New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Guide Authoring

by microlinkhq in microlinkhq/www

Create or revise docs guides under src/content/docs/guides with runnable MDX examples.

MITAuto-check passedDocuments & Office

Install Guide Authoring

skills CLI
$ npx skills add microlinkhq/www --skill guide-authoring -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install microlinkhq/www guide-authoring --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/microlinkhq/www.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/guide-authoring .claude/skills/guide-authoring && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
guide-authoring
GitHub stars
142
Token cost
~2.5k tokens
SKILL.md length
1,205 words
Files
2 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Create or revise docs guides under src/content/docs/guides with runnable MDX examples.

  • Works in 7 steps: src/content/docs/guides/index.md → The target utility guide folder, if it… → src/content/docs/guides/screenshot/*.md… → …
  • Tasks that involve Markdown
  • SKILL.md covers Goal, When to Use, Read first and Core principles, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Guide Authoring is an agent skill from microlinkhq/www. Create or revise docs guides under src/content/docs/guides with runnable MDX examples.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/templates.md`).

It sits in Documents & Office, covering Markdown. The repository describes itself as: AI-ready infrastructure for interacting with the web. Built on real browsers. Exposed through a single API. The licence is MIT.

When your agent uses it

  • Tasks that involve Markdown

Example prompts

  • “/guide-authoring”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. src/content/docs/guides/index.md
  2. The target utility guide folder, if it exists.
  3. src/content/docs/guides/screenshot/*.md as the house-style baseline.
  4. All relevant src/content/docs/api/parameters/** pages for the utility.
  5. Related shared docs when applicable
  6. Common pattern pages under src/content/docs/guides/common/
  7. src/components/patterns/Aside/constants.js if the guide set changes.

What it can do on your machine

Read from SKILL.md and the folder at commit d160a67. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Guide Authoring loads about 2.5k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 26 tokens; SKILL.md has 1,205 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from microlinkhq/www at commit d160a67, republished under its MIT licence (© microlinkhq). 1,205 words, ~2,462 tokens.

Download SKILL.mdSave it as .claude/skills/guide-authoring/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
guide-authoring
description
Create or revise docs guides under src/content/docs/guides with runnable MDX examples.

Goal

Create guides like the current screenshot guide: practical, workflow-first, easy to scan, and strictly aligned with the API docs.

When to Use

  • The user wants to add a new guide for a Microlink utility under src/content/docs/guides.
  • The user wants to turn API parameter docs into a guide set.
  • The user wants feedback on guide structure, coverage, or sequencing before writing.
  • The user wants an existing Microlink guide rewritten from parameter-by-parameter reference style into workflow-first documentation.

Read first

When asked to create or revise a guide, read:

  1. src/content/docs/guides/index.md
  2. The target utility guide folder, if it exists.
  3. src/content/docs/guides/screenshot/*.md as the house-style baseline.
  4. All relevant src/content/docs/api/parameters/** pages for the utility.
  5. Related shared docs when applicable:
    • basics: authentication, cache, endpoint, error-codes, rate-limit
    • shared params: embed, filter, filename, force, headers, meta, proxy, retry, staleTtl, timeout, ttl
  6. Common pattern pages under src/content/docs/guides/common/:
    • caching.md — shared caching patterns (ttl, staleTtl, force)
    • private-pages.md — shared auth patterns (headers, x-api-header-*, endpoint, proxy)
    • troubleshooting.md — shared debug patterns (timeouts, blocked sites, error codes, debug headers)
    • production-patterns.md — best practices for production integrations
  7. src/components/patterns/Aside/constants.js if the guide set changes.

The screenshot guide is the current benchmark for tone, depth, and cross-linking. Match its quality, not necessarily its exact file count.

Core principles

  • Guides explain user jobs, not parameter catalogs.
  • The main index.md is a quickstart and hub, not a thin landing page.
  • Explain the key mental model once early:
    • response shape
    • canonical syntax
    • important choice points such as JSON vs embed, viewport vs element, fresh vs cached
  • Use one canonical syntax consistently across guide pages. For utility-specific options, prefer the nested object form in interactive examples when the API supports it.
  • Compare related options directly with tables, checklists, or "choose X vs Y" sections.
  • Use live MultiCodeEditorInteractive examples. If metadata is not the point, add meta: false.
  • Prefer stable demo URLs and selectors. Default to microlink.io, github.com/microlinkhq, or other durable targets. Avoid deprecated third-party services (e.g., source.unsplash.com is deprecated).
  • End each subguide with ## Next step.
  • Add a ## See also section at the bottom of the index.md linking to related guides that solve adjacent problems.
  • Mark Pro features with ProBadge only when the authoritative parameter page has isPro: true or the user explicitly confirms the plan gating.
  • Do not document undocumented parameter shapes. If the type/examples do not show a boolean, object, string, array form, do not invent it.

