GitHub organization
Agent skills by sandgardenhq
- skills
- 53
- repository
- 1
Repositories by sandgardenhq
Skills by sandgardenhq, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | A skill your agent uses when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation… | sandgardenhq/ | 137 | 4 repos | ~1.4k | Automated safety check: Pass | Unknown | 17 days ago |
| 2 | A skill your agent uses when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state… | sandgardenhq/ | 137 | 3 repos | ~933 | Automated safety check: Pass | Unknown | 17 days ago |
| 3 | A skill your agent uses when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally… | sandgardenhq/ | 137 | 3 repos | ~970 | Automated safety check: Pass | Unknown | 17 days ago |
| 4 | Build AI agents using prompt-native architecture where features are defined in prompts, not code. | sandgardenhq/ | 137 | — | ~2k | Automated safety check: Pass | Unknown | 17 days ago |
| 5 | 5.Adhoc Run and manage ad-hoc AI prompts in sgai workspaces without starting a full agentic session. | sandgardenhq/ | 137 | — | ~1.2k | Automated safety check: Pass | Unknown | 17 days ago |
| 6 | You must use this skill when debugging web UI bugs or testing interactive components that require multi-step browser interactions. | sandgardenhq/ | 137 | — | ~3.7k | Automated safety check: Pass | Unknown | 17 days ago |
| 7 | Guide for creating custom opencode agents with proper configuration, permissions, path-based delegation, work splitting, and strict status envelopes. | sandgardenhq/ | 137 | — | ~1.8k | Automated safety check: Pass | Unknown | 17 days ago |
| 8 | A skill your agent uses when reading JSON files in Go applications, especially for configuration files, data files, or any JSON parsing that requires comprehensive error handling for missing files… | sandgardenhq/ | 137 | — | ~2.2k | Automated safety check: Pass | Unknown | 17 days ago |
| 9 | Interactive wizard to compose valid GOAL.md files for SGAI with step-by-step guidance through 7 phases. | sandgardenhq/ | 137 | — | ~645 | Automated safety check: Pass | Unknown | 17 days ago |
| 10 | A skill your agent uses when building any HTMX interface with polling, SSE, or auto-refresh - prevents state loss (form inputs, scroll positions, details/accordion state) during automatic DOM… | sandgardenhq/ | 137 | — | ~3.6k | Automated safety check: Pass | Unknown | 17 days ago |
| 11 | Understand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures. | sandgardenhq/ | 137 | 2 repos | ~1.8k | Automated safety check: Pass | Unknown | 17 days ago |
| 12 | Handle agent questions and work gates in sgai workspaces. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~1.4k | Automated safety check: Pass | Unknown | 17 days ago |
| 13 | 13.Scale Game Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales. | sandgardenhq/ | 137 | 1 repo | ~582 | Automated safety check: Pass | Unknown | 17 days ago |
| 14 | 14.Knowledge Access agents, skills, and code snippets available in sgai workspaces. | sandgardenhq/ | 137 | — | ~1.5k | Automated safety check: Pass | Unknown | 17 days ago |
| 15 | 15.Monitoring Monitor sgai workspace status, events, progress, and workflow diagrams. | sandgardenhq/ | 137 | — | ~1.2k | Automated safety check: Pass | Unknown | 17 days ago |
| 16 | SSE with useSyncExternalStore, reconnection with exponential backoff, snapshot rehydration, typed event parsing, connection status UI. | sandgardenhq/ | 137 | — | ~3.1k | Automated safety check: Pass | Unknown | 17 days ago |
| 17 | A skill your agent uses when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches bounded reviewer subagents with TASKPACKET and… | sandgardenhq/ | 137 | — | ~856 | Automated safety check: Pass | Unknown | 17 days ago |
| 18 | Start and stop agentic sessions in sgai workspaces. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~873 | Automated safety check: Pass | Unknown | 17 days ago |
| 19 | Entry point for STPA (System Theoretic Process Analysis) hazard and safety analysis. | sandgardenhq/ | 137 | — | ~2.4k | Automated safety check: Pass | Unknown | 17 days ago |
| 20 | 20.Using Sgai Drive sgai (Software Garden AI) from any MCP-capable harness or AI agent. | sandgardenhq/ | 137 | — | ~1.3k | Automated safety check: Pass | Unknown | 17 days ago |
| 21 | Create, fork, delete, and rename sgai workspaces via the HTTP API. | sandgardenhq/ | 137 | — | ~1.3k | Automated safety check: Pass | Unknown | 17 days ago |
| 22 | Post-completion factory improvement analysis. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~7.7k | Automated safety check: Pass | Unknown | 17 days ago |
| 23 | Interactive idea refinement using Socratic method to develop fully-formed designs. | sandgardenhq/ | 137 | — | ~1.4k | Automated safety check: Pass | Unknown | 17 days ago |
| 24 | 24.Code Cleanup 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". | sandgardenhq/ | 137 | — | ~1.2k | Automated safety check: Pass | Unknown | 17 days ago |
| 25 | Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?". | sandgardenhq/ | 137 | — | ~570 | Automated safety check: Pass | Unknown | 17 days ago |
