agentleFS
preetamnathpreetamnath/agent-skills/skills/structure-prose/SKILL.md

structure-prose

Skill4 starsChanged 7 months agoMITView on GitHub

Reshape one prose block into a list or table when it fuses several independent rules, keeping each claim's wording. TRIGGER when: user says 'break this up', 'wall of text', 'should this be a list/bullets', 'structure this paragraph'; a dense block buries rules a reader needs to jump to.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Leave shrinking or clarifying to tighten-instruction.

    line 26
  2. Distinctive:

    Test each label: read its item without the label.

    line 27
  3. Distinctive:

    Remove the label if the item is just as easy to find.

    line 28
  4. Distinctive:

    If a caller owns a file-level gate, return the score and proposal without editing.

    line 31

≈ “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

Structure Prose

Primitive: FUSED-BLOCK — does the block state several independent rules, or one connected chain of reasoning?

Steps

  1. Count the block's distinct claims — rules, facts, or cases that stand alone. 1–2 claims, or a block that already scans in one line → prose is fine; stop.
  2. Apply the fused-block test. Independent — items make sense in any order, even after a shared setup → structure them. One chain — each sentence sets up the next (a narrative, a causal argument, an explanation that builds) → keep prose; stop.
  3. Pick the shape:

    ShapeWhen it helps
    Plain bulletsEach item is easy to find by its opening words.
    Labeled bulletsA brief label makes an item easier to find.
    Numbered listOrder matters.
    TableItems share comparable fields, and columns make them easier to compare.
  4. Reshape, content verbatim:
    • Move each claim into an item without changing its words.
    • For labeled bullets, use a short bold label that adds no claim.
    • Leave shrinking or clarifying to tighten-instruction.
  5. Test each label: read its item without the label.
    • Remove the label if the item is just as easy to find.
    • Rename a useful label that misnames the item.
  6. Score and gate the edit. Score confidence 0.00–1.00 that the claims remain verbatim and the new shape scans better.
    • If a caller owns a file-level gate, return the score and proposal without editing.
    • Otherwise, apply at c ≥ 0.80; below that, keep the prose block and report the proposal as held.

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.