Controls Shelly Duo GU10 RGBW smart bulbs (Gen1) over LAN HTTP REST. Includes mDNS discovery (with the critical 'bind to non-loopback IPv4' gotcha), color/temperature/off endpoints, status probe, and the 0.2s min-interval for LAN debounce. Use when the user wants to control a Shelly bulb directly without their cloud (Gen1 Shelly Color, Shelly Duo, Shelly RGBW2 share most of this contract), do mDNS discovery on a JVM, or build a low-latency IoT pipeline against a local Shelly device.

Installs spec-as-source enforcement scripts, CI workflow, and pre-commit hooks into a project. Trigger — setup spec enforcement, add spec checks, configure spec-as-source, install spec scripts, add spec CI.

Syncs .github/workflows/spec-verification.yml with the test runner and test files declared in specs. Trigger — update CI workflow, sync spec CI, regenerate workflow, CI out of sync with specs, add spec test to CI.

Deletes all files declared as targets in specs/*.spec.md and rebuilds them from the specs to verify spec-as-source integrity. Trigger — clean rebuild, verify source of truth, spec drift check, regenerate from specifications, rebuild from spec.

Guided setup for TripIt→Reclaim travel timezone sync credentials. Validates environment variables and runs a dry-run to confirm everything works. Use when the user wants to set up, configure, or troubleshoot the TripIt to Reclaim calendar sync, API keys, or integration connection.

Run the TripIt→Reclaim travel timezone sync and interpret its JSON output. Handles no-change silence, change summaries, overlap warnings, and errors. Use when the user asks to sync time zones, update Reclaim from TripIt, check travel schedule sync, or run the calendar timezone update.

Build, scaffold, and demo Java AI agent systems with the langchain4j-agentic module — workflow patterns (sequential, loop, parallel, conditional), supervisor, and custom Planner strategies including the flagship typed-verdict (CriticResult-style) critic pattern, plus langchain4j-mcp tool servers and langchain4j-agentic-a2a remote agents. Use whenever the user mentions LangChain4j, langchain4j-agentic, Java AI agents, @Agent / @Tool, AgenticScope, AgenticServices, sequenceBuilder / loopBuilder / supervisorBuilder / plannerBuilder, MCP or A2A in Java, or wants to build a conference demo / workshop / POC around autonomous Java agents. Pinned to 1.15.0 core + 1.15.0-beta25 agentic/mcp; refresh with scripts/check_versions.sh.

Use when the user asks to log work, record what was done, or save task progress. Creates a structured markdown task log in `agent-logs/` with validation, waivers, and a final gates summary.

Use when the user asks you to implement a feature, fix a bug, or complete a repository task end-to-end (from scoping through code changes, validation, and final gate summary).

Use when `.tf` or `.tfvars` files have been edited, added, or removed and you need to verify that the code changes produce the intended Terraform plan before the task is considered complete. Runs `terraform plan` in `examples/test_app` and cross-checks the result against the change set you expected your edits to cause. This is a gate: do not declare a Terraform task done without passing it.

Use this when handling a CODE ticket (a bug or feature in application source) that should go through the review-and-merge flow. Do NOT use for docs-only tickets, or for context-artifact changes.

Use this for a documentation-only ticket — adding or editing README content, guides, prose, or code comments with no change to application behavior. Adding a new section (e.g. a quickstart) counts. Edits the file directly, no PR or review. Not for code bugs or features — use fix-the-ticket for those.

Optimizes RLS policies by enforcing SELECT-wrapped auth.uid() calls, mandatory B-Tree/GIN indexes on policy-referenced columns, and SECURITY DEFINER encapsulation of deep JOINs. Use when optimizing RLS performance, fixing policy full table scans, wrapping auth.uid in SELECT, or indexing columns used in RLS policies.

Configures pgsodium Vault extension for API key and secret storage. Creates SECURITY DEFINER functions assigned to service_role for secure access. Eliminates hardcoded secrets. Use when storing API keys, managing secrets in Supabase, implementing pgsodium Vault, or replacing hardcoded credentials with Vault references.

Creates PL/pgSQL RPC implementing Reciprocal Rank Fusion (score = 1/(k+rank)) to fuse semantic pgvector results with full-text tsvector results. Use when implementing hybrid search, RRF search, semantic plus keyword search, exact SKU and conceptual queries, or vector and full-text fusion.

