agentleFS
jezwebjezweb/vite-flare-starter/skills/save-research-doc/SKILL.md

save-research-doc

Skill49 starsChanged 3 months agoMITView on GitHub

Save a piece of research, notes, or content to the user's filesystem as a well-organised markdown document with metadata. Use when the user asks to save, archive, file away, or "keep this for later".

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After producing a substantial result the user wants to retain

    line 12
  2. Distinctive:

    All lowercase, hyphens not spaces

    line 22
  3. Very specific:

    Use offer_choices: "Open the file", "Save another version", "Add to a topic index", "Done"

    line 45
  4. Distinctive:

    Always add the date — future you needs to know when this was true

    line 49
  5. Distinctive:

    Don't save without permission if the conversation didn't explicitly ask

    line 53
  6. Very specific:

    Don't overwrite without warning.

    line 54
  7. Distinctive:

    Don't save sensitive data (passwords, keys, personal info that shouldn't be persisted)

    line 55
  8. Distinctive:

    Don't dump raw chat transcript — synthesise the useful content

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Save Research Document

When to use

  • "Save this for me"
  • "File this under [topic]"
  • "I want to keep this research"
  • After producing a substantial result the user wants to retain

Steps

  1. Identify what to save — usually it's the most recent assistant output. If ambiguous, confirm via ask_questions.
  2. Decide on path and filename:
    • Top-level folder by topic: research/, notes/, briefs/, code/, drafts/
    • Filename with date for time-sensitive content: YYYY-MM-DD-slug.md
    • Otherwise descriptive slug: analyse-pricing-strategy.md
    • All lowercase, hyphens not spaces
  3. Add frontmatter — the document gets YAML frontmatter for searchability:
    ---
    title: [Document title]
    created: [ISO date]
    tags: [tag1, tag2]
    summary: [One-sentence summary]
    sources: [optional list of URLs cited]
    ---
  4. Format the body:
    • H1 title at the top
    • Source content cleaned up (preserve markdown formatting)
    • Inline source links if research-based
    • Footer with "Last updated: [date]"
  5. Write the file — call fs_write with the path and content.
  6. Confirm and offer follow-ups:
    • Show the path and size via plain message
    • Use offer_choices: "Open the file", "Save another version", "Add to a topic index", "Done"

Style

  • Generous structure. Use headings, bullet points, dividers — make it scannable later.
  • Always add the date — future you needs to know when this was true
  • Cross-link related saved docs if you know about them (call fs_list to check)

What not to do

  • Don't save without permission if the conversation didn't explicitly ask
  • Don't overwrite without warning. Check fs_read first; if exists, ask via confirm_action
  • Don't save sensitive data (passwords, keys, personal info that shouldn't be persisted)
  • Don't dump raw chat transcript — synthesise the useful content

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.

Reviews can't be read right now.

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.