update-readme

Analyze the codebase and regenerate README.md to reflect current project structure, commands, skills, MCP servers, and configuration. Use after code changes, new features, or when README is stale.

ranjankumarpatel/claude-code-multi-model1 installsApache-2.0Synced Aug 26

Works with

Claude CodeCursorCodex CLIGitHub CopilotGemini CLI
---
name: update-readme
description: Analyze the codebase and regenerate README.md to reflect current project structure, commands, skills, MCP servers, and configuration. Use after code changes, new features, or when README is stale.
license: Apache-2.0
---

# Update README

Analyze the current codebase and update README.md to accurately reflect the project state.

## Target README

- If `$ARGUMENTS` specifies a path, update that README
- Otherwise update `plugins/multi-model/README.md` (primary plugin README)

## Analysis Steps

1. **Scan project structure** — use Glob to map directories, key files, scripts, configs
2. **Inventory commands** — read all files in `commands/` directories, extract slash command names and descriptions
3. **Inventory skills** — read SKILL.md files in `skills/` directories, extract name and description
4. **Inventory MCP servers** — read plugin.json manifests for bundled MCP server declarations
5. **Check requirements** — scan scripts for environment variables, dependencies, imports
6. **Read current README** — compare existing content against discovered state
7. **Diff analysis** — identify what's new, changed, or removed since last README update

## README Structure

Generate/update README with these sections (preserve any custom sections the user added):

```markdown
# {project-name}

{one-line description}

## Install
{installation instructions}

## Requirements
{dependencies, env vars, prerequisites}

## Commands
{table or list of all slash commands with descriptions}

## Skills
{list of skills with trigger descriptions}

## MCP Servers
{bundled servers and what they provide}

## Configuration
{key settings, env vars, optional features}
```

## Rules

- **Preserve custom content** — if the user added sections not in the template above, keep them
- **Be concise** — one line per command/skill, no verbose explanations
- **Use tables** for commands and models when there are 4+ entries
- **Show actual values** — real command names, real env var names, real model IDs
- **No stale references** — if a file/command/skill no longer exists, remove it from README
- **No aspirational content** — only document what exists now, not planned features

More Writing & Documentation skills

paper-context-resolver

lllllllama/rigorpilot-skills

Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.

450.8k

repo-intake-and-plan

lllllllama/rigorpilot-skills

Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.

450.0k

minimal-run-and-audit

lllllllama/rigorpilot-skills

Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

449.9k

← All Writing & Documentation skills

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY