Callstack Agent Skills is a collection of instructions that gives AI coding assistants practical knowledge for building React Native applications. Developers use it for app development, performance, navigation, testing, CI, device automation, and migrations to React Native. The catalogue entries are the project's skills, rules, and instructions for compatible coding assistants.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add callstackincubator/agent-skills --skill writing-user-docsgit clone --depth 1 https://github.com/callstackincubator/agent-skillsWrote 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/callstackincubator/agent-skills/writing-user-docs)<a href="https://agentmods.dev/skills/callstackincubator/agent-skills/writing-user-docs"><img src="https://agentmods.dev/badge/skills/callstackincubator/agent-skills/writing-user-docs/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/callstackincubator/agent-skills/writing-user-docs"><img src="https://agentmods.dev/badge/skills/callstackincubator/agent-skills/writing-user-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00168 | $0.01086 |
| Opus 5.5 | $0.00067 | $0.00434 |
| Sonnet 5.5 | $0.00034 | $0.00217 |
| Haiku 4.5 | $0.00017 | $0.00109 |
Grade A, and why
writing-user-docs 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 29d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User-facing documentation
Write for the person using the tool, not the person who built it.
"User" means whoever uses the thing. For an app, that's an end user. For a library, it's the developer who installs it. Either way they are not implementing it, and the docs should reflect that.
Voice
Everyday English — the way you'd explain it to a colleague sitting next to you. Formality doesn't add authority, it just adds distance and words.
- Second person, active, present tense. "You tap Save," not "the Save button should be tapped" or "the user will then be able to save."
- Cut "just," "simply," "easy," "obviously." They add nothing when things work, and read as mockery when they don't.
- No marketing adjectives. "Powerful," "seamless," "robust," "intuitive" — that's the author admiring the product. The reader is mid-task and doesn't care.
- One term per concept, matching the UI exactly. If the button says Workspace, the docs never say "project" or "team space." Varying your vocabulary is good prose and bad documentation — every synonym reads as a new concept.
Scope: what goes in
Include only what the reader needs to use the tool. The default is to leave things out.
Implementation details stay out. Not the database, the queue, the framework, the algorithm's name, the internal service, the refactor it took to ship. The test isn't "is this technical?" — it's "will the reader be surprised, or make a wrong decision, without it?"
Observable behavior passes that test even when it sounds technical, and belongs in the docs: rate limits, offline behavior, what syncs and when, where files are stored, what happens on a conflict, what survives a reinstall. The machinery producing that behavior doesn't.
Concise means no filler, not short. Every sentence earns its place. A thorough troubleshooting section is still concise if none of it is padding — and a two-line page is bloated if one line is a welcome message. Cut preambles, restatements of the heading, and "in this article you will learn."
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.
- 29d ago First seen · 61 lines · 168 tokens per session scan A b631015f194c
writing-user-docs is a skill published in the GitHub repository callstackincubator/agent-skills (1,672 stars, last pushed 7d ago), licensed MIT. It adds 168 tokens to every session and 1,086 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…