AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Ship It Mvp

skill-nanfei892-ship-it-skills-ship-it-mvp · by nanfei892

Turn a rough product or app idea into a build-ready MVP blueprint: a focused product brief, scope, user flow, acceptance criteria, architecture recommendation, and dependency-ordered implementation plan. Use when a user says 'build my idea', asks for an MVP, PRD, product requirements, product spec, app scope, feature breakdown, user flow, acceptance tests, launch plan, or needs to make a vague so…

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-nanfei892-ship-it-skills-ship-it-mvp

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-nanfei892-ship-it-skills-ship-it-mvp)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
9d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ship It Mvp? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Ship It: MVP Blueprint

Create a decision-ready blueprint before writing code. Optimize for a small first release that proves one valuable user outcome, not for feature completeness.

Intake

Extract these facts from the request, repository, and supplied material:

  • target user and the moment they need help
  • painful job-to-be-done and desired end state
  • platform, constraints, integrations, deadline, and existing assets
  • evidence of success and the riskiest unknown

Ask at most three decisive questions only when an answer would materially change the MVP. Otherwise proceed with a short Assumptions section. Do not invent customer research, legal compliance, pricing, technical constraints, or integrations.

Scope the MVP

Define exactly one primary user, one core job, and one end-to-end happy path. Include no more than three supporting capabilities unless the user explicitly requires more.

Classify every requested capability:

| Class | Meaning | | --- | --- | | Now | Required for the primary journey to reach its done state. | | Next | Valuable after the first user outcome has been proven. | | Not now | Deliberately excluded; name the reason or trigger for reconsidering it. |

Prefer a reversible local implementation when an external service, account, API key, payment flow, or production infrastructure is not already available. Surface the biggest risk early with a low-cost validation step.

Deliver the Blueprint

Use these headings in order. Keep language concrete enough that a designer or engineer can begin work without a follow-up meeting.

# [Product] MVP Blueprint

## Outcome
- **Primary user:**
- **Job:** When ..., I want to ..., so I can ...
- **Success signal:**

## Assumptions
- ...

## MVP Scope
| Now | Next | Not now |
| --- | --- | --- |
| ... | ... | ... |

## Core User Flow
1. ...
2. ...
3. ...

## Requirements and Acceptance Criteria
### [Capability]
- Requirement: ...
- Given ..., when ..., then ...
- Empty, loading, error, and permission states: ...

## Technical Shape
- **Recommended stack:**
- **Data entities:**
- **Interfaces/integrations:**
- **Security and privacy:** State only constraints supported by the brief; otherwise list open questions.

## Build Plan
1. [Milestone] - deliverable, dependencies, and proof it works.
2. ...

## Risks and Validation
| Risk | Cheapest validation | Decision after result |
| --- | --- | --- |
| ... | ... | ... |

Write acceptance criteria for every Now capability. Cover a successful result plus the state most likely to block that user. Define observable outcomes rather than implementation details.

Repository-Aware Work

When an existing codebase is in scope, inspect its project structure, package manifest, routing, data model, and tests before proposing a stack or plan. Preserve established conventions. Identify the narrowest files or modules likely to change, then map each build-plan item to them where possible.

When the user asks to implement immediately, present the blueprint briefly, state the assumptions that affect behavior, then build the first milestone. Keep Next and Not now work out of the implementation unless the user expands scope.

Optional Generator

Use scripts/make_mvp_blueprint.py when a reusable Markdown file is useful. Supply a JSON brief and generate a deterministic starter blueprint:

python scripts/make_mvp_blueprint.py --input brief.json --output mvp-blueprint.md

Use this input shape. now, next, and not_now may be empty arrays.

{
  "product_name": "DeskFocus",
  "primary_user": "Remote workers who lose track of deep-work sessions",
  "job": "start and finish one distraction-free work block",
  "success_signal": "A user completes a timed focus session",
  "assumptions": ["The first release is a browser app."],
  "now": ["Create a named session", "Run a timer", "Show completion"],
  "next": ["Weekly history"],
  "not_now": ["Team workspaces"],
  "flow": ["Name a session", "Start timer", "See completion"],
  "risks": [{"risk": "Users may not return", "validation": "Test with five target users", "decision": "Add history only if repeat use is observed"}]
}

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.