docsector-reader: Skill for Claude Code

.github/skills/docsector-documentation-authoring/SKILL.md

docsector-documentation-authoring is a skill for Claude Code from docsector/docsector-reader. It costs 65 tokens per session (1,482 once invoked), scanned A, original, MIT.

A writing guide for creating Docsector documentation pages in Markdown, including its custom page elements and content structures. Docsector is a system for publishing documentation that can be read by people and AI agents.

In plain words
What is it for?
Use it to write or edit guides, API references, release notes, landing pages, examples, and troubleshooting pages. It also helps document Docsector’s authoring syntax for another AI assistant.
Why use it?
It helps you choose the right page structure and formatting instead of guessing how Docsector content should be written. It also points to current Docsector documentation when connected sources are available.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is docsector/docsector-reader's own configuration. It tells Claude Code how to work on docsector-reader itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything docsector-reader configures →

Reuse

Borrowing it

Nothing to install: this file belongs to docsector/docsector-reader. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/docsector/docsector-reader/main/.github/skills/docsector-documentation-authoring/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/docsector/docsector-reader

Made for: Claude Code.

Wrote 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.

agentmods badge for docsector-documentation-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/docsector/docsector-reader/docsector-documentation-authoring/github.svg)](https://agentmods.dev/skills/docsector/docsector-reader/docsector-documentation-authoring)
Your own site
<a href="https://agentmods.dev/skills/docsector/docsector-reader/docsector-documentation-authoring"><img src="https://agentmods.dev/badge/skills/docsector/docsector-reader/docsector-documentation-authoring/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.

agentmods 80×15 button for docsector-documentation-authoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/docsector/docsector-reader/docsector-documentation-authoring"><img src="https://agentmods.dev/badge/skills/docsector/docsector-reader/docsector-documentation-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.01482
Opus 5.5 $0.00026 $0.00593
Sonnet 5.5 $0.00013 $0.00296
Haiku 4.5 $0.00006 $0.00148

Measured 1mo ago against content hash 106d3e344171, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docsector-documentation-authoring 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.

.github/skills/docsector-documentation-authoring/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docsector Documentation Authoring

When to Use

Use this skill when creating, reviewing, or editing documentation for a site built with Docsector Reader.

Use it for:

  • Choosing the right Docsector block for a content need.
  • Writing Markdown pages with Docsector custom elements.
  • Creating overview, showcase, guide, API reference, changelog, or landing content.
  • Finding live Docsector docs through MCP, WebMCP, Markdown negotiation, or llms.txt.
  • Teaching an AI assistant how Docsector pages, blocks, and examples are authored.

Expected Outcome

  • The page uses standard Markdown where Markdown is enough.
  • Rich interactions use the appropriate Docsector custom element.
  • Links, assets, examples, and API JSON use Docsector conventions.
  • The result is easy to scan, accessible, and friendly to both humans and agents.
  • When MCP or WebMCP is available, current Docsector documentation is queried instead of relying only on memory.

Authoring Workflow

  1. Identify the page purpose: concept, tutorial, API reference, release note, navigation hub, example showcase, or troubleshooting guide.
  2. Use headings to shape the reading path. In normal page content, start with ## because the page title is supplied by metadata — the registry entry, or an optional title: in the page's own frontmatter block.
  3. Pick the simplest block that communicates the content. Prefer Markdown first, then Docsector custom elements when the layout or interaction needs it.
  4. Keep custom element attributes short and explicit. Use to for internal navigation and href for external URLs.
  5. Put reusable assets in stable public paths such as /images/..., /files/..., /api/..., or /quasar-api/....
  6. For live examples, place Vue SFCs under src/examples/**/*.vue and reference them with <d-block-code-example>.
  7. For API references, serve JSON from a same-origin public asset and reference it with <d-block-api>.
  8. Put frequently asked questions in the page's faq: frontmatter (- q: / a: items) instead of a hand-written section: Docsector renders them as the closing FAQ, adds the ToC entry and emits FAQPage JSON-LD.
  9. Validate links, anchors, code fences, and custom element closing tags before finishing.

Read the full file on GitHub · 121 lines

Files

What ships with it

4 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.

Changes

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.

  1. 1mo ago Changed · +1 lines 106d3e344171
  2. 1mo ago Changed · +1 lines 562c7f933776
  3. 2mo ago First seen · 119 lines · 65 tokens per session scan A 29bdc2cf9ff1

Subscribe to this mod's changes

docsector-documentation-authoring is a skill published in the GitHub repository docsector/docsector-reader (21 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,482 once invoked, about $0.0003 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.

Related

docsector-documentation-authoring compared with skills from other repositories

docsector-documentation-authoring next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docsector-documentation-authoringdocsector/docsector-readerSkill211mo agoMITA65Claude Code
enrich-exceltinyfish-io/tinyfish-cookbookSkill2.3k3d agoMITA92Claude Code, Codex
review-docinvertase/docs.pageSkill6788d agoApache-2.0A103Claude Code, Codex
Folio Contentevergreen-it-dev/folioSkill81yesterdayMITA37Claude Code, Codex
Folio Formsevergreen-it-dev/folioSkill81yesterdayMITA37Claude Code, Codex
Folio Basesevergreen-it-dev/folioSkill81yesterdayMITA41Claude Code, Codex
slides-to-pdfglukicov/slideopsSkill515d agoMITA76Claude Code