Auto Run — Development skill for Claude Code
Autonomous personalized research loop — set a topic, get a quality-gated report.
How to install Auto Run
Installs to ~/.claude/skills/primeline-ai-claude-adaptive-research-auto-run/SKILL.md
mkdir -p ~/.claude/skills/primeline-ai-claude-adaptive-research-auto-run && curl -fsSL https://raw.githubusercontent.com/primeline-ai/claude-adaptive-research/HEAD/commands/auto-run.md -o ~/.claude/skills/primeline-ai-claude-adaptive-research-auto-run/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Auto Run does
description: "Autonomous personalized research loop — set a topic, get a quality-gated report" arguments:
- name: topic description: "Research topic (free text) or --preset name or --setup for first-time configuration" required: false
/auto-run
Autonomous research loop with quality gate and personalized adaptations.
FIRST RUN CHECK
Check if `_autonomous/config.yaml` exists in the current project directory.
**If NOT exists → run setup automatically:**
- Show the user
Alternatives in Development
- Ralph Loop — Autonomous coding loop — works through tasks, commits, repeats 14k ★
- Ralphy — My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & 2.8k ★
- /autopilot — Autonomous hunt loop with deterministic scope safety and configurable checkpoints 1.2k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Supervisor Drive
Autonomous orchestrator — survey state, pick the right OMCR engine, run it, re-evaluate, loop. Interactive by
Max Research
Nuclear-scale autonomous research — deploys 500-1000 agents in ONE massive simultaneous wave for exhaustive to
Autoloop
Autonomous recursive improvement loop for a single target. Runs gap analysis, recursive refinement, evaluation
Research To Deck
End to end - run /research on a topic, then /deck on the resulting report; produces the cited report, the HTML
Pi
PI Wisdom-in-Action Engine v23 — top mandates, scene router, delivery quality gates, anti-patterns, battle mom
Vault Autoresearch
3-round autonomous research loop with intermediate notes and synthesis
Related Agents
Safe Build
Autonomous reversibility-first implementer — executes code/UI changes through the safe-build checkpoint loop (
Research Loop
Autonomous iterative research loop — hypothesis, search, ingest, evaluate, keep/discard via checkpoint. Max 3
Applier 2
Generates copy-paste answers for job application forms based on pipeline research. Human-in-the-loop — never a