github-readme-overhaul
Use when writing, rewriting, branding, visually overhauling, or optimizing a GitHub README.md for installs, downloads, stars, marketplace conversion, OSS…
Skill by joeblackwaslike
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/joeblackwaslike-github-readme-overhaul
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/github-readme-overhaul
What's inside
- Skill name
github-readme-overhaul- Description
- Use when writing, rewriting, branding, visually overhauling, or optimizing a GitHub README.md for installs, downloads, stars, marketplace conversion, OSS adoption, or immediate product value, including badges, hero graphics, tagline, pain-point messaging, quickstart, terminal demos, screenshots, GIFs/videos, and README-native visual assets.
- License
- MIT
- Metadata
- last_updated: 2026-05-26
- Instructions
- 156 lines in SKILL.md · view on GitHub
Files (9)
- SKILL.md
- openai.yaml · agents/
- badges.md · references/
- copy-patterns.md · references/
- infographics.md · references/
- quality-gate.md · references/
- strategy.md · references/
- terminal-demo.md · references/
- visual-system.md · references/
SKILL.md (first lines)
# GitHub README Overhaul Turn a README into a GitHub-native conversion surface: visitors should understand the pain, see the fix, trust the proof, and know how to install within the first screen. ## Core Behavior When the user asks for a compelling README, the agent should rewrite the README as a branded mini case study with clear install intent, infographic-level visual proof, and tight copy, even if the user says "landing page," "viral," or "pull out all the stops." Borrow landing-page strategy, but do not create a fake website inside Markdown or walls of text. ## Required Inputs Inspect the repo before writing: 1. Existing `README.md`, package metadata, manifests, screenshots, docs, examples, CI, releases, and install paths. 2. Product category: CLI, library, app, extension, agent skill, MCP server, GitHub Action, plugin, template, SaaS, or internal tool. 3. Real proof: terminal demo video/GIF, screenshot, terminal output, benchmark, before/after, testimonials, stars/downloads, examples, supported platforms. 4. Install path: one command, marketplace link, package manager, Docker, browser extension store, VS Code Marketplace, Claude plugin install, GitHub template, or hosted URL. If proof is missing, create a placeholder task or asset brief, but do not invent metrics. ## Above-the-Fold Formula Use this order unless the repo strongly suggests a better one: 1. Logo or compact wordmark if available. 2. H1 with product name. 3. Tagline that names the painful job and the promised outcome. 4. Badge row with only meaningful, maintained badges. 5. Hero proof: terminal demo, screenshot, terminal panel, flow diagram, benchmark chart, or before/after graphic. 6. One-line install or primary CTA. 7. Three concrete value bullets. The first screen should answer: "What is this, why do I care, can I trust it, and how do I try it?" ## Reference Router Read only what the task needs: | File | When to Read | | --- | --- | | `references/strategy.md` | README narrative, conversion structure, viral/adoption mechanics | | `references/badges.md` | Badge selection, ordering, sources, and anti-spam rules | | `references/visual-system.md` | Hero graphics, screenshots, diagrams, GitHub rendering constraints | | `references/infographics.md` | Compelling README infographics, proof graphics, and visual density rules | | `references/terminal-demo.md` | Terminal demo video/GIF planning, recording, scripting, export, and embedding | | `references/copy-patterns.md` | Taglines, pain-point framing, CTAs, section copy patterns | | `references/quality-gate.md` | Final review checklist and failure modes | ## README Structure Default section order: ```markdown <brand/logo> # Product Name > Pain-point tagline with outcome. <badge row> <hero proof visual> <install command or marketplace CTA> ## Why this exists ## See it work ## Install ## Quick start ## What you get ## Examples ## How it works ## Configuration ## Comparisons / tradeoffs ## Roadmap ## Contributing ## License ``` Collapse or reorder sections when the product needs a simpler path. For libraries, quickstart moves higher. For visual tools, screenshots move higher. For developer tools, terminal proof moves higher. ## Visual Rules - Design for GitHub Markdown rendering, dark/light mode, mobile width, and skim reading. - Prefer a sequence of strong proof visuals over long explanatory sections. - Use actual product UI, terminal output, diagrams, or screenshots when possible. - For CLI/dev tools, strongly consider a short terminal demo as the hero proof. - For complex developer tools, use infographic blocks like before/after, architecture, savings, workflow, and supported surfaces. - Store assets under `assets/readme/` or the repo's existing docs asset folder. - Use Mermaid for maintainable diagrams when it fits. - Use SVG/PNG only when visual polish matters or Mermaid is too limited. - For generated visuals, prompt for "GitHub README documentation graphic, not a website." Do not add nav bars, pricing cards, fake CTA buttons, huge landing-page sections, or marketing graphics that do not explain the product. ## Copy Density Rules - Replace paragraphs with labeled visuals, short callouts, tables, and examples. - Keep each section to one job: pain, proof, install, example, or detail. - Lead sections with the sharpest claim, then prove it visually. - Prefer one memorable sentence over three explanatory paragraphs. - If a README already looks visually strong, improve wording, ordering, and proof clarity without flattening the visual system. ## Badge Rules Use badges as trust signals, not decoration. Prefer: - package version/downloads - CI/build - test coverage only if true and maintained - license - marketplace/version/install count - docs - supported runtime/platform - security/audit status when real Avoid badge soup. Five to eight strong badges usually beat twenty weak ones. ## Viral / Adoption Mechanics
From joeblackwaslike/agent-skills, MIT.
