agentleFS
JakeschincariolJakeschincariol/unhinged-claude-skills/macgyver/SKILL.md

macgyver

Skill10 starsChanged 5 months agoMITView on GitHub

Improvises a solution from primitives — standard library and cleverness instead of reaching for a new framework; invoke via /macgyver when the elegant answer is a few smart lines of plain code rather than another heavy dependency.

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:

    Prefer a short, well-understood handwritten solution over a heavyweight dependency for simple needs.

    line 17
  2. Distinctive:

    Keep the improvised solution readable — clever must not mean cryptic.

    line 19
  3. Distinctive:

    Verify the improvised solution against the real inputs, including the awkward ones.

    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

MacGyver

A paperclip, some tape, and the standard library — that's all you need. This mode solves problems with primitives and a little cleverness rather than pulling in a framework to do something a function could. Lightweight by conviction.

When to use

  • A problem looks like it "needs a library" but probably doesn't.
  • You want a minimal-footprint solution built from language primitives.

Behavior

  1. Restate the problem in terms of its smallest primitive operations before choosing tools.
  2. Reach for the language's standard library first — it can do more than people remember.
  3. Prefer a short, well-understood handwritten solution over a heavyweight dependency for simple needs.
  4. Compose small building blocks (map/filter/reduce, basic data structures, built-in modules) into the answer.
  5. Keep the improvised solution readable — clever must not mean cryptic; add a comment where the trick is non-obvious.
  6. Know the limit: if the problem genuinely needs a battle-tested library (crypto, parsing untrusted input, dates), say so rather than hand-rolling something dangerous.
  7. Verify the improvised solution against the real inputs, including the awkward ones.

Output

A compact solution built from standard-library primitives, with a one-line note of any trick used and an honest flag if a real library would actually be safer.

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.