Catalog-first agent workflows

Loops Radar

A searchable public index of reusable loops for agents, research, content, coding, and personal ops. Open a loop, copy the recipe, or submit an improvement.

Agent skill

Use Loops Radar in your coding agent.

Install the skill so your agent can search the catalog, choose a relevant loop, adapt the source markdown into the work ahead, and deliver daily or weekly loop digests from the public weekly feed. Ask for "Recommended today" when you want a compact daily outlook.

npx skills add georgewangyu/loops-radar --skill loops-radar -g

View repository

Contribute

Missing a loop?

Send a rough workflow through the full request form at the bottom of the page.

Go to full form

292 matching loops / showing 1-12Balanced sources

Goal recipe / GeorgeLoopsRefactor Until Architecture SettlesGive an agent a bounded architecture-refactor objective that continues until the design is coherent, real user-facing behavior has been exercised, and the result is reviewable.Open

Evaluation loops / Forward Future Loop LibraryThe full product evaluation loopA comprehensive product-quality workflow that evaluates realistic scenarios across every major capability, fixes weak outcomes, and reruns them to the defined bar.Open

Interval command loops / Awesome Agent LoopsKill flaky testsNo interval — Claude self-paces and ends the loop itself once 5 green runs in a row is provably met. [source](https://x.com/ericzakariasson/status/2064122350866682100)Open

Loop contracts / ChaoYue Awesome Loop EngineeringBug huntingFind, validate, and report likely bugs with reproducible evidence instead of filing speculative agent-generated issues.Open

Loop patterns / Cobus Loop EngineeringPR Babysitter Loop**Goal**: Reduce the human time spent herding pull requests through review, CI, rebase, and merge while keeping the human in the judgment seat.Open

Pipeline loops / Pi Pipelinesautomatic-loop>Open

Queue loop patterns / Agent Loop PatternsMetric Optimization LoopUse this when success can be scored: build time, test runtime, latency, bundle size, memory use, accuracy, allocations, or any other repeatable number.Open

Loop prompt libraries / Invincible Awesome Loop Engineering`/goal` and `/loop` prompts (Claude Code)Two related primitives, and the difference is the whole lesson:Open

Runtime loop assets / Millraceexecution.ladExecution loop with stages: builder, checker, fixer, doublechecker, updater, troubleshooter, consultant.Open

Official skills / Anthropic Skillsclaude-api|-Open

Engineering skills / Addy Osmani Agent Skillscode-review-and-qualityConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.Open

Engineering skills / Superpowersdispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesOpen

Contribution intake

Submit to Loops Radar

Public is the default. Private review is still available for ideas that need a quieter path before they become a visible issue.