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 NPC-Worldwide/npcsh --skill technical-writinggit clone --depth 1 https://github.com/NPC-Worldwide/npcshWrote 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/npc-worldwide/npcsh/technical-writing)<a href="https://agentmods.dev/skills/npc-worldwide/npcsh/technical-writing"><img src="https://agentmods.dev/badge/skills/npc-worldwide/npcsh/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/npc-worldwide/npcsh/technical-writing"><img src="https://agentmods.dev/badge/skills/npc-worldwide/npcsh/technical-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 64 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00022 | $0.00548 |
| Opus 5.5 | $0.00009 | $0.00219 |
| Sonnet 5.5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
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 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
technical-writing
Patterns for clear technical writing in documentation, READMEs, API references, and design documents.
Clarity
One idea per sentence. One topic per paragraph.
- Use simple subject-verb-object order. Avoid nested clauses.
- Replace jargon with plain language unless the term is standard for the audience.
- Define acronyms on first use. Do not assume the reader knows internal project names.
- Use active voice: "The scheduler retries failed tasks" not "Failed tasks are retried by the scheduler."
Precision
Be exact about behavior, not suggestive.
- Write "Returns a list of strings" not "Returns some data."
- Write "Throws ValueError if the input is negative" not "May throw an error for bad input."
- Write "Timeout is 30 seconds" not "Timeout is fairly short."
- Distinguish "must" (requirement), "should" (recommendation), and "may" (optional).
Structure
Documents follow a predictable hierarchy:
- What this is (one sentence).
- What problem it solves (one paragraph).
- How to use it (minimal working example).
- Configuration or parameters (table or list with types and defaults).
- Error handling and edge cases.
- Limitations and assumptions.
- Links to related docs or source code. Do not bury the example under three paragraphs of motivation.
Code-Examples
Every concept must have a minimal reproducible example.
- Show the simplest possible call that produces a valid result.
- Show one error case if the failure mode is non-obvious.
- Include expected output as a comment or separate block.
- Keep examples copy-pasteable. No pseudocode in API docs.
Cross-References
Never leave the reader hunting for related information.
- Link to prerequisite concepts before using them.
- Link to deeper dives from high-level summaries.
- If a term is defined elsewhere, link the first use in each major section.
- Keep links working. Broken links erode trust faster than missing links.
Revision-Checklist
Before marking a doc complete:
- Can a new reader follow the example without asking for help?
- Are all claims verifiable (traceable to code, test, or source)?
- Are there any ambiguous pronouns ("it", "this") that could mislead?
- Is every number, parameter, and default current with the code?
- Does the doc answer "what happens if this goes wrong?"
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 · 69 lines · 22 tokens per session scan A a966de807e20
technical-writing is a skill published in the GitHub repository NPC-Worldwide/npcsh (495 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 548 once invoked, about $0.0001 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 2026-08-30.
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…