agentsclimarketplace

Cms fields writer

Skill ur-grue/autopunk-media-skills/skills/archive-legal/cms-fields-writer

Generates the complete set of metadata fields — tags, categories, keywords, slug, and summary — needed to publish a piece of content in a content management system, ready to copy and paste into each field.From its SKILL.md

Install
npx -y skills add ur-grue/autopunk-media-skills --skill cms-fields-writer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 21 stars21 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.8 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

CMS Fields Writer

What This Skill Does

Generates the complete set of metadata fields — tags, categories, keywords, slug, and summary — needed to publish a piece of content in a content management system, ready to copy and paste into each field.

When To Use This Skill

  • You have finished writing or editing a piece and need to fill in all the CMS fields before publishing
  • A sub-editor or social media manager needs to hand off a complete metadata package with the article
  • You are republishing or updating archived content and need to refresh its metadata to current house style
  • You are onboarding a new contributor and want to show them a standard metadata set for a typical article

What You Need To Provide

Required:

  • The article or content text (paste the full text, or a detailed summary if the piece is very long)
  • Publication name or type (e.g. "daily news site", "monthly trade magazine", "broadcast news service")

Optional:

  • Your tag taxonomy or category list — paste your site's existing categories so the assistant matches them exactly rather than inventing new ones
  • Maximum number of tags permitted by your CMS
  • Preferred slug format (e.g. lowercase-hyphenated, date-prefixed)
  • Whether a meta description is needed in addition to the on-page summary
  • Audience or section (e.g. "Politics section", "consumer-facing")

How the Assistant Approaches This

  1. Reads the content and identifies the primary topic, secondary topics, named entities (people, places, organisations, events), and content format (news, feature, opinion, explainer).
  2. Maps these to the metadata fields typically required by a CMS: title tag, slug, category, primary tags, secondary tags, keywords, and summary or standfirst. If a category list was provided, it matches categories to that list exactly.
  3. Presents each field on its own clearly labelled line so you can copy individual values directly into each CMS input field without reformatting.

Output Format

A labelled list, one field per line, with no additional commentary. Each label is followed by a colon and the value. Tags and keywords are comma-separated on a single line. The summary is a single sentence of 25–35 words in active voice. The slug is lowercase and hyphenated. Example structure:

Title tag: ...
Slug: ...
Category: ...
Primary tags: ..., ..., ...
Keywords: ..., ..., ..., ...
Summary: ...
Meta description: ... (if requested)

No markdown formatting inside field values. No quotes around values unless they contain commas. Output is ready to paste as-is.

Quality Criteria

  • Every field is populated — no blank fields, no "TBD" placeholders
  • Tags and keywords use consistent capitalisation (typically sentence case for display tags, lowercase for keywords)
  • The slug is URL-safe: lowercase, hyphenated, no special characters, no stop words
  • The summary reads as a complete sentence that would work as a standfirst or search result snippet
  • If a category list was provided, the selected category exists in that list verbatim
  • Tag count does not exceed any maximum stated by the user
  • No keyword stuffing — each keyword adds distinct search value

Example

Input

Article text: A major study published this week found that urban cycling infrastructure directly correlates with reduced emergency hospital admissions for cardiovascular disease. Researchers tracked data from 47 cities across Europe over a ten-year period. Cities that invested in protected cycle lanes saw a 19% reduction in heart-attack-related admissions compared to cities with no dedicated cycling infrastructure. The lead researcher said the findings should be a "wake-up call" for city planners prioritising road space for private vehicles. The study was conducted by a consortium of public health universities and published in a peer-reviewed journal.

Publication type: Daily news website, general audience Category list: Health, Environment, Transport, Politics, Science, Business, World, Opinion Maximum tags: 5

Output

Title tag: Urban cycling infrastructure linked to 19% drop in heart attack hospital admissions, study finds Slug: urban-cycling-infrastructure-heart-attack-hospital-admissions-study Category: Health Primary tags: Cycling, Public health, Urban transport, Heart disease, Research Keywords: cycling infrastructure, cardiovascular health, hospital admissions, city planning, cycle lanes, European cities Summary: A ten-year study of 47 European cities finds that protected cycle lanes are associated with a 19% reduction in heart-attack-related hospital admissions.

Known Limitations

  • If you do not provide your CMS's category list, the assistant will generate plausible categories that may not match your actual taxonomy — always check before publishing.
  • This skill works best with a complete article text. Summaries or bullet-point notes produce less precise keyword sets because topic nuance is lost.
  • The assistant cannot access your CMS directly. All field values must be manually entered. This skill produces the text only.
  • For very long articles (over 3,000 words), paste the introduction, subheadings, and conclusion rather than the full text to stay within input limits while preserving enough context for accurate tagging.

Related Skills

What ships with it: 1 file

83 B alongside SKILL.md

Gives 0 of the 12 instructions most docs writing skills give in ~1.1k tokens

Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06

  • Use third-person for skill descriptionsin 54 of 1951, across 35 files
  • Start descriptions with Use whenin 43 of 1951, across 29 files
  • Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
  • Use active voicein 40 of 1951, across 36 files
  • Map file responsibilities before defining tasksin 36 of 1951, across 29 files
  • Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
  • Ask one question at a timein 35 of 1951
  • Offer execution options after saving the planin 33 of 1951, across 24 files
  • Include complete code in every stepin 33 of 1951, across 27 files
  • Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
  • Announce the skill usage at the startin 30 of 1951
  • Verify agent compliance after adding the skillin 29 of 1951, across 17 files

Said here and by no other author read

  • Read the provided content text
  • Map content to required CMS fields
  • Match categories to provided list
  • Format tags and keywords as comma-separated
  • Write summary as one active sentence
  • Ensure no blank fields

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.