Sandgarden
Official@sandgardenhq
Offers a rigorous framework for test-driven software engineering, system safety analysis, and structured development lifecycle management within modular workspaces.
Agent Skills by Sandgarden
Showing 63 vetted skills indexed across 1 GitHub repositories.
new-openai-sdk-app
Generate OpenAI Agents SDK applications for Python or TypeScript agents.
test-driven-development
Write failing tests before production code using a red-green-refactor cycle.
testing-anti-patterns
Enforce TDD practices and prevent mock-related testing anti-patterns.
systematic-debugging
Locate and validate root causes before implementing fixes.
project-completion-verification
Summarize GOAL.md task completion by parsing markdown checkboxes.
markdown-navigation
Generate hierarchical outlines and extract sections from markdown files using bash utilities.
run-long-running-processes-in-tmux
Runs commands in detached tmux sessions with lifecycle management and monitoring.
dispatching-parallel-agents
Dispatch one focused agent per independent software test failure in parallel.
retrospective
Analyze completed AI factory session artifacts to identify inefficiencies and propose enhancements.
code-cleanup
Audit generated code against GOAL.md and log changes in PROJECT_MANAGEMENT.md.
finishing-a-development-branch
Run tests before offering merge, pull request, or cleanup actions.
browser-bug-testing-workflow
Automate browser debugging with tmux servers and Playwright interactions.
using-jj-instead-of-git
Replace Git version control actions with Jujutsu (jj) equivalents.
condition-based-waiting
Replace arbitrary test sleeps with condition-based polling loops.
deployment
Deploy built artifacts with pre-deployment gates, rollback plans, and post-deployment health checks.
react-best-practices
Apply performance guidelines to React and Next.js codebases.
testing-skills-with-subagents
Orchestrate RED-GREEN-REFACTOR cycles to harden skills against agent rationalizations.
requesting-code-review
Analyze git commit ranges and categorize code review issues by severity.
set-workflow-state
Update workflow state files with status, task, and progress via sgai_update_workflow_state.
frontend-design
Design and generate distinctive frontend interfaces with HTML, CSS, JavaScript, React, or Vue.
using-skills
Enforce mandatory skill checks before any AI task.
receiving-code-review
Interpret, verify, and implement code review feedback in priority order.
new-sdk-app
Scaffold TypeScript or Python Claude Agent SDK projects with dependency installation and verification.
htmx-auto-refresh-preservation
Preserve user state during HTMX auto-refresh with Idiomorph morph swaps.
Frequently Asked Questions About Sandgarden
FAQPage SchemaWhat specific engineering tasks does Sandgarden enable?▼
Sandgarden enables rigorous test-driven development, systematic debugging, and formal system safety analysis using STPA methodologies. It facilitates structured project management through markdown-based goal tracking, automated code review categorization, and lifecycle management for long-running processes within isolated development workspaces.
Which technical personas benefit most from these capabilities?▼
Software engineers, systems architects, and reliability engineers benefit from these capabilities. The platform is designed for developers focused on high-integrity codebases, those implementing strict TDD cycles, and teams requiring formal hazard analysis and safety-critical system modeling.
What are the primary prerequisites for integrating these skills?▼
Integration requires a workspace environment compatible with the sgai interface. Users should have familiarity with Go project structures, Jujutsu version control, and standard POSIX-compliant shell environments for managing tmux sessions and HTTP-based workspace interactions.