Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
From everything-claude-codenpx claudepluginhub ibytechaos/claudeThis skill uses the workspace's default tool permissions.
Guides AI-assisted editing of real video footage: transcribe/plan cuts with Claude, execute via FFmpeg bash scripts, augment with Remotion/ElevenLabs/fal.ai, polish in Descript/CapCut.
Ingests video/audio from files, URLs, RTSP, desktop; indexes/searches moments with timestamps/clips; transcodes/edits timelines (subtitles/overlays/dubbing); generates assets and live alerts.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
This is the v1.8+ canonical loop skill name. It supersedes autonomous-loops while keeping compatibility for one release.
Start
|
+-- Need strict CI/PR control? -- yes --> continuous-pr
|
+-- Need RFC decomposition? -- yes --> rfc-dag
|
+-- Need exploratory parallel generation? -- yes --> infinite
|
+-- default --> sequential
Recommended production stack:
ralphinho-rfc-pipeline)plankton-code-quality + /quality-gate)eval-harness)nanoclaw-repl)/harness-audit