Shared content architecture

Caching, private pages, and troubleshooting contain patterns that are identical across all workflows. To avoid duplication and maintenance drift:

  1. Shared pattern pages live under src/content/docs/guides/common/. They contain the universal advice: how ttl/staleTtl/force work, how headers/x-api-header-*/proxy work, and how to read debug headers.
  2. Per-guide pages for caching, private pages, and troubleshooting are slim — they contain only the guide-specific advice (e.g., "set meta: false for screenshot-only requests") and link to the shared pattern page for the universal parts.
  3. When creating a new guide, do NOT duplicate the shared content. Write the guide-specific tips and link to common/.

The pattern is:

  • Guide-specific intro ("The biggest speedup for screenshot requests is…")
  • Guide-specific checklist or examples
  • Link to shared pattern page ("For cache controls that apply to all workflows, see caching patterns.")
  • Next step link

Pick the page set

Start with the smallest useful set. Do not copy the screenshot page list blindly.

PageUse whenTypical content
index.mdAlwaysQuickstart, response model, canonical syntax, key decision points, roadmap, "See also"
customizing-output.mdThe utility has output-specific optionsOutput modes, formatting, visual differences, asset customization
browser-settings.mdHeadless browser rendering changes the resultDevice, viewport, color scheme, media type, JavaScript, rendering settings
page-interaction.mdBrowser actions affect successwaitUntil, waitForSelector, click, scroll, styles, scripts, function, adblock
embedding.mdUsers need to consume assets in markup or choose a delivery modeJSON vs direct asset response, embed, response shaping, filenames
caching-and-performance.mdFreshness, cost, and speed matterGuide-specific speedups only, then link to common/caching
private-pages.mdAuth, sessions, forwarded headers, or endpoint choice matterGuide-specific examples only, then link to common/private-pages
troubleshooting.mdFailure modes are common or multi-causalGuide-specific issues only, then link to common/troubleshooting

Rename pages when the utility needs different language (e.g., the markdown guide uses choosing-scope.md instead of defining-rules.md), but keep the workflow-first grouping.

Show full SKILL.md (510 more words)Show less

Authoring workflow

  1. Audit the utility surface.

    • Gather all utility-specific parameters.
    • Gather cross-cutting parameters that materially change user success.
    • Note response fields, defaults, plan gating, and common failure modes.

  2. Design the information architecture.

    • Group by user decisions and workflows.
    • Separate output, delivery, auth/private pages, and troubleshooting when those are meaningful.
    • Avoid one giant page unless the utility surface is genuinely small.

  3. Write the hub page.

    • First runnable example.
    • Response model.
    • Canonical syntax.
    • One or two decision sections or tables.
    • "What's next" list linking to every subguide.
    • "See also" section linking to related guides.

  4. Write subguides.

    • Start with the user problem the page solves.
    • Show a runnable example early.
    • Explain when to use the option or pattern.
    • Compare it with adjacent options.
    • Keep reference-style detail out unless it helps a decision.
    • For caching, private pages, and troubleshooting: keep guide-specific, link to common/.

  5. Update shared navigation.

    • Update src/content/docs/guides/index.md (including the "Which guide do I need?" table).
    • Update src/components/patterns/Aside/constants.js.

  6. Cross-check before finishing.

    • Verify every claim against the API docs.
    • Align syntax, defaults, response fields, and plan gating.
    • If the guide exposes a clear reference inconsistency, fix it.
    • If the inconsistency is ambiguous, ask the user instead of inventing behavior.
    • Use an ask-questions step when the utility surface, page set, or plan gating is unclear.
    • Verify all example URLs are stable and not deprecated.

MDX conventions

Common imports:

js
import { Link } from 'components/elements/Link'
import { Figcaption } from 'components/markdown/Figcaption'
import { MultiCodeEditorInteractive } from 'components/markdown/MultiCodeEditorInteractive'
import ProBadge from 'components/patterns/ProBadge/ProBadge'
  • Import only what you use.
  • Use Link for internal docs links.
  • Use Figcaption to explain the takeaway of the example, not restate the code.
  • Frontmatter descriptions should explain the page's user value, not list every parameter.
  • Keep titles short and consistent with existing guide naming.
  • Prefer markdown tables for comparisons and decision points.

Guardrails

  • Never wrap markdown link text in code spans: write [function](…) with plain link text.
  • Do not mirror the API reference page-for-page.
  • Do not add pages just for symmetry.
  • Do not duplicate universal patterns that belong in common/. Link instead.
  • Do not bury critical workflows like private pages or troubleshooting if the utility needs them.
  • Do not rely on fragile selectors or gated third-party pages for core examples.
  • Do not ship inconsistent syntax between guide and reference.
  • Do not use deprecated third-party services (verify URLs are still live).
  • When docs conflict, prefer:
    1. parameter page type, frontmatter, and examples
    2. directly related basics/getting-started docs
    3. explicit user confirmation
  • Do not infer behavior from pricing blurbs, isolated prose mentions, or error codes alone.

Definition of done

  • The page set matches the real utility surface.
  • index.md works as both quickstart and hub.
  • index.md has a "See also" section linking to related guides.
  • The guide focuses on workflows and decision points.
  • Examples are runnable and use stable URLs.
  • Plan gating matches the authoritative docs.
  • Syntax, defaults, and response fields match the reference.
  • Caching, private pages, and troubleshooting pages link to common/ for shared patterns.
  • src/content/docs/guides/index.md is updated (including "Which guide do I need?" table).
  • src/components/patterns/Aside/constants.js is updated if needed.
  • Each subguide has ## Next step.
  • The guide reads like one cohesive system, not separate parameter notes.

