loop
01Skill Codex
Use only when user explicitly invokes $loop.
not rated 630
changed 1mo ago A SkillSpector: warn 11 tokens
original Apache-2.0
claude-loop
02Skill Claude CodeCodex
Autonomous orchestrated loop that works through a prd.json story-by-story using a fresh Task subagent per story. Use this skill whenever the user asks to "run the loop", "claude loop", "start the loop", "kick off the loop", "work through the prd", "process prd.json", "implement all the stories", "iterate through the…
not rated 49 3mo ago A 275 tokens
original MIT
agile-loop
03Skill Claude CodeCodex
Run the queued GSD → Superpowers → review → ship loop end-to-end. Reads tasks from docs/agile-loop/tasks/.md, spawns isolated child sessions per stage, opens one PR per task, and auto-merges it (squash) before continuing to the next task. Use when asked to "run the agile loop", "process the next queued task", or…
not rated 5 4mo ago A 89 tokens
original MIT
humanizer
04Skill Claude Code
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
not rated 5 8mo ago A 92 tokens
agent-loop
05Skill Claude CodeCodex
Run bounded, resumable OpenAI-native coding loops with shell and applypatch, similar to Claude Code agent loops. Use when the user asks for a loop, autonomous iteration, or a persistent inspect-edit-test cycle with a turn cap.
not rated 4 6mo ago A 50 tokens
original MIT
perpetuum
06Skill Claude CodeCodex
A system for running a long-term team of coding agents on one or more real project directories. It organizes work as Stories, which are trackable pieces of work with a complete, verifiable outcome.
not rated 0 1mo ago A Socket: warnSnyk: warn 48 tokens
original MIT