This skill should be used when the user asks to "write a readme", "create readme", "generate readme", "improve readme", "audit readme", "review readme", "fix readme", "readme best practices", "readme standard", "perfect readme", or mentions README quality, documentation standards, or developer experience documentation.
/plugin marketplace add hculap/better-code/plugin install readme-writer@better-codeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/audit-checklist.mdreferences/codebase-analysis.mdProduct-Ready Documentation README standard for creating documentation that reliably produces correct adoption decisions, fast first success, low support burden, sustained trust, and low drift.
A README is "perfect" when it achieves:
Follow these steps in order when creating or improving a README.
Before writing any README content, define these three lines:
Primary user: [e.g., "Python developer who wants an HTTP client library"]
Primary job: [e.g., "install → call API → handle auth"]
Success in 5 minutes: [e.g., "send one request and see JSON response"]
Failure to define these results in either a manifesto or an API dump.
Goal: 15-30 seconds to decide whether to continue reading.
Include in this exact order:
# ProjectNameStatus: active | beta | stable | deprecated | unmaintainedRules:
Goal: First working result in under 5 minutes (TTFS - Time To First Success).
Quickstart must contain:
Quality bar: A brand-new user copies and pastes commands with zero edits. If secrets required, point to .env.example with minimum required variables.
Goal: Enable meaningful use beyond hello-world.
For each workflow include:
Structure:
Goal: Keep README readable and maintainable.
README includes only the 80/20 (most common paths). Move deep details to:
/docs/*CONFIGURATION.mdARCHITECTURE.mdAPI.mdLink to these clearly from README.
If accepting contributions:
CONTRIBUTING.mdIf not accepting contributions:
Answer these questions:
Make non-ambiguous:
LICENSESECURITY.md or provide reporting instructionsMandatory for production adoption in organizations.
Apply these checks:
Treat README like code with automation:
Minimum: Monthly README validation workflow or validation on each release.
Use this skeleton unless there's a strong reason not to:
# Title
One-line value proposition
Status: [status] | [Docs](link) | [Releases](link) | [Support](link)

## Why / Motivation (short)
## Quickstart
### Prerequisites
### Install
### Run
### Expected Result
## Usage
### Common Workflow 1
### Common Workflow 2
## Configuration
## Troubleshooting / FAQ
## Roadmap (optional)
## Contributing
## Support
## Security
## License
## Maintainers / Credits
Run these 10 checks against any README. All must pass for "perfect" status:
| # | Test | Pass Criteria |
|---|---|---|
| 1 | What is it? | New user answers in 10 seconds |
| 2 | Is it maintained? | New user answers in 10 seconds |
| 3 | Quickstart works | Works on clean machine in ≤5 minutes |
| 4 | Runnable example | At least one exists and is copy/pasteable |
| 5 | Expected output | Shown or described |
| 6 | Navigation | Find Install/Usage/Support via headings in ≤10 seconds |
| 7 | License | Explicit and linked |
| 8 | Contribution route | Clear (even if "not accepting") |
| 9 | Accessibility | Images have alt text, headings hierarchical |
| 10 | Scope | Doesn't try to be entire manual; deep info linked |
For detailed guidance on specific aspects:
references/codebase-analysis.md - How to analyze a codebase to auto-detect target reader and job-to-be-donereferences/audit-checklist.md - Detailed audit procedure with scoringFor README generation:
For README auditing:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.