More from joeblackwaslike/agent-skills
- 0.592score
developing-for-github
joeblackwaslike
Use when building software that integrates with GitHub — GitHub Apps, OAuth apps, webhook consumers, bots, CI checks, and automation built on the GitHub API.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
beads-operations
joeblackwaslike
Use when running, maintaining, or troubleshooting beads (`bd`) day-to-day — deciding bd vs TodoWrite, Joe's shared-server conventions (`bd init…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
docusaurus-docs-builder
joeblackwaslike
Use when creating, redesigning, rewriting, or improving a Docusaurus documentation site, docs portal, developer docs, product docs, API docs, guide site…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
devcontainers
joeblackwaslike
Use when building, modifying, using, or distributing Dev Containers — creating or editing devcontainer.json from scratch, adding devcontainer features…
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
recovering-session-context
joeblackwaslike
Reconstruct what happened in prior agent sessions from their transcripts and surface everything raised but never resolved — unanswered questions, work…
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
best-practices-for-agentic-development
joeblackwaslike
Use when designing, building, reviewing, testing, or improving agents, agentic workflows, agent skills, MCP servers, tool interfaces, subagent systems, or…
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
authoring-agent-skills
joeblackwaslike
Use when creating, adding, or maintaining a skill in this agent-skills repo — especially a "working-with-X" skill that wraps external/official docs by…
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
agent-instructions
joeblackwaslike
Use whenever creating OR editing CLAUDE.md, AGENTS.md, GEMINI.md, a SKILL.md, or any other file whose job is to instruct an AI coding agent, at any scope…
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
autonomous-agent-operations
joeblackwaslike
Use when operating solo on a task handed off without the user available for interactive check-ins — ask every clarifying question up front, decide and file a…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
senior-engineering-best-practices
joeblackwaslike
Use in any development session that benefits from a senior engineer's accumulated judgment, methodology, and runbooks — broader than any single category, most…
SkillBFreshness: B★ 1Claude Code +9 - 0.540score
git-github-workflows
joeblackwaslike
Git and GitHub workflow router.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
domain-driven-design
joeblackwaslike
Use when modeling a business domain or structuring a backend around business rules — designing aggregates, entities, value objects, domain events…
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 10, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/joeblackwaslike/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from joeblackwaslike
- 0.592score
developing-for-github
joeblackwaslike
Use when building software that integrates with GitHub — GitHub Apps, OAuth apps, webhook consumers, bots, CI checks, and automation built on the GitHub API.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
docusaurus-docs-builder
joeblackwaslike
Use when creating, redesigning, rewriting, or improving a Docusaurus documentation site, docs portal, developer docs, product docs, API docs, guide site…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
beads-operations
joeblackwaslike
Use when running, maintaining, or troubleshooting beads (`bd`) day-to-day — deciding bd vs TodoWrite, Joe's shared-server conventions (`bd init…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
devcontainers
joeblackwaslike
Use when building, modifying, using, or distributing Dev Containers — creating or editing devcontainer.json from scratch, adding devcontainer features…
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
recovering-session-context
joeblackwaslike
Reconstruct what happened in prior agent sessions from their transcripts and surface everything raised but never resolved — unanswered questions, work…
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
best-practices-for-agentic-development
joeblackwaslike
Use when designing, building, reviewing, testing, or improving agents, agentic workflows, agent skills, MCP servers, tool interfaces, subagent systems, or…
SkillBFreshness: B★ 1Claude Code +9
Cite this page
github-readme-overhaul skill. Agent Mart. https://agentmart.dev/skills/joeblackwaslike-github-readme-overhaul (last updated 2026-10-24)