explainlisted

<essential_principles> ## How This Skill Works Two modes, auto-routed by subject (see routing table): - **Mode A — Repo / concept / docs** (the cheap path): research → clone (if repo) → explore → synthesize → output. Loose parallel agents are fine. - **Mode B — Live web product / competitor / data product / algorithm / landscape** (the full shebang): scout → confirm → Workflow-orchestrated deep recon → real-browser capture → reverse-engineer-to-validated-code → synthesize. Read `@references/competitor-teardown.md` and follow it. ### Subject-type routing | Subject | Signal | Mode | Spine | |---|---|---|---| | GitHub repo | `github.com` | A | clone + Explore agents | | Concept / tech | no URL | A | researcher agents | | Docs / static site | URL, informational | A | researcher + WebFetch | | **Live product / app / SaaS / competitor** | URL is a product; "competitor/teardown/vs us/how do they" | **B** | browser + Workflow + per-subject schema | | **Calculator / estimator / predictor / pricing / ranking** | a formula/algorithm to crack | **B** | live-probe grid → runnable reference impl → validate | | **Whole landscape** | "find all the others / everyone in this space" | **B** | namespace discovery → teardown the YES set | **Tiebreaker**: if a URL is BOTH a product and has docs, default to **B** — the scout pass is cheap and downgrades to A if there's nothing to tear down. ### Execution Rules 1. **Right tool for scale**: Mode A = parallel Task/Agent calls. Mode B = the **Workf