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 CODE-SAURABH/OpenSkills --skill technical-writergit clone --depth 1 https://github.com/CODE-SAURABH/OpenSkillsWrote 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/code-saurabh/openskills/technical-writer)<a href="https://agentmods.dev/skills/code-saurabh/openskills/technical-writer"><img src="https://agentmods.dev/badge/skills/code-saurabh/openskills/technical-writer/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/code-saurabh/openskills/technical-writer"><img src="https://agentmods.dev/badge/skills/code-saurabh/openskills/technical-writer.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 | $0.00082 | $0.02937 |
| Opus 5.5 | $0.00033 | $0.01175 |
| Sonnet 5.5 | $0.00016 | $0.00587 |
| Haiku 4.5 | $0.00008 | $0.00294 |
Grade A, and why
technical-writer 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 1mo 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writing
Approach every documentation task as a senior engineer who has joined a new team and could not figure out how to run the project from the existing docs. Write the documentation that would have saved you three hours on your first day.
Documentation is not a formality. It is the interface between your system and the humans who must use, operate, and extend it. Bad documentation costs real time — onboarding time, debugging time, support time. Good documentation compounds: every hour spent writing saves ten hours across the team.
Technical Writing Principles
- Write for the reader, not the writer. You know how the system works. Your reader does not. Write for their starting point, not yours.
- One document, one job. A document that tries to be a tutorial, a reference, and a how-to guide at the same time fails at all three. Follow the Diataxis framework: every document is exactly one of — Tutorial, How-To, Reference, or Explanation.
- Accurate beats elegant. A beautifully written document that describes how the system used to work is worse than an ugly document that is correct. Accuracy first, prose second.
- Show, don't just tell. Code examples, command outputs, screenshots, and diagrams are worth more than prose descriptions of the same thing.
- Docs that are hard to find are docs that do not exist. Structure matters. A runbook buried five folders deep will not be found at 3am during an incident.
- Update docs in the same PR as the code. A doc updated a week after the code change is a doc that was wrong for a week. Stale documentation erodes trust faster than no documentation.
The Diataxis Framework
Every piece of documentation you write falls into exactly one of these four types. Determine the type before writing.
| Type | Question it answers | Audience mindset | Example |
|---|---|---|---|
| Tutorial | How do I learn this? | I am new and want to succeed at something | "Build your first API in 10 minutes" |
| How-To | How do I do X? | I know what I want; guide me | "How to deploy to production" |
| Reference | What is X? | I need to look up a specific detail | API endpoint reference, CLI flag reference |
| Explanation | Why does X work this way? | I want to understand the design | "Why we chose event-sourcing" |
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.
- 1mo ago First seen · 325 lines · 82 tokens per session scan A 2e89cf9e0915
technical-writer is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (3 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 2,937 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
blog-notebooklm
Query Google NotebookLM notebooks for source-grounded, citation-backed answers from user-uploaded documents. Manages notebook library, handles Google authentication, and supports smart discovery. Works standalone via /blog notebooklm or internally from blog-write and blog-researcher for source-grounded research…
library-rag
Semantic search over a personal library using Nemotron-3-Embed-1B embeddings + sqlite-vec. Index books, documents, any text corpus; query by meaning. Includes EPUB→Markdown conversion and MCP server for auto-available search tools.
fill-template
Use when the user wants to "fill in this letter for each person", "mail merge", "generate letters for this list", "turn this filled letter into a template", or hands over a template plus a list. Bulk-fills ONE master template — a Word (.docx) letter/form or an Excel (.xlsx) form — from a data table, one filled file…
people-enrichment
Use when the user has a list of names or companies and wants their job, employer, work history, LinkedIn URLs or company profiles looked up, or wants to find people or companies matching criteria — trigger on phrases like "enrich these contacts", "find their LinkedIn", "look up these people", "who works at X", "find…
pdf2epub
Use when converting a PDF book to EPUB, e.g. 'pdf to epub', 'convert this PDF book for my e-reader', 'EPUB with cover and TOC', 'pdf to ebook for kobo/kindle'. Builds a text-layer PDF into an EPUB with cover image, one section per chapter, a parsed 目录/Contents TOC, inline illustrations, and footnote endnotes.…
youtube-fetcher
Retrieve YouTube transcripts and subtitles, summarize or analyze what was said, or save an Obsidian-ready Markdown knowledge-base note with captions, creator metadata, chapters, language, and source provenance. Use for a YouTube URL or video ID when the request needs spoken content or an archival note. A bare YouTube…