-
Notifications
You must be signed in to change notification settings - Fork 27
Add before-you-build planning skill #5
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: master
Are you sure you want to change the base?
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
| @@ -0,0 +1,36 @@ | ||||||
| --- | ||||||
| name: before-you-build | ||||||
| description: Review a product idea or feature before implementation by identifying the biggest demand, positioning, monetization, retention, and distribution risks. Use when a senior developer or founder wants to build a new product, landing page, MVP, or major feature but needs a reality check first. | ||||||
|
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. The frontmatter description is quite long compared to other skills in the repository. Shortening it to focus on the core purpose and target audience will align it better with the existing style.
Suggested change
|
||||||
| --- | ||||||
|
|
||||||
| # Before You Build | ||||||
|
|
||||||
| ## Purpose | ||||||
| Pressure-test a product idea or feature before implementation starts. | ||||||
|
|
||||||
| ## Inputs to request | ||||||
| - Who the product or feature is for. | ||||||
| - The concrete situation where they would use it. | ||||||
| - The painful problem it solves. | ||||||
| - How people solve the problem today. | ||||||
| - Any existing signals: users, conversations, waitlists, revenue, usage, churn, or competitor evidence. | ||||||
|
|
||||||
| ## Workflow | ||||||
| 1. Restate the idea in one plain sentence. | ||||||
| 2. Identify the riskiest assumption that would make the project fail if false. | ||||||
| 3. Check demand, distribution, willingness to pay, positioning, retention, and trust risks. | ||||||
| 4. Separate weak evidence from stronger evidence. | ||||||
| 5. Recommend the smallest next validation step before building. | ||||||
|
|
||||||
| ## Output | ||||||
| - Short verdict: build, validate first, narrow the scope, or stop. | ||||||
| - Biggest risk with rationale. | ||||||
| - Evidence gaps. | ||||||
| - Specific next validation action. | ||||||
| - Optional kill criteria that would stop the project. | ||||||
|
|
||||||
| ## Quality bar | ||||||
| - Do not recommend tech stacks, architecture, or implementation details. | ||||||
| - Be direct and concrete, not motivational. | ||||||
| - Prefer one sharp risk over a long generic checklist. | ||||||
| - If the idea is too broad, ask who it is for, when they use it, and what painful problem it replaces. | ||||||
|
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Instructing the LLM to simply ask questions when an idea is too broad can lead to incomplete or unhelpful single-turn responses. It is better to have the LLM make reasonable assumptions to proceed with the analysis while explicitly listing the clarifying questions needed to validate those assumptions.
Suggested change
|
||||||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The description for the before-you-build skill is significantly longer than the other descriptions in this section, which are typically around 60 characters. Consider shortening it to maintain visual consistency and readability, for example: