agentleFS
mementomori-comementomori-co/maker-mastery/.claude/skills/research-one/SKILL.md

research-one

Skill2 starsChanged 26 days agoMITView on GitHub

Use when ONE narrow question needs primary sources before it can be verified and filed. Runs the researcher in a fresh context and writes a claims table to research\inbox\<topic>\<question>.md; /research-topic calls this once per question.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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:

    Write the claims table in the researcher's required format: # | claim | value / short quote | source URL | official / community | version …

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Overview

Input: $ARGUMENTS, three fields separated by |: topic slug, question slug, the question.

When to use

One narrow question, answerable from one or two primary pages. For a whole topic use /research-topic; for checking an existing claim use /verify.

Steps

  1. Parse the three fields. Output path: research\inbox\<topic-slug>\<question-slug>.md.
  2. Fetch primary sources (official first: wiki.bambulab.com, the Bambu store and TDS pages, the BambuStudio GitHub source, then staff forum posts; community sources labelled "community"). On HTTP 402/403 use curl -sL -A "Mozilla/5.0" <url> -o <scratch file under work\> and read the file.
  3. Write the claims table in the researcher's required format: # | claim | value / short quote | source URL | official / community | version or date on page, then ## Not found and ## Pages fetched. Keep quotes short (about 15 words); paraphrase the rest.
  4. Return only the path and counts (claims, official, community, not found).

Common rationalizations

RationalizationReality
"I remember this from training."Memory is not a source. Fetch it, or write it under Not found.
"The search snippet shows the number."A snippet is not the page. Fetch it or mark "snippet only".

Red flags

  • A row without a URL fetched this run.
  • A number without unit, condition, or version.

Verification

  • File exists at the output path.
  • Every row has a fetched URL and a quote.
  • Community rows labelled; Not found lists what was searched.

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.