Configures TUS resumable upload client for files over 6MB with Postgres Advisory Lock 409 Conflict handling. Enforces tenant-scoped bucket paths. Use when implementing large file uploads, resumable uploads, TUS protocol, uploads over unstable networks, or files larger than 6MB in Supabase Storage.

Creates RLS policies enforcing tenant_id isolation on shared-schema tables. Verifies ALTER TABLE ENABLE ROW LEVEL SECURITY before policy creation. Requires tenant_id column and custom-access-token-hook JWT claims. Use when implementing multi-tenant data isolation, tenant-safe queries, shared schema RLS, or tenant_id policy creation.

Inspects database health by analyzing slow queries, identifying bottlenecks, and checking Postgres performance indicators. Use when diagnosing database issues, checking slow queries, inspecting DB health, finding performance bottlenecks, or troubleshooting Supabase Postgres problems.

Configures pgvector HNSW indexes with correct distance operators. Enforces inner product operator for normalized embeddings instead of cosine distance. Use when setting up vector search, creating embedding indexes, configuring semantic search, or choosing between HNSW and IVFFlat index types.

Generates code verifier/challenge pairs, exchanges authorization codes for sessions, sets secure HTTP-only session cookies, and configures server-side callback handling to implement the Proof Key for Code Exchange auth flow. Replaces implicit token-in-fragment flows by removing hash-based token extraction and localStorage usage. Use when implementing Supabase authentication, OAuth login, secure browser auth, SSR auth setup, or modern auth flow migration.

Registra en docs/bitacora-ia.md cada tarea hecha con un agente de código (Claude Code, Codex u otro), con lo que se le pidió, lo que hizo, lo que revisó o corrigió la persona, las propuestas descartadas y su motivo, y el tiempo que tomó. Úsala al terminar una tarea hecha por el agente, cuando la persona corrige o descarta una propuesta del agente, al cerrar un entregable, o para reconstruir la bitácora desde el historial de git antes de escribir el README.

Crea la rama de un entregable, abre el pull request y lo integra en la rama de integración (por ejemplo ProductionEnv) con merge commit y etiqueta, sin borrar la rama, para que cada entregable se vea claro en el historial de git. Úsala al empezar o terminar un entregable, al integrar una rama, al preparar la entrega final hacia main, o cuando pregunten cómo dejar el historial de git listo para una revisión.

Escribe o revisa el README.md de entrega de una prueba técnica hecha con agentes de código, con los 12 puntos obligatorios (funcionalidades, tecnologías y versiones, estructura, cumplimiento de requisitos, instalación, base de datos, procedimiento almacenado, tiempo, herramientas de IA, uso del agente, decisiones técnicas y consideraciones). Toma los datos del código, del historial de git, de la bitácora de IA y del glosario. Úsala al preparar la entrega, al cerrar un entregable o cuando pidan revisar si el README cumple.

Adds hard similarity threshold guards to vector retrieval RPCs. Returns empty results instead of weak matches to prevent downstream hallucination. Use when implementing retrieval guardrails, minimum similarity thresholds, match_threshold parameters, or preventing RAG hallucination from low-confidence results.

Configures private Realtime channels with RLS-backed authorization on the realtime.messages table. Enforces tenant-scoped Presence and Broadcast security. Use when implementing private realtime channels, realtime authorization, presence security, broadcast security, or securing the realtime messages table.

Sets up Prometheus scrape jobs targeting the Supabase metrics endpoint and configures log drain pipelines. Establishes monitoring dashboards and alerting baselines. Use when configuring Supabase monitoring, setting up Prometheus metrics, implementing log drains, or establishing observability for production Supabase deployments.

Creates Postgres triggers that fire database webhooks to Edge Functions or external endpoints on INSERT/UPDATE/DELETE events. Configures pg_net for HTTP callouts and payload serialization. Use when implementing event-driven workflows, database webhooks, trigger-based notifications, or automated pipelines on table changes.

Configures Edge Functions to use EdgeRuntime.waitUntil for background work while returning immediate 200 OK. Routes massive async workloads through pg_cron discovery and pgmq task queuing. Use when building background processing, async third-party calls, long-running edge function tasks, or webhook-driven pipelines.