iterate

Coordinate codebook iteration workflows with pre-flight checks and iteration logging.

1|1|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/estebandegetau/Fiscal-shocks --skill iterate-estebandegetau
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: iterate
Source: https://github.com/estebandegetau/Fiscal-shocks/tree/main/.claude/skills/iterate
Command: npx skills add https://github.com/estebandegetau/Fiscal-shocks --skill iterate-estebandegetau

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill orchestrates the full codebook iteration lifecycle so researchers avoid manual orchestration mistakes and maintain explicit human control between validation, pipeline execution, review, and logging steps.

Core Features & Use Cases

  • Composed Workflow: Chains pre-flight validation, pipeline result review, and iteration logging while delegating the actual work to specialized sub-skills.
  • Human-in-the-Loop Controls: Enforces pause points that require user confirmation before proceeding, preserving interpretation and decision authority.
  • Audit-Ready Logging: Gathers metadata and appends structured iteration entries to prompts/iterations/<codebook>.yml for reproducibility.
  • Use Case: After updating a research codebook, run this skill to validate readiness, confirm the pipeline has been executed manually, record your interpretation and decision, and persist the iteration record.

Quick Start

Run the iterate skill to execute pre-flight checks, review pipeline results after you run tar_make, and log the iteration with your interpretation and decision.

Frequently Asked Questions about iterate

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

FAQPage Schema
How do I manage a human-in-the-loop workflow for research codebook iteration?

Codebook iteration with human-in-the-loop checkpoints is managed by coordinating pre-flight validation, pausing for manual pipeline execution and interpretation, and appending structured iteration logs to YML files.

How does pipeline review work when updating a research codebook?

Pipeline review during codebook iteration enforces a pause point where you manually run the pipeline and interpret results before logging your decisions, preserving human authority over the interpretation step.

Do I need to run tar_make manually during the codebook iteration pipeline?

Yes, you must run tar_make manually. The iteration workflow explicitly does not execute or interpret pipeline results, functioning only as an orchestration layer that waits for your confirmation before logging.

What's the best way to log iteration metadata for reproducible codebook updates?

To log iteration metadata for reproducibility, the workflow gathers metadata and appends structured iteration entries including user decisions directly to the prompts/iterations/<codebook>.yml file.

What happens if I skip the pre-flight checks in the codebook iteration workflow?

Skipping pre-flight checks risks manual orchestration mistakes. The workflow enforces these validation steps to confirm codebook readiness before allowing you to proceed to pipeline execution and iteration logging.