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 GuiBibeau/technical-writing-skill --skill technical-writinggit clone --depth 1 https://github.com/GuiBibeau/technical-writing-skillWrote 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/guibibeau/technical-writing-skill/technical-writing)<a href="https://agentmods.dev/skills/guibibeau/technical-writing-skill/technical-writing"><img src="https://agentmods.dev/badge/skills/guibibeau/technical-writing-skill/technical-writing.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.00961 |
| Opus 5 | $0.00032 | $0.00481 |
| Sonnet 5 | $0.00013 | $0.00192 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
technical-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 7d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writing
Make a technical truth usable. Give the reader a recognizable problem, a clear model, enough proof to trust it, the boundary of the claim, and a concrete next move.
Choose the mode
Select one mode before doing the work:
- Plan: Return the reader contract, evidence gaps, selected document pattern, section beats, and verification plan. Do not draft the prose unless asked.
- Draft or rewrite: Return publication-ready prose in the requested format, plus unresolved verification notes only when they affect safe use or publication.
- Review: Return prioritized editorial findings or an annotated draft at the requested depth. Do not silently replace a review with a rewrite.
If the request combines modes, keep their artifacts distinct.
Establish the reader contract
Recover these from the request and source material:
- Reader: Who will use this, and what can they already know?
- Job: What should they understand, decide, build, debug, or review afterward?
- Friction: What failure, cost, misconception, or constraint makes the piece necessary?
- After-state: What observable result would mean the document worked?
- Boundary: What is deliberately out of scope, unchanged, or uncertain?
- Evidence: Which code, commands, data, sources, screenshots, logs, or lived examples can carry the claims?
Infer low-risk gaps. Ask only when a missing answer would materially change the artifact. Preserve the user's format, scope, and own voice or requested abstract voice qualities; use original phrasing rather than imitating a named writer.
The contract is complete only when all six fields are explicit in the working notes.
Select the document pattern
For a substantial plan, draft, rewrite, or structural review, read the closest pattern in references/document-patterns.md. Use one primary pattern and borrow another only when the reader's job genuinely crosses formats.
The pattern is selected when its reader job matches the request and its completion criterion describes the intended after-state.
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.
- 7d ago First seen · 62 lines · 65 tokens per session scan A 1d89c1cd0232
technical-writing is a skill published in the GitHub repository GuiBibeau/technical-writing-skill (0 stars, last pushed 8d ago), licensed MIT. It adds 65 tokens to every session and 961 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
canvas-course-builder
Scaffold complete Canvas LMS course structures from specs, templates, or existing courses. Creates modules, pages, assignments, and discussions in bulk. Use when asked to "build a course", "scaffold modules", "create course structure", "set up a new course", or "copy course structure".
grokipedia-recommendations
When the user wants to add recommendations, links, or content to Grokipedia. Also use when the user mentions "Grokipedia," "GEO wiki," "AI encyclopedia," "suggest Grokipedia article," "Grokipedia citation," "Grokipedia listing," "AI search citation," "GEO visibility," or "Grokipedia optimization." For multi-platform…
schema-markup
When the user wants to add or optimize structured data (Schema.org, JSON-LD). Also use when the user mentions "schema," "structured data," "JSON-LD," "rich results," "rich snippets," "Google rich snippets," "featured snippet schema," "add schema to page," "missing structured data," "schema validation error," "Schema…
google-search-console
When the user wants to analyze Google Search Console data, use the GSC API, or interpret search performance. Also use when the user mentions "GSC," "Search Console," "indexing report," "Core Web Vitals," "Enhancements," "Insights report," "search performance," "search queries," "search performance report," "URL…
image-optimization
When the user wants to optimize images for search engines and performance. Also use when the user mentions "image SEO," "alt text," "image captions," "figcaption," "image optimization," "WebP," "lazy loading," "LCP," "image sitemap," "responsive images," "srcset," "image format," or "hero image optimization." For CWV…
video-optimization
When the user wants to optimize videos for Google Search, video sitemap, VideoObject schema, or video SEO on websites. Also use when the user mentions "video SEO," "video sitemap," "VideoObject," "video thumbnail," "video indexing," "video preview," "key moments," "Clip schema," or "embedded video optimization." For…