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 hubvue/skills --skill tech-writinggit clone --depth 1 https://github.com/hubvue/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/hubvue/skills/tech-writing)<a href="https://agentmods.dev/skills/hubvue/skills/tech-writing"><img src="https://agentmods.dev/badge/skills/hubvue/skills/tech-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 | $0.00094 | $0.02180 |
| Opus 5 | $0.00047 | $0.01090 |
| Sonnet 5 | $0.00019 | $0.00436 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
tech-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 8d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Article Co-writing
Reorganize engineering knowledge into an article that a defined reader can understand step by step and verify against evidence. Do not mirror the codebase structure, command list, or internal object model unless that structure genuinely serves the reader.
Choose the working mode
Infer the mode from the request. Do not ask again when the intent is clear.
- Section-by-section co-writing (default): plan first, then draft one section at a time. Do not write an unapproved candidate into the manuscript.
- Direct draft: when the user explicitly requests a full draft or direct file edits, complete the requested scope and run a unified review.
- Review: diagnose and propose changes. Do not edit files without authorization.
- Continue: read the existing manuscript, collaboration notes, and project sources; recover accepted claims, structure, terminology, and voice before writing the next section.
The user owns editorial decisions, section boundaries, and approval to persist a candidate. Research that is safe and clearly in scope may proceed without waiting for process confirmation.
Route the language
Determine the target language before drafting:
- Follow an explicit user request.
- Otherwise preserve the language of the existing manuscript.
- For a new article with no explicit language, use the audience's working language; if still unclear, follow the user's language.
Then load the matching review guide:
- Chinese article: read references/writing-review-zh.md.
- English article: read references/writing-review-en.md.
- Translation or bilingual article: establish the primary audience and primary language, then read both guides. Do not create sentence-by-sentence bilingual duplication unless requested.
For English, preserve or establish a spelling convention such as US or UK English. For every language, preserve technical identifiers, commands, field names, code, and official product names unless the user asks to localize them. Treat localization as adaptation for that audience, not literal translation.
What ships with it
7 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.
- 8d ago First seen · 208 lines · 94 tokens per session scan A dccfe6358a47
tech-writing is a skill published in the GitHub repository hubvue/skills (6 stars, last pushed 7d ago), licensed MIT. It adds 94 tokens to every session and 2,180 once invoked, about $0.0005 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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…