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 stonegiantstudio/skills --skill technical-writinggit clone --depth 1 https://github.com/stonegiantstudio/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/stonegiantstudio/skills/technical-writing)<a href="https://agentmods.dev/skills/stonegiantstudio/skills/technical-writing"><img src="https://agentmods.dev/badge/skills/stonegiantstudio/skills/technical-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/stonegiantstudio/skills/technical-writing"><img src="https://agentmods.dev/badge/skills/stonegiantstudio/skills/technical-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 | $0.00099 | $0.00850 |
| Opus 5 | $0.00049 | $0.00425 |
| Sonnet 5 | $0.00020 | $0.00170 |
| Haiku 4.5 | $0.00010 | $0.00085 |
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 10d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical writing
Documentation succeeds when a reader completes their task and fails when they stall. Every rule here reduces stalls.
Sentence discipline
Distilled from the principles of ASD-STE100 Simplified Technical English. (The STE specification and its dictionary are copyrighted; this skill applies the principles and reproduces none of the content.)
- One instruction per sentence. "Save the file. Restart the service." Never "save the file and then you can restart the service."
- One topic per paragraph.
- Active voice, always naming the actor. "The scheduler retries the job" — not "the job is retried."
- Present tense for facts, imperative for steps. "The cache expires after 60 seconds." "Delete the cache key."
- Short sentences. About 20 words for procedures, about 25 for description. Split anything longer.
- One term, one meaning. Pick one name per concept and repeat it. In literary prose, repeating a word is a flaw; in documentation, varying it is the flaw. A reader who sees "endpoint," "route," and "URL" must ask whether they name three things or one.
- Keep the articles. "Insert the pin in the housing" — not "insert pin in housing." Telegraphic style saves nothing and costs clarity.
- Warnings before the step they protect. A reader mid-command does not scroll ahead.
- Vertical lists for sequences, one action per step. Number steps only when order matters.
Worked demonstration of every rule on one runbook:
references/examples.md.
The reader model
- Every page is page one (Baker). Readers arrive mid-document from search. Each page states its purpose, its prerequisites, and where it sits — without assuming the reader saw any other page.
- Fight the curse of knowledge (Pinker). State what the reader must already know. Define each term on first use or link its definition. The author's familiarity is the main source of reader stalls.
Doc types (Diátaxis)
Pick one type per document; do not blend.
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.
- 10d ago First seen · 76 lines · 99 tokens per session scan A 735ae4766a29
technical-writing is a skill published in the GitHub repository stonegiantstudio/skills (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 99 tokens to every session and 850 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…
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…
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…