AI & ML

Use `analysis-agent` to identify domain ownership, invariants, state transitions, and cross-context effects when rules change or ownership is unclear. Skip presentation-only or question-only work with no domain behavior.

`analysis-agent`/`task-agent`/`review-agent`: use for recurrence guards on known defects, incidents, or escaped failures; skip speculative risk without a prior failure mechanism.

Use `analysis-agent` when engineering intent lacks desired behavior, boundaries, constraints, or completion signals. Skip requests with an accepted Engineering Brief and no-repo direct-answer work.

Use an independently assigned `review-agent` for post-authoring review of changed rd-skills routing registries, fixtures, mappings, or owner conflicts without repair. Skip product work and in-task global rerouting.

`analysis-agent`/`task-agent`/`review-agent`: primary-Skill-selected for races, locks, optimistic conflicts, or worker overlap; never task owner; skip without concurrency impact.

`analysis-agent`/`task-agent`/`review-agent`: use for database, broker, cache, HTTP, framework, process, or transaction seam proof; skip local, portfolio, and release-verdict work.

Use `review-agent` for a high-risk Engineering Brief when a critical path, architecture boundary, material risk, or multiple downstream tasks need deeper design evidence. Skip ordinary work without those signals.

`task-agent`/`review-agent`: use when broker delivery, ordering, acknowledgement, DLQ, backpressure, or replay changes; skip synchronous retry without message semantics.

`analysis-agent`/`task-agent`/`review-agent`: use when fixtures, factories, seeds, isolation, cleanup, or sensitive test-data rules change; skip when test data is unaffected.

`analysis-agent`/`task-agent`: use when commit timing, payloads, schema, ordering, idempotency, or retry changes; skip when no domain-event decision is required.

`analysis-agent`/`task-agent`/`review-agent`: use when Go context, goroutine, channel, error, interface, or resource semantics affect behavior; skip generic or non-Go work.

`analysis-agent`/`task-agent`/`review-agent`: use when latency, throughput, bundle, memory, CPU, query, rendering, or resource cost needs a budget; skip without performance risk.

Use `task-agent` to update source-backed documentation or `review-agent` to assess documentation impact and accuracy when public behavior or operator workflows change. Skip work with no audience-facing behavior change.

Analyze an API, schema, migration, or compatibility decision with `analysis-agent`, or implement its bounded contract change with `task-agent`. Do not select it when no data or public-contract surface is affected.

`analysis-agent`/`task-agent`/`review-agent`: use when merges, rebases, conflicts, history rewrite, generated files, or recovery need evidence; skip when Git is irrelevant.

`task-agent`/`review-agent`: use when structured errors, logs, correlation, redaction, propagation, or safe diagnostics change; skip when logging/error handling is unaffected.

`analysis-agent`/`task-agent`/`review-agent`: use when a service split affects ownership, deployment, scaling, isolation, contracts, or data; skip without a split decision.

`analysis-agent`/`task-agent`/`review-agent`: use when personal-data purpose, retention, deletion, sharing, telemetry, or provider handling changes; skip legal-only work.

`analysis-agent`/`task-agent`/`review-agent`: use for structure, workspace or package bootstrap, config, scripts, or quality gates; skip without an initialization decision.

`analysis-agent`/`task-agent`/`review-agent`: discover source of truth, candidate owner, and change surface before planning; hand known candidates to impact inspection.

`analysis-agent`/`task-agent`: use when a use case coordinates authorization, domain work, transactions, or external effects; skip transport, storage, and rule-only work.

`analysis-agent`/`task-agent`/`review-agent`: use when authoring SKILL.md, triggers, decisions, references, registry, routing, or validation; skip when no Skill content changes.

Use `analysis-agent` for integration decisions or `task-agent` for cross-system/external changes involving contracts, retries, idempotency, authentication, or reconciliation. Skip isolated work with no integration edge.

`analysis-agent`/`task-agent`/`review-agent`: use when uploads, object storage, streaming, MIME, scanning, access, retention, or cleanup changes; skip without file/storage impact.

`analysis-agent`/`task-agent`/`review-agent`: use when repeated failure needs a new hypothesis or proof path; skip an initial failure with verified cause and a different action.

`analysis-agent`: use when raw requests need behavior, actors, scope, non-goals, constraints, deliverables, acceptance, or test traceability; skip when structure already exists.

`task-agent`: use when local, server, global, derived, optimistic, persisted, form, auth, or cache state ownership changes; skip when state boundaries are unaffected.

`analysis-agent`/`task-agent`/`review-agent`: use when behavior needs deterministic seams for time, randomness, UUIDs, collaborators, or external I/O; skip when seams are adequate.

Use with analysis-agent or task-agent for task-local transaction, isolation, and conflict decisions. Do not use without a transaction decision or as task owner.

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

Expert in designing effective prompts for LLM-powered applications. Masters prompt structure, context management, output formatting, and prompt evaluation. Use when: prompt engineering, system prompt, few-shot, chain of thought, prompt design.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.