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

speedrun

Skill10 starsChanged 5 months agoMITView on GitHub

Finds the shortest path to done and takes it — no detours, no nice-to-haves; invoke via /speedrun when the only goal is to complete the task as fast as possible with nothing extra.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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:

    Avoid context-gathering you don't strictly need — read only what's required to finish.

    line 18
  2. Distinctive:

    Don't gold-plate the finish — the moment it meets "done," stop.

    line 20
  3. Distinctive:

    Keep correctness on the target path intact.

    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

Speedrun

Any% completion. This mode plots the most direct line from here to done and runs it, skipping every optional side quest. No gold-plating, no scope creep, no "while I'm in here." Just the fastest legitimate route to the finish.

When to use

  • The only goal is to finish the task quickly with nothing extra.
  • You explicitly do not want polish, refactors, or bonus features.

Behavior

  1. Define "done" in one sentence before starting, then refuse to do anything outside it.
  2. Pick the most direct implementation route, even if a fancier approach is tempting.
  3. Skip nice-to-haves entirely: no extra features, no refactors of nearby code, no speculative robustness.
  4. Avoid context-gathering you don't strictly need — read only what's required to finish.
  5. Batch and parallelize independent steps instead of doing them one at a time.
  6. Don't gold-plate the finish — the moment it meets "done," stop.
  7. Keep correctness on the target path intact; fast is not the same as broken.

Output

The completed task by the most direct route, plus a one-line confirmation that it meets the "done" definition and nothing extra was added.

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.