agentleFS
shangyiyshangyiy/life-kit/skills/presentation/find-the-argument/SKILL.md

find-the-argument

Skill10 starsChanged 7 days agoMITView on GitHub

Find the single argument underneath raw thinking (notes, a spoken or written monologue, voice notes, a draft or an outline) and rebuild the reasoning around it, or review an existing outline or draft for whether one argument holds it together and what reasoning it lost. Use for a thesis and outline from notes or voice notes, for checking a draft's structure, or on /find-the-argument.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Keep the understanding, not the thinking process: Treat raw thinking as thinking, not dictation.

    line 21

≈ “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

/find-the-argument

People think in observations: they explore ideas, revisit them and correct themselves. Good communication is organized around an argument. Use these to do the work or to review it; in a review, check the outline or draft, and its source thinking when given, and name each lapse once, with its fix. The request decides what to produce.

Principles

  1. One argument, not a summary. The argument is the single idea that makes the other ideas feel inevitable. Find it by asking what the author is actually trying to convince someone of, what the audience should remember if they remember only one thing, and why all these ideas belong in the same conversation. Prefer one coherent argument over several disconnected good ideas.
  2. Keep the understanding, not the thinking process. Treat raw thinking as thinking, not dictation. The result reads as though the author had explained the idea clearly from the beginning: the reasoning survives, the false starts, detours and wording do not.
  3. The argument decides what stays. Keep every piece of the author's final reasoning that bears on the argument: evidence, explanation, implications, limitations, and uncertainty where it matters. A limitation or an open question that bears on the argument is part of it, so keep it even when it weakens the case. Remove what does not bear on it: filler and tangents.
  4. Merge what repeats. Ideas that make the same point become one. Where the author changed their mind, the later reasoning replaces the earlier one unless the change itself matters to the argument.
  5. Organize by what each idea explains, never by when it appeared. Separate the thesis from its support, and give each idea its role: observation, hypothesis, conclusion, evidence, explanation, example, implication, limitation, open question or tangent. Order follows the logical relations between ideas, such as observation to implication, problem to cause to solution, hypothesis to evidence, principle to example, or a lesson learned, whichever the material calls for.
  6. The outline feels inevitable. Someone reading only the section titles can reconstruct the overall reasoning.

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.