| 26 | 26.Compose Use the sgai compose wizard to create and manage GOAL.md files for workspaces. | sandgardenhq/ | 137 | — | ~1.5k | Automated safety check: Pass | Unknown | 17 days ago |
| 27 | Find breakthrough insights by forcing unrelated concepts together, detecting meta-patterns across domains, and discovering simplification cascades. | sandgardenhq/ | 137 | — | ~2k | Automated safety check: Pass | Unknown | 17 days ago |
| 28 | Go code review checklist based on official Go style guides. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~3.1k | Automated safety check: Pass | Unknown | 17 days ago |
| 29 | Go 1.22+ enhanced HTTP routing with method matching and wildcards. | sandgardenhq/ | 137 | — | ~1.3k | Automated safety check: Pass | Unknown | 17 days ago |
| 30 | Go module structure and project organization patterns. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~1.7k | Automated safety check: Pass | Unknown | 17 days ago |
| 31 | Go testing patterns, coverage analysis, and best practices. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~2.5k | Automated safety check: Pass | Unknown | 17 days ago |
| 32 | A skill your agent uses when you need to find code snippets by language and query. | sandgardenhq/ | 137 | — | ~489 | Automated safety check: Pass | Unknown | 17 days ago |
| 33 | Guide for adding new code snippets to the library; When you need to add a new code snippet to the sgaifindsnippets library, when creating files without proper metadata, when using incorrect… | sandgardenhq/ | 137 | — | ~807 | Automated safety check: Pass | Unknown | 17 days ago |
| 34 | Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?". | sandgardenhq/ | 137 | — | ~521 | Automated safety check: Pass | Unknown | 17 days ago |
| 35 | Spot patterns appearing in 3+ domains to find universal principles. | sandgardenhq/ | 137 | — | ~519 | Automated safety check: Pass | Unknown | 17 days ago |
| 36 | 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. | sandgardenhq/ | 137 | — | ~3.9k | Automated safety check: Notes | Unknown | 17 days ago |
| 37 | Guide for creating and implementing plugins to extend OpenCode functionality, including hooks, custom tools, and event handling. | sandgardenhq/ | 137 | — | ~1.2k | Automated safety check: Notes | Unknown | 17 days ago |
| 38 | Recognize when disagreements reveal valuable context, preserve multiple valid approaches instead of forcing premature resolution. | sandgardenhq/ | 137 | — | ~1.3k | Automated safety check: Pass | Unknown | 17 days ago |
| 39 | Automatically scans GOAL.md for unchecked items, provides completion status summary, and enables coordinator to mark items as complete. | sandgardenhq/ | 137 | — | ~1.2k | Automated safety check: Pass | Unknown | 17 days ago |
| 40 | Guide for using tmux to manage detached sessions for long-running processes, including lifecycle management, cleanup, startup, verification, and output capture; When you need to run servers or… | sandgardenhq/ | 137 | — | ~1.4k | Automated safety check: Pass | Unknown | 17 days ago |
| 41 | Coordinator and retrospective workflow-state protocol. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~1.2k | Automated safety check: Pass | Unknown | 17 days ago |
| 42 | Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z". | sandgardenhq/ | 137 | — | ~725 | Automated safety check: Pass | Unknown | 17 days ago |
| 43 | STPA Step 1 - Define the purpose of analysis by identifying losses, hazards, and system-level constraints. | sandgardenhq/ | 137 | — | ~1.2k | Automated safety check: Pass | Unknown | 17 days ago |
| 44 | STPA Step 3 - Identify Unsafe Control Actions (UCAs) using the 4-type analysis framework. | sandgardenhq/ | 137 | — | ~1.5k | Automated safety check: Pass | Unknown | 17 days ago |
| 45 | STPA Step 4 - Identify Loss Scenarios by tracing causal pathways back through control loops to understand why UCAs might occur. | sandgardenhq/ | 137 | — | ~1.9k | Automated safety check: Pass | Unknown | 17 days ago |
| 46 | Shared delegation contract for SGAI agents that invoke Task subagents. | sandgardenhq/ | 137 | — | ~741 | Automated safety check: Pass | Unknown | 17 days ago |
| 47 | Shared return contract for SGAI Task subagents. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~604 | Automated safety check: Pass | Unknown | 17 days ago |
| 48 | YOU MUST USE THIS SKILL WHENEVER YOU NEED TO USE git OR jj. An agent skill from sandgardenhq/sgai. | sandgardenhq/ | 137 | — | ~1.3k | Automated safety check: Pass | Unknown | 17 days ago |
Questions, answered from the data.
What is the best skill by sandgardenhq?
Root Cause Tracing from sandgardenhq/sgai ranks first of the 53 skills by sandgardenhq listed here, with the highest score: its repository has 137 GitHub stars, 4 other GitHub owners carry a copy, its SKILL.md loads about 1.4k tokens and it passes the automated safety check with no findings. Next come Condition Based Waiting and Defense In Depth.
Are sandgardenhq's skills official?
None yet. All 53 skills by sandgardenhq listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.