By lightseekorg
Enforce a structured contribution workflow for the Shepherd Model Gateway: orient to the codebase by crate, implement features using subsystem-specific recipes, run multi-step quality gates before opening PRs, and perform systematic code reviews that check layering, configuration, lifecycle, routing, and error handling.
Use when preparing to commit, open a PR, or check quality gates in the SMG repository — enforces verification before shipping
Use when implementing a feature, adding functionality, fixing a bug, or modifying behavior in the SMG repository — routes to subsystem-specific recipes and enforces step-by-step execution
Use when you need to understand the SMG codebase structure, find which crate owns a subsystem, or understand how crates depend on each other before making changes
Use when reviewing a pull request, checking a diff, or doing code review in the SMG repository — enforces systematic subsystem-aware review
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI-powered development guide for the Shepherd Model Gateway — 4 process-enforcing skills that change what your AI coding agent does, not just what it knows.
Works with Google Antigravity, Gemini CLI, Claude Code, Codex, and Cursor.
Project-level (Recommended): Antigravity natively supports the skills through its workflow system. Simply open this repository (or copy the .agents/ and skills/ directories into your SMG project root) in the Antigravity IDE and it will automatically discover them.
Global: To make these skills and workflows available across all projects, copy or symlink them into your global Antigravity ~/.gemini/antigravity/ directory:
git clone https://github.com/lightseekorg/smg-dev-guide.git ~/.gemini/antigravity/repos/smg-dev-guide
mkdir -p ~/.gemini/antigravity/workflows ~/.gemini/antigravity/skills
ln -s ~/.gemini/antigravity/repos/smg-dev-guide/.agents/workflows/* ~/.gemini/antigravity/workflows/
ln -s ~/.gemini/antigravity/repos/smg-dev-guide/skills/* ~/.gemini/antigravity/skills/
The Gemini CLI natively supports Agent Skills. You can install these skills directly from the repository using the CLI's built-in package manager.
Global Installation (Available in all projects):
gemini skills install https://github.com/lightseekorg/smg-dev-guide.git
Workspace Installation (Only in current project):
gemini skills install https://github.com/lightseekorg/smg-dev-guide.git --scope workspace
From the shell:
claude plugin marketplace add lightseekorg/smg-dev-guide
claude plugin install smg@smg-dev-guide
Or inside Claude Code:
/plugin marketplace add lightseekorg/smg-dev-guide
/plugin install smg@smg-dev-guide
Run /reload-plugins (or restart Claude Code) to load the skills.
Copy or symlink the skills into your user skills directory:
git clone https://github.com/lightseekorg/smg-dev-guide.git ~/.agents/repos/smg-dev-guide
ln -s ~/.agents/repos/smg-dev-guide/.agents/skills/* ~/.agents/skills/
Or clone into the SMG repo and skills are discovered automatically from .agents/skills/.
Install as a Cursor plugin via .cursor-plugin/plugin.json.
4 skills, each enforcing a specific developer action:
| Skill | Action | What It Does |
|---|---|---|
map | Orient | Crate map, layering rules, config propagation, request flow, label pipeline |
implement | Build | Detects subsystem, loads recipe, creates tasks, enforces step-by-step execution with verification |
review-pr | Review | Maps changed files to checklist sections, creates review tasks per subsystem, cites file:line |
contribute | Ship | 5-step quality gate (fmt → clippy → test → bindings → commit format) with enforcement |
Google Antigravity — invoke workflows using slash commands in the chat:
/map → discover codebase structure and ownership
/implement-feature → guides you through building a feature
/review-pr → checks your work against anti-patterns
/verify-pr → runs the full 5-step quality gate
Gemini CLI — skills trigger automatically based on your prompt:
"Where does the label pipeline live?" → Activates map skill
"Am I ready to submit?" → Activates contribute skill
Note: You can view installed skills by running gemini skills list.
Claude Code — use the /smg command:
/smg where does the label pipeline live → smg:map
/smg add a --timeout flag → smg:implement
/smg review PR #562 → smg:review-pr
/smg am I ready to submit → smg:contribute
Codex — skills trigger automatically based on your prompt, or invoke explicitly via $smg-implement, $smg-contribute, etc.
Unlike passive reference docs, these skills enforce workflows:
implement → contribute → review-pr flowimplement auto-detects what you're building and loads the right recipe:
npx claudepluginhub lightseekorg/smg-dev-guide --plugin smgVerification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Corca Workflow Framework — consolidated hooks and skill orchestration for structured development sessions
Git and PR workflows with code review, onboarding, and PR enhancement
PROJECT.md-first autonomous development with hybrid auto-fix documentation. 8-agent pipeline, auto-orchestration, docs auto-update on commit (true vibe coding). Knowledge base system with 90% faster repeat research. Strict mode enforces SDLC best practices automatically. Works for ANY Python/JavaScript/TypeScript/Go project.
Autonomous session orchestrator for Claude Code - manages multi-phase development workflows
Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review) with typed handoff contracts, lifecycle hooks, and MCP servers.