skills.rest
beefiker
beefikerCOMMUNITY
Explore all skills by this author →
GitHub

superloopy-loop

Automate strict evidence loops for Codex and Claude Code tasks.

105|16|Updated Jun 29, 2026
Search Tags:#Codex#Claude Code#quality gate#evidence audit#loop engineering#evidence loop#artifact-backed completion
One-click install
npx skills add https://github.com/beefiker/superloopy --skill superloopy-loop
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: superloopy-loop
Source: https://github.com/beefiker/superloopy/tree/main/skills/superloopy-loop
Command: npx skills add https://github.com/beefiker/superloopy --skill superloopy-loop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires superloopy, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of creating strict evidence loops for Codex and Claude Code tasks, ensuring durable progress, criteria, and artifact-backed completion.

Core Features & Use Cases

  • Strict Evidence Loop Creation: Automatically create and manage evidence loops for tasks requiring durable criteria and artifact-backed completion.
  • Loop Engineering: Supports loop engineering with commands for guidance, proof, preflight, and finishing loops.
  • Crew Mode: Escalate to full fan-out, dispatching across independent lanes with role-specific agents for implementation, review, QA, and audit.
  • Optional Subagent-Driven Mode: Utilize custom agents from .codex/agents/ for subagent-driven workflows.
  • Evidence Audit: Independently re-checks recorded proof and ensures criteria are met with a deterministic spine.
  • Quality Gate: Ensures all artifacts exist, are non-empty, and live under the active evidence root.
  • Steering: Accepts structured prompt-level steering for adding goals, revising criteria, and reordering pending goals.
  • Doctor: Checks the package, hooks, skills, CLI, and runtime environment for issues.

Quick Start

Run 'loopy <task>' to initiate a strict evidence loop for your Codex or Claude Code task.

Frequently Asked Questions about superloopy-loop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create strict evidence loops for Codex and Claude Code tasks?▼

Strict evidence loops are created by running the 'loopy <task>' command, which automates durable progress tracking, criteria enforcement, and artifact-backed completion for Codex and Claude Code workflows.

What is artifact-backed completion and how does it validate task progress?▼

Artifact-backed completion validates task progress through a quality gate that ensures all required artifacts exist, are non-empty, and live under the active evidence root before a loop can finish.

Does evidence loop automation require installing the Superloopy CLI first?▼

Yes, evidence loop automation requires the Superloopy CLI and supporting agents to handle loop engineering, evidence audits, and quality gate checks for your tasks.

Can I dispatch Codex tasks across independent lanes with role-specific agents?▼

Yes, you can use crew mode to escalate to full fan-out, dispatching tasks across independent lanes with role-specific agents for implementation, review, QA, and audit.

How do I add goals or revise criteria in an active evidence loop?▼

You can add goals, revise criteria, and reorder pending goals in an active evidence loop by using structured prompt-level steering commands provided by the loop engineering system.

What is the best way to check for issues in my evidence loop environment?▼

Use the doctor command to check your package, hooks, skills, CLI, and runtime environment for issues that might affect your evidence loop automation.

Related Skills

Explore More Software Engineering Skills→
beefikerbeefiker
105

superloopy-doctor

Diagnose Superloopy installations and generate detailed health reports.

Community
Intermediate
MohamedAbdallah-14MohamedAbdallah-14
3

wz:verification

Enforce completion claims with fresh command evidence or deterministic proof paths.

Community
Advanced
mattei2005mattei2005

kanban-orchestrator

Decompose orchestration goals into Kanban task graphs routed to specialist profiles.

Community
Advanced
hungv47hungv47
14

run-pipeline

Orchestrate staged marketing/content loops with pauses at gates.

Community
Advanced