Auto Itera

Use when the user wants to autonomously search for the best AI/engineering approach across competing candidates (prompts, models, retrieval strategies, architectures, algorithms) — give it a goal + candidate arms + success threshold, it runs the experiment to a defensible ship-or-kill verdict. Autonomously handles sourcing real production data, scoring arms in parallel, diagnosing per-row, sprint-and-generalize iteration, and writing the conclusion doc. Built-in safeguards (held-out test discipline, variance-floor checks, generalization gates) keep the verdict trustworthy.

6 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add clfhaha1234/auto-itera --skill auto-itera

Manual install

git clone --depth 1 https://github.com/clfhaha1234/auto-itera.git /tmp/auto-itera
mkdir -p ~/.claude/skills
cp -r /tmp/auto-itera/. ~/.claude/skills/auto-itera

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Auto Itera

## Overview

**Autonomous experimentation engine for AI engineering decisions.** You provide three things — a goal, the candidate approaches, and a success threshold. auto-itera does the rest: sources real production data, scores baseline + arms in parallel, diagnoses per-row, iterates in disciplined sprints, runs the held-out test pass, and writes a one-page conclusion doc with publication-quality charts.

The pivot: **AI engineering decisions move from handcrafted trial-and-error to autonomous scientific search.** Instead of opening a notebook and eyeballing diffs, you delegate the whole experimental loop and get back a verdict you can defend in a code review.

Internally the loop is a six-phase scientific method — **Frame → Source → Metric → Run → Diagnose → Conclude** — with sprint-and-generalize refinement (not unbounded iteration, not arbitrary hard caps). The autonomy lives in phases 1, 3, 4, and 5; phases 0 (Frame) and 2 (Metric pre-registration) are the user-provided inputs that anchor the search.

**Honest expectation boundary**: auto-itera autonomously *runs* the experiment given a goal and candidate arms. It does **not** autonomously brainstorm what to test — you (or the human asking Claude) still write the candidate prompts / pick the candidate models / define the metric. The autonomy is "from candidates to verdict", not "from blank slate to verdict".

Read the full skill on GitHub

Details

Skill name: auto-itera
Repository: clfhaha1234/auto-itera
License: MIT
Repo updated: 3 June 2026

FAQ

What does the Auto Itera skill do?

How do I install the Auto Itera skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add clfhaha1234/auto-itera --skill auto-itera. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Auto Itera popular?

It lives in clfhaha1234/auto-itera, which has 6 GitHub stars and 0 forks.

Related skills

Chinese De AI Writing

tangwenwen-md/chinese-de-ai-writing

中文去 AI 味：审稿、改稿、写作、流水线审核四种模式，专管简体中文。规则按证据分级：只有人机语料实测成立的特征才当硬规则，社区共识特征要"命中且空泛"才改，已被实测推翻的流行规则（调句长、删设问、删比喻、加口语词、加错别字、同义词替换）明确不用。最高约束是信息守恒：不编造经历、病例、数字、引文，不改论断强度。医学内容尤其如此。附 scripts/zh_ai_scan.py：量化扫描破折号、翻案腔、提示性冒号、段首零回指等 10 项实测特征，给出每千字密度和人机基线对照。文体分档：小红书/社媒、口播稿与短剧台词旁白、科普、正式文书（标书、汇报、公文）、中文学术。触发词：「去AI味」「去 AI 味」「AI味太重」「AI腔」「一眼AI」「像AI写的」「不像人话」「说人话」「改得像人写的」「这段有没有AI味」「帮我审一下AI味」「口播稿太书面」「台词不像人说的」「小红书文案太AI」「标书AI味」「中文humanize」。也用于 Claude 自己产出中文正文（小红书文案、科普稿、台词、汇报）之后的自检。不管：英文文本；以"降低知网/朱雀 AIGC 检测率"为唯一目标的改写（本 skill 改的是写法，不承诺过检测，也不用错别字、回译等对抗手段）；视觉层面的 AI 味；剧情结构与留存。

AI, LLMs & Agents

Aperture

lukethecat/aperture

A skill for AI agents that want to produce better daily reports and discover more of what their users actually want. Scans source front pages, diffs them against yesterday, prescreens with a weighted profile, reviews with an LLM, deduplicates, publishes, and evolves the profile from user feedback. All decisions go to an append-only tape for audit and replay.

AI, LLMs & Agents

Claude Code Starter

cassmtnr/claude-code-starter

Analyze a project's tech stack and generate comprehensive Claude Code configuration files (.claude/ directory with CLAUDE.md, skills, agents, rules, and commands). Use when setting up Claude Code for a new or existing repository.

AI, LLMs & Agents

AI Slop Cleaner En Ru

tuwulalo/ai-slop-cleaner-en-ru

Detect and clean AI-generated text ("AI slop"), bilingual EN + RU. Use to rewrite AI clichés, "it's not just X, it's Y", "delve", "under the hood", "важно отметить", "под капотом", the rule of three, into natural human prose, or to check whether text was written by a neural network / ChatGPT and rate its "AI-likeness". Detects the text's register first (official / press / blog / forum) and rewrites within it: no slang in a formal post, no officialese in a casual one. Tells decorative AI emoji (🚀💡✅ markers) from genuine human emoji. Двуязычный детектор и чистильщик ИИ-текста: проверить, напис

AI, LLMs & Agents

Create Operator

riceshowerX/arknights-operator-skill

Distill an Arknights operator into an AI Skill. Generate Knowledge + Persona with 5-layer structure, evolution support. | 将明日方舟角色蒸馏成AI Skill，生成知识库+5层人格，支持持续进化。

AI, LLMs & Agents

AI Citation Auditor

madrank8/ai-citation-auditor

Audit any page to predict whether AI search engines (Google AI Overviews and AI Mode, ChatGPT, Perplexity, Gemini, Claude) will cite it, then return a prioritized fix list. Scores 6 dependency-free layers gated by a retrieval-rank prerequisite: answer-first extractability, evidence corroboration, consensus alignment, source-quality fingerprint, SEO-slop detection, and machine structure. Runs on native web fetch and search or on pasted content, with no paid APIs, connectors, or crawlers required. Two modes: AUDIT (URL or draft in, scored scorecard plus fixes out) and REWRITE (turn one section i

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.