Compare multiple alternatives using explicit criteria, weighted scoring, and tradeoff analysis. Use when choosing between options, evaluating alternatives, or making decisions.

Reviews WidgetKit code for timeline management, view composition, configurable intents, and performance. Use when reviewing code with import WidgetKit, TimelineProvider, Widget protocol, or @main...

General principles for structured content modeling that apply across CMSs, with Sanity-specific guidance. Use when designing content schemas, planning content architecture, or evaluating content...

Quantify values with uncertainty bounds. Use when estimating metrics, calculating risk scores, assessing magnitude, or measuring any quantifiable property.

Convert data between formats, schemas, or representations with explicit loss accounting and validation. Use when reformatting data, mapping between schemas, normalizing inputs, or translating structures.

Create or update root and nested AGENTS.md files that document scoped conventions, monorepo module maps, cross-domain workflows, and (optionally) per-module feature maps (feature -> paths,...

Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.

Execute the Debug Code Change workflow end-to-end with safety gates. Use when debugging code changes, investigating issues, or performing root cause analysis with audit trail.

Install a pre-commit hook that scans .specstory/history for secrets before commits. Run when user says "set up secret scanning", "install specstory guard", "protect my history", or "check for secrets".

Frontend-specific technical decision criteria, anti-patterns, debugging techniques, and quality check workflow. Use when making frontend technical decisions or performing quality assurance.

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.

Reviews Swift Testing code for proper use of #expect/#require, parameterized tests, async testing, and organization. Use when reviewing .swift files with import Testing, @Test, #expect, @Suite, or...

Watch and report current state of a target system, process, or entity. Use when monitoring status, inspecting live systems, checking current conditions, or observing runtime behavior.

Fetch known facts or data from specified sources with citations and evidence pointers. Use when you know what you need and where to find it. Emphasizes provenance and verifiable references.

Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.

Agentic MCP - Three-layer progressive disclosure for MCP servers with Socket daemon. Use when the user needs to interact with MCP servers, query available tools, call MCP tools, or manage the MCP...

Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or creating multi-agent...

Write stable learnings, decisions, and patterns to durable storage like CLAUDE.md or knowledge files. Use when saving project decisions, recording patterns, or updating long-term memory.

Create a safety checkpoint marker before mutation or execution steps. Use when about to modify files, execute plans, or perform any irreversible action. Essential for the CAVR pattern.

Extract architectural decisions from conversations. Identifies problem-solution pairs, trade-off discussions, and explicit choices. Use when analyzing session transcripts for ADR generation.