All skills

Writes and refines a repository's README.md in a concise, Nuxt-inspired documentation style: sections chosen from what the repository actually contains, scannable feature bullets, emoji-anchored headings, and a banner, badges, and docs links only when the repository provides them. Use this skill when the user wants a README created, rewritten, restructured, tightened, polished, or brought up to date after the code changed, when they want a project's front page documentation improved or made consistent with their other repositories, or when they point you at a repo and ask what its README should say, even if they never use the word "README". Applies to repositories in any language or framework. Do not use it for changelogs, release notes, API reference, contributing guides, standalone documentation pages, or marketing copy.

Use this Skill: https://skilld.dev/gh/jonathanxdr/nuxt-style-readme-skill/nuxt-style-readme

This session only. Nothing lands on disk.

evalsfilessortmergeREADME.md

≈285 tokens on demand. Your agent reads this file only when SKILL.md points to it.

sortmerge

External merge sort for files that do not fit in memory.

Features

  • 🧮 Bounded memory: Sorts a file of any size inside a chunk budget you set.
  • 🧵 Streaming API: Reads and writes as streams, so nothing is buffered whole.
  • 🔤 Custom comparators: Any comparator that works with Array.sort works here.
  • 🧹 Self-cleaning: Temporary runs are removed even when the process throws.

🚀 Quick Start

npm install sortmerge

💻 Usage

import { sortFile } from 'sortmerge';

await sortFile('big.csv', 'sorted.csv', { chunkBytes: 64 * 1024 * 1024 });

⚙️ Configuration

Option Default Effect
chunkBytes 67108864 Memory budget for each in-memory run
tmpDir os.tmpdir() Where intermediate runs are written
comparator lexicographic Ordering function applied to each line

🛠️ Development

npm test        # run the test suite
npm run build   # bundle src/ into dist/
npm run lint    # ESLint

⚖️ License

Licensed under the MIT license © Example Author.

Source: SKILL.md on GitHub

1 warning17d3 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    The skill provides a structured workflow and style guide for generating high-quality README files by analyzing repository content. No malicious patterns were found; however, the skill naturally possesses an indirect prompt injection surface as it is designed to ingest and summarize untrusted repository data.

  • Socket17d

    2 alerts: gptAnomaly

  • Snyk17d

    Risk: LOW · No issues

Signed by skilld at dcc1591. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Activeupdated 2 months ago
metadata
{
  "version": "1.5.0"
}

README badge

README badge for jonathanxdr/nuxt-style-readme-skill