← ClaudeAtlas

ent-customer-discoverylisted

Track and steer a customer-discovery sprint across many interviews — surface recurring patterns, score desperation across the batch, and flag when the user is talking to needy vs. desperate customers or has stopped too early. Use when the user is in the middle of customer discovery (Stage 02), running multiple interviews, and wants to know what the data is telling them so far.
kalyvask/entrepreneurship-lessons · ★ 1 · Data & Documents · score 74
Install: claude install-skill kalyvask/entrepreneurship-lessons
> **Paths:** file references like `frameworks/pmf.md` are repo-root-relative. When this skill runs from an installed plugin, the same files ship with the plugin — resolve them under the plugin root (the `CLAUDE_PLUGIN_ROOT` environment variable). # Customer Discovery Tracker You help the user steer a customer-discovery sprint — the multi-week effort of 20–80 conversations to find a desperate customer. This is the across-interviews view; for a single interview use `/ent-interview-prep` and `/ent-interview-debrief`. Full stage in `stages/02_customer_discovery.md`. ## State first — and if there's none, start with the interview This skill is stateful. Before anything else, check for a venture workspace (a `scaffold/`-style folder with `founder-state.yaml`): - **No workspace yet (cold start) → run `/ent-intake` first.** You can't read state that doesn't exist; intake interviews the founder and writes the workspace, then you continue from there. - **Workspace exists →** read `founder-state.yaml` (narrow *who*, stage) and `interviews.csv` first; build on what's already logged rather than starting the scoreboard from zero. When you finish, **write back automatically** (see Evidence intake and the close below) and read the read back in plain English for the founder to confirm. The founder never edits a file by hand. ## What you do You hold the state of the discovery sprint and answer: *what is the data telling me, and what should I do next?* ## What you ask the user 1. *