define-loop
yc-software/qmSkill
Define a Loop — a durable scaffold that works a queue of recurring tasks autonomously (Sentry issues, Front tickets, small perf PRs) with its outputs held for human review. Use when someone wants an agent to keep doing a kind of work on a schedule, rather than one-off. Walks the interview, runs one real item live before arming anything, then writes the playbook and creates the loop.
Why this score
This repo hosts 10 skills, so its 15,450 stars are split between them (about 1,545 each) for scoring.
Popularity score: 82/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit 7417aa2a3f91, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onedefine-loop yc-software/qm · Skill | 82 | ★ 15k | ≈99 always | 16d ago |
| define-security-policy openai/codex-security · Skill Both about define | 80 | ★ 11k | ≈71 always | 16d ago |
| flow-define nyldn/claude-octopus · Skill Both about define | 75 | ★ 4.3k | ≈64 always | 16d ago |
| define-rubric DheerG/swarms · Skill Both about define | 48 | ★ 85 | ≈31 always | 3mo ago |
| define-goal openai/skills · Skill Both about define and durable | 79 | ★ 28k | ≈98 always | 2mo ago |
| loop-engineering alvinunreal/oh-my-opencode-slim · Skill Both about loop and interview | 79 | ★ 9.7k | ≈27 always | 16d ago |