Templates

For copyable outlines, see references/templates.md.

© microlinkhq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .cursor/skills/guide-authoring of microlinkhq/www.

  • SKILL.md
  • references/templates.md

Open the folder on GitHubat commit d160a67

Compare with similar skills

Guide Authoring next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Guide Authoring compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Guide Authoring this skillmicrolinkhq/www142—~2.5kAutomated safety check: PassMIT
Markdown Article FormatterJimLiu/baoyu-skills26k6 repos~3.5kAutomated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Obsidian MarkdownAtmosphere/atmosphere3.8k20 repos~1.3kAutomated safety check: PassApache-2.0
Gzh Designisjiamu/gzh-design-skill3.9k1 repos~2.2kAutomated safety check: PassAGPL-3.0
Crosspostingwasp-lang/wasp19k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Markdown Article Formatter

    JimLiu/baoyu-skills

    Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy.

    26k GitHub starsUsed in 6 repos~3.5k tokens
    Documents & OfficeAuto-check passed

  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes

  • Obsidian Markdown

    Atmosphere/atmosphere

    Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax.

    3.8k GitHub starsUsed in 20 repos~1.3k tokens
    Documents & OfficeAuto-check passed

  • Gzh Design

    isjiamu/gzh-design-skill

    微信公众号文章排版引擎，将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取，自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入（非 Markdown…

    3.9k GitHub starsUsed in 1 repo~2.2k tokens
    Documents & OfficeAuto-check passed

  • Crossposting

    wasp-lang/wasp

    Crosspost Wasp blog articles (MDX) to DEV.to and Medium. An agent skill from wasp-lang/wasp.

    19k GitHub stars~1.1k tokensUpdated today
    Documents & OfficeAuto-check passed

  • Segment Docs

    JanDeDobbeleer/oh-my-posh

    Reference mapping between Oh My Posh Go segment source code and MDX documentation.

    24k GitHub stars~1.1k tokensUpdated today
    Documents & OfficeAuto-check passed

More from microlinkhq/www

  • Customer Story

    microlinkhq/www

    Scaffold a customer story page under src/pages/use-cases/customers/ from the CustomerStory module.

    142 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Use Case Landing

    microlinkhq/www

    Create or improve use-case landing pages under src/pages/use-cases/ from the UseCaseStory module.

    142 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed

  • Generate Changelog

    microlinkhq/www

    Generate concise, user-facing changelog entries for Microlink by inspecting git commits across relevant repositories.

    142 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

  • Verify

    microlinkhq/www

    Verify UI changes in microlink/www by driving the Gatsby dev server with agent-browser.

    142 GitHub stars~311 tokensUpdated yesterday
    Auto-check passed

  • Alternative Landing

    microlinkhq/www

    Create or improve competitor alternative pages under src/pages/alternative/.

    142 GitHub stars~5.2k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Guide Authoring

What does Guide Authoring do?

Create or revise docs guides under src/content/docs/guides with runnable MDX examples. Guide Authoring is an agent skill from microlinkhq/www. Create or revise docs guides under src/content/docs/guides with runnable MDX examples.

When should I use Guide Authoring?

Guide Authoring fits situations like: tasks that involve Markdown.

How do I install Guide Authoring in Claude Code?

Run `npx skills add microlinkhq/www --skill guide-authoring -a claude-code`. Or copy the skill folder (.cursor/skills/guide-authoring in microlinkhq/www) into .claude/skills/guide-authoring in your project. Claude Code loads it when a task matches its description.

How do I install Guide Authoring in Codex?

Run `npx skills add microlinkhq/www --skill guide-authoring -a codex`. Or copy the skill folder (.cursor/skills/guide-authoring in microlinkhq/www) into .agents/skills/guide-authoring in your project. Codex loads it when a task matches its description.

Can I use Guide Authoring in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microlinkhq/www --skill guide-authoring -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/guide-authoring, .gemini/skills/guide-authoring, .github/skills/guide-authoring and .opencode/skills/guide-authoring in your project.

What does Guide Authoring need to run?

SKILL.md names no scripts, command-line tools or credentials: Guide Authoring is instructions for the agent only.

Does Guide Authoring access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Guide Authoring safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Guide Authoring use?

Guide Authoring is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Guide Authoring use?

About 2.5k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Guide Authoring?

Skills that share tags, products or a category with Guide Authoring: Markdown Article Formatter (JimLiu/baoyu-skills, 26k stars), Markitdown (ImCa0/just-laws, 781 stars), Obsidian Markdown (Atmosphere/atmosphere, 3.8k stars) and Gzh Design (isjiamu/gzh-design-skill, 3.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Guide Authoring?

microlinkhq (a GitHub organization) maintains it in microlinkhq/www, which has 142 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 6, 2026.

Source: microlinkhq/www on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.