Phase 2 - Clarify technical requirements from product specs. Requires product-adr.md as input. Outputs tech-adr.md. Use when running /technical-requirements, clarifying technical ADRs, or moving from product requirements to a fully-specified technical specification via research, approach selection, and 15 sequential categories.
Use when finding validated tiny iOS app ideas or explicitly validating a wedge for one opportunity from an existing App Tiny Bets report. Phase 1 performs keyword-first discovery with Astro and competitor evidence. Phase 2 runs only when explicitly requested with a report and one selected opportunity, then mines competitor reviews and creates a wedge brief.
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server — snapshot its accessibility tree, click/type/scroll by element_index or pixel coords, verify via re-snapshot, all without bringing the target to the foreground. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host.
Orchestrate and judge an issue-to-PR pipeline without editing artifacts directly. Use when the user wants an issue-to-PR workflow, task-to-PR pipeline, or structured path from request to PR readiness. Routes each stage to the owning skill or subagent, checks gate outputs, asks for revisions when the pipeline drifts, and keeps PR as a placeholder.
Review agentic system quality with a lean heuristic gate. Use when auditing, approving, improving, or quality-checking skills, agents, prompts, or agentic workflows and a verdict is needed.
Reusable verification gate for completed work before commit or merge. Use when implementation is done and Claude must prove the task works, verify the main user flow, route verification by platform, and return a PASS/FAIL/BLOCKED verdict with evidence. Web and mobile-web verification uses agent-browser. iOS and macOS verification uses xcodebuildmcp-cli.
Fresh-subagent code quality review gate after implementation and before verification. Use when code changes are complete and the orchestrator needs APPROVE_CODE, REVISE_CODE, or ASK_USER based on plan fidelity, simplicity, tests, repo style, security, and maintainability. Does not implement or write files.
Research first SOP before implementing any code change. Use when starting any task that involves modifying an existing codebase features bugs refactors open source contributions. Triggers when I want to work on X help me implement or fix or refactor X gather relevant context for X lets work on this. Launches parallel atlas subagents for local codebase evidence plus voyager external signal research, then presents 3 ranked approaches minimal diff first for user approval before any code is written.