agentleFS
Sign inStart free
Wsh7AshWsh7Ash/skillmcp/skills/tool-surface-minimisation/SKILL.md

tool-surface-minimisation

Skill0 starsChanged 14 days agoMITView on GitHub

Ship the fewest tools that cover the workflow, because every extra tool is a wrong choice waiting to happen. Use when a server is accumulating tools and the list is getting hard for a model to choose from

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Remove tools that duplicate another tool's output

    line 22
  2. Distinctive:

    Keep one discovery tool, one fetch tool and the minimum for the domain

    line 23
  3. Distinctive:

    Check that each remaining tool has a distinct reason to exist

    line 24
  4. Distinctive:

    Document the removal so a later contributor does not re-add it

    line 25
  5. Distinctive:

    every tool maps to a distinct workflow step

    line 62

≈ “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

Tool Surface Minimisation

Ship the fewest tools that cover the workflow, because every extra tool is a wrong choice waiting to happen

Use when: a server is accumulating tools and the list is getting hard for a model to choose from

Avoid when: the server is new and its first three tools are still being validated

Procedure

  1. List every tool and the workflow step it serves
  2. Merge tools that differ only by an argument value
  3. Remove tools that duplicate another tool's output
  4. Keep one discovery tool, one fetch tool and the minimum for the domain
  5. Check that each remaining tool has a distinct reason to exist
  6. Document the removal so a later contributor does not re-add it

Signals

  • each tool maps to one workflow step and no two overlap
  • the tool list fits on one screen
  • a model choosing between two tools cannot pick wrong
  • removed tools are recorded with the reason

Patterns

1. Core trio

list_packs, search_skills, get_skill

2. Merge candidate

get_skill_by_tag folds into search_skills

3. Removal note

removed dump_all: unbounded output, replaced by search

Pitfalls

  • Adding a tool per keyword instead of making search better
  • Keeping a convenience tool that returns unbounded output
  • Removing a tool without noting why, so it returns in six months

Done when

  • every tool maps to a distinct workflow step
  • removals are recorded with their reason

References

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.

Check your setup, free