Agent-Loop-Skills bundle — loop until it's better

Six verification-gated loops in one open-standard skill bundle — autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, and red-teaming — portable across Claude Code, Codex, and Cursor. Use the red-teaming loop only against systems you own and are authorized to test.

Implementation note

When to use: you want verification-gated looping across more domains than code — the bundle covers autoresearch, scientific writing, data analysis, code, SQL, and prompt optimization, plus red-teaming, in one install. How it works: six loops packaged as open-standard Agent Skills, portable across Claude Code, Codex, and Cursor. Each follows the same loop-until-it-is-better contract: iterate, check the result against a verification gate, and continue only while the gate says the artifact genuinely improved — the same anti-self-grading structure applied per domain. Safety: verification gates are the common rail across all six loops. The red-teaming loop carries its own explicit boundary: use it only against systems you own and are authorized to test — pointing an autonomous adversarial loop at anything else is out of bounds regardless of intent. As with any skill bundle, read each skill before first run and apply your own iteration caps around it.

Source: gaasher/Agent-Loop-Skills ↗

More quality loops