Starts or tracks an autonomous Ralph loop for iterative development with risk-based governance oversight.

Install

mkdir -p .claude/skills/demerzel-loop && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12047" && unzip -o skill.zip -d .claude/skills/demerzel-loop && rm skill.zip

Installs to .claude/skills/demerzel-loop

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Start or monitor a governed Ralph Loop — autonomous iterative development with graduated governance oversight
109 charsno explicit “when” trigger
Advanced

Key capabilities

  • Initiate a new governed Ralph Loop with a specified goal and repository
  • Check the progress and status of an ongoing loop
  • Manually halt a running loop
  • Classify loop risk (Low, Medium, High, Critical) to determine governance mode
  • Monitor for convergence, regressions, and drift within the loop

How it works

The skill manages autonomous iterative development loops by initiating, monitoring, and halting them, applying governance based on risk classification and predefined criteria.

Inputs & outputs

You give it
A command to start, status, or halt a loop, with optional goal, repo, or loop-id
You get back
A new governed Ralph Loop, status information, or a halted loop

When to use demerzel-loop

  • Start an autonomous development loop
  • Check loop progress
  • Halt a development loop

About this skill

Demerzel Governed Ralph Loop

Start or monitor autonomous iterative development cycles with governance checkpoints.

Usage

/demerzel loop start [goal] [repo] — initiate a new loop /demerzel loop status [loop-id] — check loop progress /demerzel loop halt [loop-id] — manually halt a loop

Risk Classification (determined before loop starts)

RiskDescriptionGovernance Mode
LowReversible, single repo, no securityboundary-only
MediumReversible but significant, affects behaviorboundary-only
HighIrreversible, cross-repo, security-sensitiveper-iteration
CriticalGovernance integrity, Zeroth Lawper-iteration + human pre-approval

Loop-Specific Review Criteria

  1. Convergence: Is the loop making progress? (3 stalls → halt)
  2. Regression: Did this iteration break a previous iteration's work? (→ halt)
  3. Drift: Has the loop wandered from its goal? (→ halt, Article 4 concern)

Iteration Limits

  • Default: 10 iterations, Absolute max: 25
  • Stall limit: 3 iterations without progress
  • Zeroth Law concern at any iteration → immediate halt

Demerzel-Initiated Loops

Demerzel may initiate loops for governance tasks only (compliance remediation, Kaizen cycles). Domain work loops are agent-initiated. Dispatched via Galactic Protocol directives.

Source

policies/autonomous-loop-policy.yaml, schemas/loop-state.schema.json

When not to use it

  • For domain work loops that are not agent-initiated

Limitations

  • Iteration limits are set to a default of 10, with an absolute max of 25
  • Stall limit is 3 iterations without progress
  • Immediate halt on Zeroth Law concern at any iteration

How it compares

This skill provides a governed framework for autonomous iterative development with built-in risk classification and monitoring, which is more structured than ad-hoc development cycles.

Compared to similar skills

demerzel-loop side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
demerzel-loop (this skill)05moNo flagsAdvanced
trello412moReviewBeginner
executing-plans63moNo flagsIntermediate
github-project-management46moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

trello

openclaw

Manage Trello boards, lists, and cards via the Trello REST API.

41205

executing-plans

obra

Use when you have a written implementation plan to execute in a separate session with review checkpoints

643

github-project-management

ruvnet

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

427

project-clickup

incidentfox

ClickUp project management integration for incident tracking and task management

320

coo-advisor

alirezarezvani

Operations leadership for scaling companies. Process design, OKR execution, operational cadence, and scaling playbooks. Use when designing operations, setting up OKRs, building processes, scaling teams, analyzing bottlenecks, planning operational cadence, or when user mentions COO, operations, process improvement, OKRs, scaling, operational efficiency, or execution.

613

tlc-spec-driven

tech-leads-club

Project and feature planning with 4 phases - Specify, Design, Tasks, Implement+Validate. Creates atomic tasks with verification criteria and maintains persistent memory across sessions. Stack-agnostic. Use when: (1) Starting new projects (initialize vision, goals, roadmap), (2) Working with existing codebases (map stack, architecture, conventions), (3) Planning features (requirements, design, task breakdown), (4) Implementing with verification, (5) Tracking decisions/blockers across sessions, (6) Pausing/resuming work. Triggers on "initialize project", "map codebase", "specify feature", "design", "tasks", "implement", "pause work", "resume work".

77

Search skills

Search the agent skills registry