Skip to content
Agentmart
Submit a tool

readme-optimization

Optimize README and public-facing content for GitHub discoverability, clear presentation flow, and accurate feature positioning

Skill by reshinto

IndexedMIT
Write a review

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/reshinto-readme-optimization

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.

We use your email only for this newsletter. Privacy

About

Optimize README and public-facing content for GitHub discoverability, clear presentation flow, and accurate feature positioning

Use cases: presentations, writing

No 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/readme-optimization

What's inside

Skill name
readme-optimization
Description
Optimize README and public-facing content for GitHub discoverability, clear presentation flow, and accurate feature positioning
License
MIT
Instructions
69 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# README Optimization

## Task

Review and optimize the README.md and repository metadata for discoverability, clear value communication, and accurate feature presentation.

## Instructions

1. Read the current README.md and repository description
2. Evaluate against each area below
3. Suggest specific copy improvements with before/after examples

## Review Areas

### First Impression (Above the Fold)

- Value proposition clear in the first 3 lines: what the project is and who it's for
- Demo visual present (screenshot or GIF showing the project in action)
- Key differentiators immediately visible
- Quick Start commands visible without scrolling on desktop

### GitHub Search Optimization

- Repository description includes the most important searchable terms for the project's domain
- Topics include relevant technology tags (e.g., framework names, domain keywords)
- README headings match common search queries users would type to find this project
- Feature and concept names match how the target audience searches for them

### Content Hierarchy

- **Primary audience first**: Core features and usage before technical implementation details
- **Secondary audience second**: Integration, customization, and advanced usage
- **Contributors third**: Architecture overview, contributing guide links
- Progressive detail: summaries with links to `docs/` for deep dives

### AIDA Presentation Flow

- **Attention**: Visual demo (GIF/screenshot) showing the project
- **Interest**: Feature bullet list highlighting what makes the project unique
- **Desire**: Concrete examples or table showing the breadth of what the project provides
- **Action**: Quick Start with copy-pasteable commands

### Accuracy

- All listed features and capabilities actually exist in the codebase
- Scripts/commands table matches project manifest (e.g., `package.json`, `Makefile`, `pyproject.toml`)
- Any listed keyboard shortcuts or CLI flags match the actual implementation
- Technology versions match the project manifest

### Developer Friendliness

- Quick Start works on fresh clone (no hidden prerequisites)
- Links to detailed docs are not broken
- No marketing language that obscures technical content

## Rules

- No superlatives or hype — let features speak for themselves
- All claims must be verifiable from the codebase
- No references to AI, Claude, or automated generation
- Keep README scannable — prefer tables and bullets over prose

## Output Format

- EFFECTIVE: [area] - what works well and why
- OPTIMIZE: [area] - specific improvement with suggested copy
- GAP: [area] - missing content + draft to fill it

From reshinto/dev-forge, MIT.

More from reshinto/dev-forge

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 8, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from reshinto

Cite this page

readme-optimization skill. Agent Mart. https://agentmart.dev/skills/reshinto-readme-optimization (last updated 2026-10-24)