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 Neuralyn-AI/claude-skills --skill helpdesk-writergit clone --depth 1 https://github.com/Neuralyn-AI/claude-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/neuralyn-ai/claude-skills/helpdesk-writer)<a href="https://agentmods.dev/skills/neuralyn-ai/claude-skills/helpdesk-writer"><img src="https://agentmods.dev/badge/skills/neuralyn-ai/claude-skills/helpdesk-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/neuralyn-ai/claude-skills/helpdesk-writer"><img src="https://agentmods.dev/badge/skills/neuralyn-ai/claude-skills/helpdesk-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 | $0.00070 | $0.03117 |
| Opus 5 | $0.00035 | $0.01558 |
| Sonnet 5 | $0.00014 | $0.00623 |
| Haiku 4.5 | $0.00007 | $0.00312 |
Grade A, and why
helpdesk-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 11d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helpdesk Writer
Produces helpdesk articles backed by technically verified information: it cross-checks the product's source code, the live UI in a sandbox account, and a voice guide before writing a single line. Publishes only after explicit human approval and only to a transport the user designates at that moment.
When to activate
Requests to write, update, or draft:
- Tutorial / step-by-step / how-to
- Explanation of a product feature, flow, or concept
- Troubleshooting article / error message explainer
- Reference for a data format, limit, or requirement
- FAQ or conceptual article
Expected environment prerequisites
- Playwright MCP installed:
claude mcp add playwright npx @playwright/mcp@latest - Product repositories cloned locally (backend, frontend, any other relevant repos).
- Python 3 with Pillow:
pip install Pillow
The skill ships no product-specific configuration. Repo paths, sandbox credentials, the chosen helpdesk transport, and the helpdesk portal structure all come from the operator — either persisted in a project config file or provided at runtime.
Master workflow
Execute these steps in order. Do not skip steps. Hard rule: no technical claim enters the article without traceable evidence — from the code or from the UI. Hard rule: never read, search, or use any file on the user's system that is outside the repositories declared in the project config. This applies to every step of the workflow, without exception.
Step 1 — Topic and language
Use AskUserQuestion (dialog) to collect:
- What the article is about — free text (e.g. "How to register products").
- Article language — offer choices based on any language already configured
in the active project. If no project languages are configured yet, offer at
least English and "Other" (the
AskUserQuestiontool requires a minimum of 2 options; never pass a single-item list).
Do not ask anything else in this round. Steps 2–3 decide the rest.
What ships with it
12 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.
- examples/_template.md 2.1 KB
- playbooks/_template.md 3.9 KB
- references/code-recon.md 7.2 KB
- references/helpdesk-platforms.md 6.8 KB
- references/portal-config.md 6.4 KB
- references/publishing-rules.md 4.1 KB
- references/README.md 4.8 KB
- references/runtime-state.md 7.0 KB
- references/screenshot-conventions.md 11 KB
- references/style-guide.md 5.4 KB
- references/ui-walkthrough.md 9.0 KB
- scripts/annotate.py 15 KB runs code
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.
- 11d ago First seen · 342 lines · 0 tokens per session scan A 82954f2fbdf6
helpdesk-writer is a skill published in the GitHub repository Neuralyn-AI/claude-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 3,117 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
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…