sandgardenhq

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 installing Gloria into a repo ("set up gloria", "install gloria in this project"), when a repo is missing .gloria/USING-GLORIA.md or the gloria section in CLAUDE.md/AGENTS.md, or after a gloria plugin update to refresh a stale doc — copies the canonical USING-GLORIA.md agent doc into the repo, wires an evergreen Gloria section into the agent instruction files (with the user's permission), and offers to register the project with gloria.dev. Idempotent; safe to re-run.

Use to investigate production problems through gloria's log debugging tools. Fires for plain requests about live behavior — "why is X failing in production", "what happened at 2pm", "debug these 500s", "is anything erroring right now", "check the logs", "what broke after the last deploy", "why are checkouts timing out" — for any project with a gloria log connection configured. Queries the org's own log provider live via the gloria MCP tools (get_log_provider_status, get_log_stats, list_error_groups, query_logs): find the spike, group the errors, correlate with the deploy, pull the stack trace, map it to source. Read-only over logs; never asks for credentials in chat.

Use to check code against a project's registered gloria Coding Standards. Fires for plain requests to compare code with the rules — "check this against our standards", "does this drift from our rules/conventions", "are we following our own standards", "review this for standards compliance", "check this PR against our standards", "run a standards check", "audit the repo for drift", "has our code drifted from the rules" — including before or after implementing a change in a project that has registered standards. Runs diff-scoped checks (the per-PR workhorse), cheap metadata checks (render stamp + rule-evidence staleness), or a full audit (snippet staleness included), and reports findings to the gloria drift ledger via report_check_run. Read-only: findings, never edits.

Use to map, document, and register a codebase's service dependencies with gloria.dev so they are monitored. Fires for plain requests to sync a dependency or project with gloria — "register this dependency", "register this project", "register/sync our services with gloria", "start monitoring this service", "add this integration to gloria", "sync my project with gloria" — and to inventory them — "document our integrations/dependencies", "what external services does this connect to", "make a health-check doc". Also fires whenever you add, remove, or swap an external service, SaaS API, SDK, API client, database, queue, or internal endpoint. Produces four Markdown docs (external SaaS inventory + health checks, internal systems inventory + health checks) and pushes the structured inventory to gloria.dev via its MCP tools (register_project, put_dependency).

Use to set up or register gloria Coding Standards for a project. Fires for plain requests to register or sync standards with gloria — "register our coding standards with gloria", "sync our conventions with gloria", "save our rules to gloria", "register our coding conventions" — and to derive them — "extract our coding standards", "derive rules and snippets from this repo", "set up the standards library". Orchestrates deriving-agent-code-style and mapping-packages-for-coding-agents, structures their findings into stable rules (slug ids, authority labels, scope, evidence), mines one canonical placeholder-ized snippet per rule-implied pattern, registers everything via the gloria MCP tools (register_standard, put_rule, put_snippet) with per-item approval, and renders a version-stamped Coding Standards section into CLAUDE.md/AGENTS.md.

Use while writing code in a project with a registered gloria Coding Standards library — before implementing anything pattern-shaped (a DAO, an API route, a migration, a test harness, a channel adapter), and whenever CLAUDE.md carries a "## Coding Standards" section with a gloria:standards stamp. Also fires for "follow/use our standards while writing this", "write this the way we do", and "register/contribute this back as a snippet". Drives the write-time discipline: find_snippets before writing, adopt or adapt the canonical exemplar, leave a gloria:snippet provenance marker, contribute reusable shapes back via put_snippet, and justify deliberate divergence.

Use when about to author a new agent skill, when asked whether the org already has a skill for some task, when sharing/publishing a reusable skill across the organization, or when installing a skill the org subscribes to from an external marketplace (e.g. Obra Superpowers) — drives the gloria.dev skills-library tools (search before you duplicate, get the full bundle, publish immutable versions org-wide, install external skills via the host agent's native marketplace).

Use when asked which agent skills a project already uses and which additional ones would help the people and agents working on it, or to stock your org's gloria.dev skills library from a project's needs. Inventories the skills in play (session list + `.claude/` config + CLAUDE.md), profiles the stack, recommends the gaps, then — only with consent — saves the useful ones to the library by reusing, copying, or authoring a bundle, and offers a local or global install.

Use when a documentation site needs real screenshots — "take the screenshots in SCREENSHOT_PLAN.md", "add screenshots to these docs", "screenshot the web app for the docs", "this page needs a picture of the dashboard", "get me terminal screenshots for this guide". Reads (or writes) a page-by-page screenshot plan, drives a browser to capture real product-UI screenshots, crops out chrome/PII, saves them under a per-page directory, and wires `` references into the docs at the exact spot. For shots it cannot generate itself (terminal output, IDE/editor state, native dialogs), it pre-wires the image path into the docs and hands the human an exact per-file capture list so dropping the file in requires no follow-up edit.

Use when you have a documentation site map / content plan and need the actual Doc Holiday instructions that generate and maintain the docs — "turn the site map into Doc Holiday prompts", "write the @doc.holiday prompts for our docs", "how do we make Doc Holiday build this docs site", "generate the create/update prompts for each page". Reads the planned IA (the output of `defining-the-documentation-site-map`) and the project's source, then emits, for every page, a ready-to-run `@doc.holiday` prompt with the right action, scope, Diátaxis mode, and target section — plus reusable Instruction Library entries for shared voice/style, ordered to match the IA, with maintenance/update prompts.

Use when you need to plan a project's documentation — "what should our docs contain and how should they be organized", "design the docs site map / IA", "lay out the docs site", "what pages do we need". Scans the source and emits a Diátaxis-organized site map (every page classified tutorial / how-to / reference / explanation) plus a per-page content plan and a Mermaid hierarchy, derived from the code and reconciled against the intended IA.

Author a Doc Holiday prompt that writes a brand-new documentation page for an undocumented feature.

Author a Doc Holiday prompt that fixes documentation which no longer matches the code.