agentleFS
forsvn-labsforsvn-labs/meta-skills/skills/write-longform/SKILL.md

write-longform

Skill14 starsChanged 3 months agoMITView on GitHub

Research, structure, and write a substantive long-form argument. Use for founder essays, articles, thought leadership, guides, reports, or other long-form work that needs a defensible thesis, evidence, examples, objections, original synthesis, and a finished publishable draft.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use invented anecdotes, citations, customers, results, or authority.

    line 27
  2. Distinctive:

    Write in the requested author/brand voice.

    line 37
  3. Distinctive:

    every factual claim is traceable.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Write a defensible long-form argument

Produce a finished piece that advances one consequential thesis. Length is a consequence of the argument, not the goal.

Establish the thesis and evidence

State the audience, decision or belief the piece should change, thesis, strongest objection, and why the author has standing to make the argument.

Build an evidence map before drafting:

  • observed facts with current primary sources;
  • operator-supplied experience and examples;
  • reasonable inferences labeled as such;
  • representative or hypothetical examples labeled clearly;
  • claims that remain unknown and what would establish them.

Do not use invented anecdotes, citations, customers, results, or authority.

Build the argument

Outline the minimum sequence needed to prove the thesis. Each section must introduce evidence, resolve an objection, distinguish an alternative, or advance the conclusion.

Open with the costly tension rather than a generic topic introduction. Explain mechanisms, not only positions. Steelman the strongest objections and name where the argument does not apply.

Write in the requested author/brand voice. Use specificity, varied sentence structure, concrete examples, and transitions that show why the next section follows. Avoid fragment-heavy “thought leadership,” empty aphorisms, and summary that merely repeats headings.

Review

Check:

  • thesis remains stable and non-obvious;
  • every factual claim is traceable;
  • examples do not masquerade as evidence;
  • objections receive substantive answers;
  • the conclusion creates a decision or operating principle;
  • removing a paragraph would either improve focus or break the argument.

Deliver

Return the finished piece, title/deck when useful, a short source/claim note, and any fact that must be verified before publication. Publishing and external submission remain human-owned.

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.