dev — architecture and exploration Architecture planning, technical exploration, and repo/branch comparison.
	docs — engineering documentation Generate, update, review, and retroactively create docs from standard templates.
	flow — end-to-end pipeline orchestration Chain skill workflows into end-to-end pipelines that run sequentially.
	pr — AI-powered code review Generate professional inline review comments from a diff, address change requests, and publish a draft review.
	qa — bug investigation and smoke testing Structured bug investigation, browser-agent smoke tests, one-command issue filing to GitHub, GitLab, or Linear.
	skill — build, maintain, and report skills Scaffold new skills, iterate on existing ones, audit quality, and report issues to skill authors.

Domains (experimental context skills for specialized engineering)

	em Experimental — engineering project planning Milestone-grouped task plans, capacity and dependency review, and sync with Linear.
	pm Experimental — product roadmaps and PRDs Phased roadmaps, per-feature PRDs, prioritization review, and Linear initiative sync.
	ux Experimental — prototyping and style research Scaffold SvelteKit prototypes, create single-file wireframe explorations, and extract styles from live sites.
	compgeo Experimental — computational geometry 3D formats, bounding boxes, voxels, point clouds, feature extraction (CGAL), ray tracing, GLTF, SDFs, rotations/quaternions, OpenVDB ops — Python, C++, TypeScript.
	hpc Experimental — high-performance computing C++ threading, OpenMP, TBB, SIMD, CUDA, SYCL, MPI, Python parallelism, Ray, Thrust, Kokkos, and NVIDIA Warp GPU kernels.
	mle Experimental — ML engineering Data pipelines (Ray Data), distributed training, model eval, TensorBoard, MLflow, model publishing, data curation, Label Studio, DVC versioning, data loaders.
	llm Experimental — LLM engineering AI SDK and LangGraph agents, tool calling, document/image processing, open-weight model serving on AWS/GCP, RAG (AWS/GCP/OSS), and LLM eval tooling.

Tools

	changelog — retcon PR/MR commit messages and preview the next changelog
	cz — show current and predicted next version using commitizen
	docker — multi-stage builds, Compose, cross-platform networking, GCP registry
	gcp — Artifact Registry, Cloud Run deploy, gcloud auth, service account patterns
	gh — Watch Actions pipelines, fetch and post inline PR review comments, manage draft reviews
	git — conventional commits with auto-formatting and safe interactive rebase
	glab — watch CI pipelines, fetch and post inline MR discussion notes, manage draft reviews
	helix — Helix editor key bindings for file navigation and selection-based workflows
	linear — create Linear issues and bug reports via MCP Linear tools
	mise — mise.toml authoring, task naming conventions, language-specific setup recipes
	release — show current and predicted next version via semantic-release or release-it
	task — detect and run tasks across mise, just, task.dev, and npm scripts
	terraform — directory structure, backend config, workspace-per-environment for GCP and AWS
	vim — Vim and Neovim key bindings for file navigation, search, and splits

Frameworks

	react — Zustand state management, shadcn/ui and Tailwind, React Three Fiber and Drei, data fetching
	sveltekit — feature-slice architecture, Svelte 5 runes, shadcn-svelte, a11y, form patterns
	tanstack — TanStack Start file-based routing, Router v1, Query v5, Form, server functions

Languages

	cpp — CMake project structure, Conan package management and publishing, gRPC service patterns, code standards, release profiles
	python — uv workspace and publishing, MLflow tracking, Ray distributed training, Warp GPU kernels, Pydantic, Click CLIs
	typescript — pnpm workspaces, publishing, Vitest, ESLint flat config, GitLab CI

Installation

Claude Code

npx skills add cloudvoyant/codevoyant

OpenCode

curl -fsSL https://raw.githubusercontent.com/cloudvoyant/codevoyant/main/scripts/install-opencode.sh | bash

VS Code Copilot

curl -fsSL https://raw.githubusercontent.com/cloudvoyant/codevoyant/main/scripts/install-vscode.sh | bash

Quick Start

# Plan and execute a feature
/spec new my-feature          # explore requirements and create a plan
/spec go my-feature           # execute step-by-step with review stops
/spec bg my-feature           # hand off to a background agent

# Ship code
/git commit                   # format → conventional commit → push
/gh ci --autofix              # watch GitHub Actions, auto-fix failures and re-push
/glab ci --autofix            # watch GitLab CI, auto-fix failures and re-push

# Review a PR/MR
/pr new                       # generate inline review comments from the diff
/pr address                   # pull reviewer feedback and propose fixes

# Plan engineering work
/em plan "migrate auth to OAuth2"    # milestone-grouped task plan
/em review my-plan                   # capacity and risk review

# Plan product work
/pm plan quarter                     # draft quarterly roadmap
/pm prd "user authentication"        # standalone PRD

# Build a skill
/skill new my-command                # scaffold from template
/skill critique my-command           # audit quality before shipping
/skill feedback spec                 # report an issue to skill authors

See the full documentation →

License

MIT © Cloudvoyant