agentleFS
Sign inStart free
ansvisoransvisor/ansvisor/skills/create/SKILL.md

create

Skill233 starsChanged 5 months agoMITView on GitHub

Writes briefs, articles, FAQ blocks, comparison pages and social posts from what AI engines ask and cite.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use status.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only these, for the chat's brand and the topic or page the person names:

    line 17
  2. Very specific:

    Use list_brands only when no brand is selected, and open_page to link the Content Library.

    line 26
  3. Distinctive:

    Ask the format (brief, article, FAQ block, comparison page or social post), the target page and the length only when the request doesn't …

    line 32
  4. Distinctive:

    Write the piece answer-first: a direct answer under each heading, then detail.

    line 38
  5. Distinctive:

    Never publish: going live is always the person's click.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Create content

The playbook of the /create shortcut ("Create content for …"): a piece of content written to be cited by AI engines, from the brand's prompts, fan-outs and the pages AI cites now.

Data plan

Read only these, for the chat's brand and the topic or page the person names:

  1. list_prompts, get_prompt_performance and list_topics: the prompts the piece should win, and how the brand does on them.
  2. get_fanouts and get_prompt_insights: what the engines search for behind those prompts, and which matter most.
  3. list_citations: the pages AI cites for them now.
  4. fetch_page for one or two of those cited pages, and for the brand's own page when the piece updates it.
  5. list_content_opportunities, when the person names no topic.
  6. list_drafts and get_draft: a draft already open for the same page.

Use list_brands only when no brand is selected, and open_page to link the Content Library.

Scope: the last 30 days, every platform the plan tracks.

Questions

  • Ask the format (brief, article, FAQ block, comparison page or social post), the target page and the length only when the request doesn't say and the answer changes what you write. Two questions at most, together.

Steps

  1. Pick the questions the piece must answer: the prompts and fan-outs with the most demand.
  2. See what the cited pages answer, and what they leave out.
  3. Write the piece answer-first: a direct answer under each heading, then detail. For an FAQ or a comparison page, add the structured data as a code block.
  4. When the person wants it kept, save it as a draft with create_draft; the app asks them first when it should. In an agent's run nobody is there to ask: always save it with its tool, and the app holds it for approval where the agent's mode needs it.

Output

The piece as a document, with its structured data as code when it has some.

Next moves

Two or three, such as opening it in the Content Editor, or an FAQ block for the same prompts.

Don't

  • Public content: no tracking numbers unless the person asks, no weak or made-up statistics, and use [placeholders] for facts, quotes and figures the person must give.
  • Never publish: going live is always the person's click.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free