agentleFS
openjckopenjck/agent-skills/skills/organize-notes/SKILL.md

organize-notes

Skill0 starsChanged 5 months agoMITView on GitHub

Rewrite and reorganize rough notes, highlighting any action items.

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:

    When organizing the rough notes provided by the user, respond with text.

    line 11
  2. Distinctive:

    If you are unsure about anything, you can ask any number of questions, within reason, to clarify your understanding before you produce the …

    line 15
  3. Distinctive:

    If you received any notes in a non-textual format (e.g., photographs of pages in a notebook, a screenshot of a note-taking app, or an audio …

    line 56

≈ “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

When organizing the rough notes provided by the user, respond with text. You may use any text format that is appropriate, as long as you also follow the instructions below.

If you are unsure about anything, you can ask any number of questions, within reason, to clarify your understanding before you produce the final result.

In the final result, do not include any introductory text (e.g., "Here is the information you asked for...") or any closing text (e.g., "Let me know if you have any other questions..."). Print only the content that is described in these instructions.

Sections

Provide two top-level sections in your response, each clearly labelled.

Notes improved by AI

Label the first top-level section "Notes improved by AI". Directly below the header for this top-level section, print the following text in italics: "These notes were written with the help of AI based on rough notes that were provided to it." In this section, provide your improved notes, based on the rough notes that were shared with you. If, and only if, there are any action items, include two sub-sections: "Notes", for your improved notes, and "Action items", for a list of action items. If there are no action items, don't create any sub-sections; just print your improved notes. Try to group action items somewhat logically, putting related action items near each other and/or putting the action items in the order they should be completed.

For each abbreviation in the rough notes, if the abbreviation is non-obvious and you are confident about what it means, expand the abbreviation the first time it's used and put the abbreviation in parentheses (e.g., "DHCP" should become "Dynamic Host Configuration Protocol (DHCP)" if that's what the notes are referring to). Do not do this any other time the abbreviation is used, since once is enough. If you don't know what the abbreviation stands for, just use the abbreviation, rather than slowing things down by asking what it stands for.

Raw notes

Label the second top-level section "Raw notes". Directly below the header for this top-level section, print the following text in italics: "These are the raw, rough notes that were provided to AI as input for the above, improved notes." Below that, provide an identical copy of any textual notes that were shared with you.

If you received any notes in a non-textual format (e.g., photographs of pages in a notebook, a screenshot of a note-taking app, or an audio recording someone made to record important information), add one subsection for each of these sources. Make the subsection heading(s) use the title "Transcribed from [source]" where [source] is a human-readable description of the multimedia source (e.g., "a photograph of a page in a notebook" or "an audio recording"). In each subsection, put the transcribed notes described by the corresponding header.

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.