Kappaemme-git
codex-first-customer-finder-skill
A Codex skill that converts a startup URL or product idea into a qualified shortlist of potential first customers by analyzing public pain, demand, and timing signals.
Why it is worth attention
It addresses the common problem of unclear READMEs by moving proof before jargon, separating visual identity (SVG) from usable Markdown, and already powering four public repositories with distinct visual languages.
Who it is for
- Open-source maintainers wanting clearer landing pages
- Developers who create frequent README updates
- Project authors seeking consistent visual identity across repos
- AI agent users who want automated but safe README improvements
Use cases
- Redesign an entire README around the project's real value and proof
- Generate only visual assets (SVG hero, diagrams, motion) without modifying text
- Run a read-only audit for clarity, hierarchy, trust, and maintenance cost
- Create a project-native hero that derives typography, color, and composition from the project itself
Strengths
- Already used by four public repositories with different visual identities (oil-ppt, draw-ui, oil-icon, Selector, torqueDASH-Next)
- Separates visual layer (SVG) from content (Markdown) so the README remains searchable and maintainable
- Provides explicit whole-README and asset-only modes with local previews and no automatic commits
- Includes a read-only audit feature that does not edit any files
Considerations
- Requires installing a Skill via npx or an agent, adding a setup step
- Output quality depends on the richness of the project's existing material—bare-minimum repos may yield limited improvements
- The method emphasizes design decisions that may need iterative feedback when the project lacks clear identity
README quick start
English · 简体中文
These are not hypothetical templates. The method is already used by four public repositories, each with its own visual language and content structure:
- oil-ppt — presents the method, results, and first-use path for programmatic slide creation in one visual system.
- draw-ui — uses real UI outputs to explain the path from a brief and reference images to HTML/CSS reconstruction.
- oil-icon — uses real icon sets to explain style locking, batch generation, slicing, and transparent delivery.
- Selector — puts page selection, structured context, and real output directly into the opening screen and examples.
- torqueDASH-Next — uses a project-native SVG hero with OBD-II PID data and a real dashboard screenshot to explain a self-hosted vehicle telemetry dashboard.
If this Skill helped you create a public README you are proud of, you are welcome to propose it for this list in a PR. This is completely optional: the footer signature is appreciated but never required, and showcase submissions remain subject to maintainer review.
Below are four independent hero directions. They do not share one house style; each derives its typography, color, composition, and proof from the project itself.
Most repositories already contain enough information. The problem is usually the order: visitors see internal terminology, installation commands, and directory trees before they understand what the project is for.
beautify-github-readme reads the real repository first, identifies the clearest value and proof, and only then decides how the page should look.
In whole-README mode, it works across three layers:
| Content | Visual system | Engineering |
|---|---|---|
| Remove repetition, move proof forward, and replace internal jargon with concrete outcomes | Derive color, typography, composition, and project-native motifs before designing the hero and supporting modules | Keep assets GitHub-safe, images accessible, commands copyable, and body text searchable |
Different projects should not receive the same template. A CLI can use command rhythm and cursors; an icon system can use keyline
Description
Design clear, theme-specific GitHub README homepages with SVG titles, real proof, and maintainable Markdown
Related repositories
Similar projects matched by category, topics, and programming language.
NousResearch
Featured
hermes-agent
Hermes Agent is an open-source, self-improving AI agent with a built-in learning loop that creates skills from experience, runs across platforms, and supports any LLM provider.
littledivy
Featured
mimic
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.