Skip to content
R

run

Run a single experiment iteration

by alirezarezvaniFree

Launch
#2673in AI Skills
0In stores

Description

Run is an agent skill that performs exactly one iteration of an experiment. It reviews the history, decides on a change, edits the target fi…

Highlights

  • Runs one experiment iteration: change, commit and evaluate
  • Keeps the change if it helps, discards it if not
  • Loads the experiment history before deciding a change
  • Lists experiments to pick from when none is named

Ratings & Reviews

No ratings yet

Be the first to rate run.

People also visit

R

resume

Resume a paused experiment

AI Skills
Launch
S

setup

Set up a new autoresearch experiment interactively

AI Skills
Launch
S

status

Show experiment dashboard with results, active loops, and progress

AI Skills
Launch
G

github

GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos

AI Skills
Launch
C

caveman-commit

Terse, conventional commit messages that prioritize reasoning over description

AI Skills
Launch
M

modelcontextprotocol/server-git

Read, search and analyze local Git repositories

AI Skills
Launch

run FAQ

What does run do?

It runs one experiment iteration: reviews history, edits the target file, commits, evaluates, then keeps or discards the change.

How is it different from loop?

Run does one iteration on demand. Loop repeats iterations on a schedule.

What if I do not name an experiment?

It lists the experiments and asks you to choose one.

How do I install it?

Run npx skills add https://github.com/alirezarezvani/claude-skills --skill run in your terminal.

Is it free?

The listing shows the skill as free.

What security audits has it passed?

skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Pass and Snyk Pass.

What are the best run alternatives?

Popular alternatives to run include resume, setup and status. See all run alternatives

Developer Stuff

Badges