Index of every page on this site: llms.txt
All skills
elithrar avatar

/create-readme

@eb4f994
by Matt Silverlockelithrar/dotfiles226 stars
16
Run it yourself

Write or improve concise, reader-focused README.md files for open source projects. Use for new READMEs, README rewrites, installation and usage examples, or README reviews. Do not use for API references, tutorials, changelogs, contributing guides, or unrelated prose editing.

Use this Skill: https://skilld.dev/gh/elithrar/dotfiles/create-readme

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈73 tokens for metadata: the name and description. ≈668 when used: this file.

Description uses 3.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈291 characters, or 3.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Create README

Write a README that tells prospective users what the project does, why it is useful, and how to reach a working result.

Workflow

  1. Inspect the existing README, manifests, public APIs, examples, tests, release metadata, and license as relevant.
  2. Identify the intended reader, the problem the project solves, its shortest useful workflow, and any adoption-critical limits or tradeoffs.
  3. Choose only the sections the project needs. A typical order is: project name, direct introduction, key capabilities, installation, a minimal example, advanced workflows or design notes, contributing, and license.
  4. Write the smallest realistic example first. Use actual commands, package names, APIs, and configuration from the repository. Add specialized examples only when they answer a likely next question.
  5. Verify changeable claims, commands, links, supported versions, and examples. Run the smallest safe example or relevant check when feasible, and report anything that remains unverified.

House Style

Use the house-style principles below. Consult these examples only when a requested style match needs more context: elithrar/ask-bonk, elithrar/simple-scrypt, elithrar/fuse-on-r2, and especially gorilla/csrf.

  • Explain usefulness before setup. Name concrete outcomes and use cases instead of calling the project powerful, robust, or easy.
  • Move quickly from context to installation and a working example.
  • Introduce examples with what they demonstrate. Progress from the common case to meaningful variants.
  • Put security warnings, operational caveats, and tradeoffs beside the example or claim they qualify.
  • Use design notes when they help readers trust an important implementation choice.
  • Keep the structure proportional to the project. A demo may need only context, tradeoffs, deployment, and links. A mature library may need compatibility, several examples, and design rationale.
  • Use concise, direct American English with a conversational technical tone. Keep mild personality when it is natural.
  • Preserve the author's terminology and voice. Avoid marketing language, filler, repetition, and sections added only by convention.

Never invent features, commands, support, performance, or maturity. If the project's purpose or audience cannot be established from available evidence, ask one focused question.

For an audit-only request, report prioritized findings without editing. For a create, rewrite, or fix request, update the README and preserve unrelated files.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill is generally safe but possesses an indirect prompt injection surface as it is designed to inspect and execute examples from untrusted project repositories.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at eb4f994. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 3 months ago

README badge

README badge for elithrar/dotfiles/create-readme