Borrowing it
Nothing to install: this file belongs to sagar-shirwalkar/collibra-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sagar-shirwalkar/collibra-atlas/main/.agents/skills/readme-writing/SKILL.mdgit clone --depth 1 https://github.com/sagar-shirwalkar/collibra-atlasWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/readme-writing)<a href="https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/readme-writing"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/readme-writing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sagar-shirwalkar/collibra-atlas/readme-writing"><img src="https://agentmods.dev/badge/skills/sagar-shirwalkar/collibra-atlas/readme-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.02769 |
| Opus 5 | $0.00025 | $0.01385 |
| Sonnet 5 | $0.00010 | $0.00554 |
| Haiku 4.5 | $0.00005 | $0.00277 |
Grade A, and why
readme-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
README Writing
A README is the project's front door. Every reader arrives with a question: what is this, should I use it, how do I start? Answer those in order without making them dig. Then curate everything else.
Tenets
Four tenets anchor every decision:
- Portal — The README answers the reader's first question before they scroll. Identity, value proposition, and quick start come first. Everything else follows.
- Tier — READMEs serve readers at different depths. Match the tier to the project's maturity and audience. See TIERS.md.
- Prove — Every claim earns trust through evidence. Show a benchmark instead of saying "fast". Show a code block instead of saying "easy to use". Show a table instead of listing features in prose. A README that proves its claims is one readers adopt from.
- Relentless — Every word earns its place. Cut anything that doesn't answer a reader's question. A sharply curated short README beats a long one that hedges.
Leading word: Curate
Every line, section, badge, and link passes the test: does this serve a reader, or is it here because it exists? Cut what fails. Curate the install section to the fastest path. Curate the feature list to what matters. Curate badges to the ones a reader actually clicks. When in doubt, leave it out.
Workflows
The skill supports two common workflows. Pick the one that matches the task.
Workflow A: Greenfield README
Write from scratch. Follow all four phases below. The project has no existing README or the existing one is unsalvageable.
Workflow B: Adapt from reference
When the user points to an existing README as the quality target ("make ours as good as X"), use this workflow:
- Read the reference README completely. Note its section ordering, depth per section, code block density, table usage, and mermaid diagrams. This is the quality bar.
- Extract the reference's skeleton. List every section heading, its audience, and its approximate length (short / medium / long). This is the template you'll adapt.
- Map each section to your project. For every section in the reference, find the equivalent in your project. Some sections map 1:1 ("Installation" stays "Installation"). Some need rethinking (the reference's "project-specific crawler" becomes your project's equivalent, or gets dropped if you don't have one).
- Identify gaps. What does the reference cover that your project also needs but doesn't have a section for? What does your project need that the reference doesn't cover?
- Adapt, don't copy. Replace every project-specific detail. Change every example, every command, every path. The structure transfers; the content must be yours.
- Run the relentless review. The adapted README still needs to pass CHECKLIST.md — the reference's quality doesn't transfer automatically.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 154 lines · 50 tokens per session scan A 5692e906607c
readme-writing is a skill published in the GitHub repository sagar-shirwalkar/collibra-atlas (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,769 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…