Skip to content

Zeyad-101/Readme-writer-skill

readme-writer

Verified

Writes a production-quality README.md for any code repository, grounded entirely in the repo's real contents. Give it a repo link to clone, or paste/upload the repo's files, and it inventories manifests, CI config, build files, and code, works out what kind of project it actually is, and drafts a README using only the sections that project needs — no placeholder text, no invented badges or benchmarks, no boilerplate sections that don't apply. Works the same way regardless of language, stack, or project category. Use whenever asked to write, generate, or improve a README for a repo, or for a specific named project, in whatever wording that request takes.

FileKindSize
SKILL.mdskill md5.3 KB
assets/master-template.mdmarkdown21.8 KB
references/section-selection.mdmarkdown6.0 KB
references/writing-style.mdmarkdown2.8 KB

references/writing-style.md

View on GitHub
# Writing Style Rules

A README that reads like it was generated is worse than a rough one a human
wrote. Apply these when drafting, and again as a pass over the finished
draft.

## Ban list (don't write these unless the repo evidences the claim)
- Throat-clearing openers: "In today's fast-paced world...", "This project
  aims to...", "Welcome to..."
- Unearned superlatives: "blazing fast", "seamless", "robust", "powerful",
  "cutting-edge", "state-of-the-art", "enterprise-grade", "next-generation"
  — only usable if a real benchmark, spec, or design doc in the repo backs
  the specific claim, and then say the number instead of the adjective.
- Generic feature bullets that just restate the tech stack ("Built with
  modern technologies", "Easy to use and extend", "Highly customizable").
- Closing filler ("Happy coding!", "We hope you enjoy...", "Feel free to
  reach out with any questions!") unless the repo owner's own voice
  elsewhere in the repo does this.
- Padding a section to look complete: if there's one real config option,
  say the one; don't invent two more one comment.

## Positive rules
- Use the project's own names: real function/class/module names, real file
  paths, real command names — not paraphrases like "the main module" when
  the file is called `sensor_fusion.cpp`.
- Vary sentence openers across bullets. Don't start every line with
  "Provides..." / "Enables..." / "Supports...".
- Pull numbers from manifests and config, not estimates: dependency
  versions, supported language/runtime versions, actual measured values if
  present in code comments, benchmarks, or commit messages — never invented
  ones.
- Write for the audience implied by the repo: a firmware repo's README
  should read like an engineer who's flashed a board explaining it to
  another engineer, not a marketing one-pager.
- Badges: only add ones with real evidence — a CI badge only if a workflow
  file exists, a license badge only if a LICENSE file exists, a version
  badge only if there's a real version string (package.json/Cargo.toml/tag).
  No coverage/quality badges without a coverage tool actually configured.
- If the repo already has a README, don't copy its wording — read it for
  facts (real usage examples, real gotchas) worth carrying over, then write
  fresh. If it states something the new inventory can't verify, leave it
  out and don't silently invent a replacement.
- Prefer short, declarative sentences over compound ones stacked with
  commas — this is documentation, not prose.

## Omission over fabrication
Every section in the draft must trace to something you actually found:
a file, a config value, a function signature, a comment, a commit message,
a CI step. If you can't point to the evidence, don't write the line —
cut the section instead of leaving a bracket, a "TBD", or a guess.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall