agentleFS
robertmnyborgrobertmnyborg/everyday-agent-skills/skills/tool-fit/SKILL.md

tool-fit

Skill0 starsChanged 8 days agoMITView on GitHub

Judge whether an external tool, repo, app, or service is worth using for the user. Use when the prompt is a GitHub or product URL plus "can I use this?", "what can this do for me?", "what can I do with this", "is this useful / valuable to my workflow", or "will it add value to my output".

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the README, the license, the latest release or commit date, and the install requirements.

    line 12
  2. Distinctive:

    If it runs code locally or calls the network, look at what it sends and where.

    line 14
  3. Distinctive:

    Write the answer in the shape below.

    line 15
  4. Distinctive:

    Do not install, sign up, or run the tool until the user says so.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

tool-fit

The user sends a link and asks whether it is worth their time. The answer is a verdict they can act on in one read, not a summary of the README.

Procedure

  1. Read the README, the license, the latest release or commit date, and the install requirements. Check that the requirements match this machine (uname -a, plus sw_vers on macOS) when it is a local install.
  2. Find what it overlaps in the existing setup. Search the descriptions in ~/.claude/skills/*/SKILL.md, the hooks in ~/.claude/settings.json, the user's scripts directory if they keep one, and the MCP server list for the same job. Name the overlap, or say "no overlap" and what you searched.
  3. If it runs code locally or calls the network, look at what it sends and where. Grep the source for endpoints when the repo is small enough to read.
  4. Write the answer in the shape below.

Answer shape

  • Verdict: yes, no, or "only if <one condition>", in the first line. In the whole answer, name at most one thing that would make it worth trying, or one cheap test. Never a list of conditions.
  • What it is: one or two sentences in plain words, with one concrete example of its use for the user's work.
  • Overlap: what it duplicates or beats in the current setup, by name.
  • Checks: license (personal use, and commercial use at the user's employer if it is for work), maturity (version, last commit, one maintainer or many), privacy (what leaves the machine).
  • Next step: the install command or the one-line trial, only if the verdict is yes.

Do not install, sign up, or run the tool until the user says so.

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.