🔁
AI EngineeringPython

Running An Iteration

by prime-radiant-inc

Running An Iteration is an AI Engineering skill for Claude Code, published by prime-radiant-inc in iterative-development.

179 stars17 forkson prime-radiant-inc/iterative-developmentAdded 2026/09/07+1% in starsRepository updated 2026/06/06
ai-agentsautonomous-agentsclaude-codeclaude-code-pluginmethodology
Install in seconds
Install Running An Iteration
Copy Running An Iteration into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/prime-radiant-inc/iterative-development/tree/main/skills/running-an-iteration ~/.claude/skills/running-an-iteration

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/prime-radiant-inc/iterative-development.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/running-an-iteration/SKILL.md in prime-radiant-inc/iterative-development
Installs to
~/.claude/skills/running-an-iteration
Collection
One of 6 skills cataloged from this repository
Category
AI Engineering3475 skills

What Running An Iteration does

Running An Iteration executes the next pending roadmap iteration by reviewing scope, baselining sentinel scenarios, dispatching implementation and evidence tasks, and updating iteration artifacts. Use it in an iterative-development loop when advancing one iteration at a time.

Running An Iteration is cataloged under AI Engineering on DirSkills. Running An Iteration comes from a repository tagged ai-agents, autonomous-agents, claude-code, claude-code-plugin and methodology.

Documentation

README

Running an Iteration

Overview

Drives one iteration: picks the next pending, runs sentinel corpus baseline, runs pre-iteration scope review via PAR, decomposes into code and evidence tasks, dispatches implementing-tasks, runs impacted + sentinel scenarios at wrap-up, and updates the roadmap and iteration log.

When to Use

Invoked by iterative-development inside the main loop. Each invocation runs exactly one iteration. After return, the orchestrator invokes auditing-progress.

Script Location

All scripts referenced below live in this skill's scripts/ directory, next to this SKILL.md file.

Iteration Process

1. Pick next iteration

Read docs/superpowers/iterations/roadmap.md, find the first iteration with status pending.

2. Load scope context

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Running An Iteration

  • What else does prime-radiant-inc publish alongside Running An Iteration?

    Running An Iteration is one of 6 skills that DirSkills catalogs from prime-radiant-inc/iterative-development, the repository it ships in. Its siblings there include Auditing Progress, Extracting Requirements and Implementing Tasks. Each one is a separate skill with its own page in this directory, installs the same way Running An Iteration does, and is maintained by prime-radiant-inc in that same repository. The rest of the collection is listed on the prime-radiant-inc/iterative-development page.

  • How does Running An Iteration compare to other AI Engineering skills?

    Running An Iteration ranks #3126 by stars among the 3475 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Running An Iteration against them. Open each page to compare what they document and how they install.

More from prime-radiant-inc/iterative-development

Running An Iteration is one of 6 skills cataloged on DirSkills from prime-radiant-inc/iterative-development.

See all 6 skills
🔍
2h ago

Auditing Progress

Auditing Progress checks evidence quality after an iteration using three tiers: current stories, impacted scenarios, and sentinel regressions. Use it when you need to verify that behavior proof is durable before moving to the next iteration.
Quality
17917
📝
2h ago

Extracting Requirements

Extracting Requirements reads human spec collateral and turns it into per-epic requirement files with proof obligations plus reusable behavior scenarios with stable IDs. Use it when bootstrapping or regenerating requirements for an iterative-development run.
Writing
17917
🛠️
2h ago

Implementing Tasks

Implementing Tasks executes an in-memory batch of TDD-sized tasks through an implementer subagent, then spec-compliance and code-quality review loops. Use it during a running iteration when tasks need to be completed one by one with per-task status reported back.
AI Engineering
17917
🔁
2h ago

Iterative Development

Iterative Development turns a large or ambiguous spec into a walking skeleton, then runs audited sprints that build behavior evidence for each externally visible requirement. Use it when you need a working, testable product at every iteration boundary.
AI Engineering
17917
🧭
2h ago

Scoping The Simplest Core

Scoping The Simplest Core turns extracted requirements into a roadmap with a walking-skeleton iteration and follow-on iterations. It is used to choose the first runnable journey scenario, split stories by dependency profile, and validate scope via review.
AI Engineering
17917