sgai

Go code review checklist based on official Go style guides. When reviewing Go code for style, idioms, and best practices

Guide for creating custom opencode agents with proper configuration, permissions, path-based delegation, work splitting, and strict status envelopes. Use when creating or updating agents for coordination, implementation, review, deployment, verification, documentation, or specialized workflows.

TDD for process documentation - test with subagents before writing, iterate until bulletproof. When you discover a technique, pattern, or tool worth documenting for reuse. When editing existing skills. When asked to modify skill documentation. When you've written a skill and need to verify it works before deploying. When skills fail to help agents, when documentation is unclear, when new patterns emerge that need standardization.

Create and setup a new OpenAI Agents SDK application with interactive guidance for language choice, agent type selection (Basic, Voice, Realtime), project setup, and automatic verification.

Create and setup a new Claude Agent SDK application with interactive guidance for language choice, project setup, and automatic verification.

Problem-Solving Dispatch; Dispatch to the right problem-solving technique based on how you're stuck; Stuck on a problem. Conventional approaches not working. Need to pick the right problem-solving technique. Not sure which skill applies.

Interactive wizard to compose valid GOAL.md files for SGAI with step-by-step guidance through 7 phases. Use when creating GOAL.md, configuring agents and model, safety-analysis guidance, or starting an SGAI project. Safety Analysis must use coordinator/reviewer stpa-overview skill guidance.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches bounded reviewer subagents with TASK_PACKET and REVIEW_STATUS envelopes before proceeding

Post-completion factory improvement analysis. Guides the retrospective agent through artifact discovery, pattern analysis, suggestion generation, and presenting proposed changes for approval. Use when the retrospective agent starts its post-completion phase.

Coordinator and retrospective workflow-state protocol. Use only when the current agent has permission to call sgai_update_workflow_state; Task subagents should return STATUS or REVIEW_STATUS envelopes instead.

Entry point for STPA (System Theoretic Process Analysis) hazard and safety analysis. Use for full 4-step STPA sessions, focused project-critic safety reviews, coordinator safety gates, reviewer hazard checks, risk assessment, unsafe state transitions, external input, filesystem, concurrency, physical systems, or AI-driven systems.

Shared delegation contract for SGAI agents that invoke Task subagents. Use before delegating implementation, review, verification, deployment, writing, safety review, or project-critic work.

Shared return contract for SGAI Task subagents. Use before any delegated implementation, deployment, writing, verification, review, or project-critic subagent reports back to its caller.

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

Monitor sgai workspace status, events, progress, and workflow diagrams. Use when you need to observe what agents are doing, track progress, get the current state of all workspaces, or subscribe to real-time updates via SSE.

Start and stop agentic sessions in sgai workspaces. Use when you need to launch AI agent sessions or halt running sessions.

Drive sgai (Software Garden AI) from any MCP-capable harness or AI agent. Covers the cyclical probe/poll/act workflow for managing AI software factory workspaces, sessions, and human interaction. Use this as the entrypoint when orchestrating sgai from Claude Code, Codex, or any AI harness.

Create, fork, delete, and rename sgai workspaces via the HTTP API. Use when you need to set up new project workspaces, create parallel forks for concurrent development, clean up finished forks, or rename existing fork workspaces.

Run and manage ad-hoc AI prompts in sgai workspaces without starting a full agentic session. Use when you need to run a one-off AI prompt against a workspace, check the status of a running ad-hoc prompt, or stop a running ad-hoc prompt.

Use the sgai compose wizard to create and manage GOAL.md files for workspaces. Supports reading compose state, updating wizard fields, saving drafts, previewing generated GOAL.md content, browsing workflow templates, and writing the final GOAL.md to the workspace.

Access agents, skills, and code snippets available in sgai workspaces. Use when you need to discover what agents are defined in a workspace, browse available skills, get skill instructions, find code snippets by language, or retrieve snippet content for a specific task.

Build AI agents using prompt-native architecture where features are defined in prompts, not code. Use when creating autonomous agents, designing MCP servers, implementing self-modifying systems, or adopting the "trust the agent's intelligence" philosophy.

Handle agent questions and work gates in sgai workspaces. Use when an agent is blocked waiting for human input, when you need to respond to multi-choice questions, approve work gates, or provide free-text answers to agent queries.

Interactive idea refinement using Socratic method to develop fully-formed designs. When your human partner says "I've got an idea", "Let's make/build/create", "I want to implement/add", "What if we". When starting design for complex feature. Before writing implementation plans. When idea needs refinement and exploration. ACTIVATE THIS AUTOMATICALLY when your human partner describes a feature or project idea - don't wait for /brainstorm command.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Go testing patterns, coverage analysis, and best practices. When writing tests for Go code or analyzing test coverage

Guide for adding new code snippets to the library; When you need to add a new code snippet to the sgai_find_snippets library, when creating files without proper metadata, when using incorrect filenames or extensions, when adding code without extensive comments

MANDATORY when GOAL.md mentions deploying, shipping, releasing, or publishing built artifacts to any environment - reads deployment instructions from the .deploy/ directory, enforces pre-deployment verification, artifact integrity checks, deployment execution safety, post-deployment validation, and rollback planning; prevents deploying without tests, skipping rollback plans, or bypassing environment validation. When GOAL.md says deploy, ship, release, publish, or push artifact to production/staging/server.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/TypeScript code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetching, bundle optimization, or performance improvements.

SSE with useSyncExternalStore, reconnection with exponential backoff, snapshot rehydration, typed event parsing, connection status UI. Use when implementing SSE data stores, real-time update hooks, or connection resilience in the React SPA. Triggers on SSE, EventSource, useSyncExternalStore, real-time updates, reconnection, or live data tasks.

Find breakthrough insights by forcing unrelated concepts together, detecting meta-patterns across domains, and discovering simplification cascades. When stuck on complex problems. When searching for innovative solutions. When same issue appears in different domains. When complexity feels excessive. When conventional approaches aren't working. When seeking radical simplification.

Recognize when disagreements reveal valuable context, preserve multiple valid approaches instead of forcing premature resolution. When multiple approaches have legitimate trade-offs. When stakeholders have conflicting valid priorities. When context determines which approach is better. During design when you're tempted to ask "which is best?" but both are good. When tensions reveal flexibility needs.

Understand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures. When problem feels familiar but can't remember details. When asked "why do we use X?". Before abandoning an approach, understand why it exists. When evaluating "new" ideas that might be revivals. When past attempts failed and need to understand why. When tracing decision genealogy.

You must use this skill when debugging web UI bugs or testing interactive components that require multi-step browser interactions. Automates common UI testing patterns for debugging web applications - starting servers, navigating to pages, interacting with form elements, and verifying expected behaviors without manual step-by-step Playwright commands

Clean up generated code by questioning why things are there and cross-referencing with GOAL.md, even when tempted to skip due to time pressure or thinking it's "good enough". After generating code, when tempted to commit messy code, or when noticing clutter that could be removed.

Go 1.22+ enhanced HTTP routing with method matching and wildcards. When defining HTTP routes using net/http ServeMux in Go 1.22+

Go module structure and project organization patterns. When setting up a new Go project or organizing existing Go code

Use when you need to find code snippets by language and query. When looking for code examples, patterns, or snippets in a specific programming language. When you need to search for code snippets quickly. When searching for code patterns or best practices.