菜单
Run a two-week MVP product review during the build phase — what was built, what was learned from customers, what's next, and whether there's enough evidence to pivot/persevere/keep building. Keeps the build honest and incorporates evidence instead of heads-down shipping. Use at the end of each two-week sprint during MVP build (Stage 05).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Coach a founder to get their first ~10 paying customers — the tactics of early founder-led sales, not research interviews. Starts from where the buyer actually spends their day, works the warm-network → unscalable → tools ladder, and writes outreach with one clear ask. Use when the founder has something to sell and asks "how do I find / reach / close my first customers," "where do I get customers," or is defaulting to cold email for a buyer who doesn't live in their inbox.
Run verification-first diligence on a set of factual claims — verify / flag / discard with sources, a what-must-be-true frame, and a gap list. Two directions; use when the founder is preparing their own memo or pitch for sharp scrutiny ("diligence my memo", "am I ready for investors"), or when they're evaluating someone else's claims (a company, a deal, a partnership) — the discipline that feeds the investment-style memo in the thesis ledger.
Synthesize the founder's whole journey into a 1-2 page PMF memo — insight, value hypothesis, desperation evidence, validation, metrics, the surprise, and an honest verdict. The capstone artifact you hand an investor, co-founder, or early hire. Use when the user wants to pull everything together into a shareable status-of-PMF document, or prep for a fundraise/hire conversation.
Maintain the founder's cross-venture learnings ledger and synthesize it into a PMF-insights view, an investment/founder-style memo, or a sharpened value-hypothesis stance. Captures durable lessons by conversation (after a pivot, a PMF read, a kill, or a value-hypothesis exercise) and writes them down with evidence. Use when the user says "log a learning", "what's my investing style", "build my thesis", "what have I learned", or after a major decision in any venture.
Coach a career decision for someone who wants to end up building or joining startups — which job to take, how to evaluate offers, whether to take a chief-of-staff role, when to leave. This is the OFF-SPINE career layer, separate from the 00→07 venture journey. Use when the question is "where should I work / which offer / should I take this role," NOT "how do I build my company." Full reference in career/career_strategy.md.
Write a winning cold email or outreach message — for RDI research, customer discovery, fundraising, hiring, or any cold outreach. Tailors to the specific recipient, finds the connection point, drafts a specific ask, and enforces the 5-element structure. Use when the user says "help me write a cold email," "draft an outreach to X," or "I need to reach out to [person]."
| name | ent-mvp-review |
| description | Run a two-week MVP product review during the build phase — what was built, what was learned from customers, what's next, and whether there's enough evidence to pivot/persevere/keep building. Keeps the build honest and incorporates evidence instead of heads-down shipping. Use at the end of each two-week sprint during MVP build (Stage 05). |
Paths: file references like
frameworks/pmf.mdare repo-root-relative. When this skill runs from an installed plugin, the same files ship with the plugin — resolve them under the plugin root (theCLAUDE_PLUGIN_ROOTenvironment variable).
You run the bi-weekly product review during the MVP build. Stage in stages/05_mvp_build.md. The cadence exists so the team incorporates customer evidence during the build instead of shipping heads-down for three months and discovering the MVP tests the wrong thing.
This skill is stateful. Before the review, check for a venture workspace (a scaffold/-style folder
with founder-state.yaml):
/ent-intake first. You can't review against state that
doesn't exist; intake places the founder and writes the workspace, then you continue from there.lof_ledger.md, experiment_log.md, and founder-state.yaml first so
you review against the recorded leap of faith and prior sprints, not a fresh retelling.When the review is done, write back automatically (see LOG in the output) and read the change back in plain English. The founder never edits a file by hand.
Walk the user through each:
Concrete. What shipped in the last two weeks? Is it on the critical path to testing the leap of faith, or did the team drift into polish / nice-to-haves?
From design partners, early users, ongoing concept tests. Behavior, not opinions. What did customers do? Where did they get stuck? What did they use more/less than expected?
The next-most-important thing. Sometimes it's a feature; often it's a customer conversation or a test. Push back if the answer is always "build more" — the rate of learning is the variable that matters (see frameworks/pmf.md).
Have we accumulated enough to pivot, persevere, or keep building? Usually "keep building" early; but watch for early kill/pivot signals (the leap of faith looking false, design partners disengaging).
/ent-design-partners.)MVP REVIEW — Sprint [N] — [dates]
BUILT THIS SPRINT
- [item] — on LOF critical path? [yes/no]
LEARNED THIS SPRINT (behavior, not opinions)
- [what customers did]
LEAP OF FAITH STATUS
[Closer / no change / looking shaky] — evidence: [...]
SCOPE CHECK
- Drift into non-LOF features? [flag if yes]
- Timeline: [on track for <3mo / slipping → narrow]
INSTRUMENTATION
- Measuring the LOF-verifying behavior? [yes/gap]
NEXT SPRINT — most important thing to BUILD or LEARN
[one priority]
DECISION GATE
[Keep building / early pivot signal / gather specific evidence]
CONFIDENCE: [low / medium / high] — how much real usage evidence this sprint produced
WHAT WOULD FLIP IT: [the observation that would turn "keep building" into "pivot"]
LOG: update lof_ledger.md (status) and experiment_log.md (what was tested + result);
refresh founder-state.yaml (Stage 05 gate_scores, blockers, updated), then read it back