SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

optim-agentOptim-Agent/optim-agent

Hands the run-experiment / read-result / pick-next-point tuning loop to an AI agent, so hyperparameter optimization adva…

No ratings yet Rate this skill
Stars801
Forks43
Watchers801
Open Issues1

InstallOne-line install

Installable · 19 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add Optim-Agent/optim-agent

19 more are not listed — run npx skills@latest add Optim-Agent/optim-agent --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Hands the run-experiment / read-result / pick-next-point tuning loop to an AI agent, so hyperparameter optimization advances automatically within a limited budget and ends with reproducible conclusions. Key capabilities include: 1. System understanding: reads the evaluation entry point and related files to clarify the objective function, parameter space and run procedure, avoiding experiments built on wrong assumptions; 2. Experiment definition and baseline: confirms the scalar objective, search range and budget, and runs a baseline result as the anchor for later comparison; 3. One informed trial per round: runs exactly one parameter point chosen from current information, records the result and updates its view of the parameter space; 4. Next-point selection: picks the next candidate from past trials plus semantic proposals, favoring high-leverage directions under small budgets; 5. Stop and report: stops when the budget or convergence condition is met, and outputs the best configuration, trial trajectory and a conclusion report.

Use Cases

machine learning model tuning, hyperparameter search for training scripts, budget-limited experiment iteration, tuning tasks that need a complete trial record.

Target Roles

AI / Algorithm Engineer, Data Analyst / Data Engineer, Backend Developer, Full-stack / Indie Developer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1794
Data sourceGitHub
RepositoryOptim-Agent/optim-agent
CategoryAI & Agents / AutoML & Hyperparameter Optimization
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1292603082
Node IDR_kgDOTQuOyg
Rank#906 (position within the source ranking)
Site-wide popularity rank#1021 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02505007501k2026-09-282026-10-112026-09-28 · 9392026-10-11 · 801
  • Now801
  • Previous point · 09-28 939
  • vs previous point -138
  • 2 data points 13 days
02040602026-09-282026-10-112026-09-28 · 432026-10-11 · 43
  • Now43
  • Previous point · 09-28 43
  • vs previous point ±0
  • 2 data points 13 days

TimelineTimeline

Repository created2026-07-07 17:05:544 months ago
Data last updated2026-10-26 12:05:5621 days ago
Last commit2026-08-14 19:09:113 months ago

CommitLatest commit

Version [v0.1.1] committed by Optim-Agent. Update Category: Codebase Iteration & Routine Maintenance. Commit details: track paper/main.pdf, ignore other paper/ files. This update updates core functional modules and advances project iteration.

39e5f94 v0.1.1 Optim-Agent 2026-08-14

Next stepsNext steps