Implementing Tasks

by prime-radiant-inc

Implementing Tasks 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

View source on GitHub Download repo ZIP

ai-agentsautonomous-agentsclaude-codeclaude-code-pluginmethodology

Install in seconds

Install Implementing Tasks

Copy Implementing Tasks 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/implementing-tasks ~/.claude/skills/implementing-tasks

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/implementing-tasks/SKILL.md in prime-radiant-inc/iterative-development
Installs to: ~/.claude/skills/implementing-tasks
Collection: One of 6 skills cataloged from this repository
Category: AI Engineering — 3475 skills

What Implementing Tasks does

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.

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

Documentation

README

Excerpt

Implementing Tasks

Overview

Takes an in-memory batch of TDD-sized tasks and executes each through: implementer subagent (TDD) → PAR spec-compliance review → fix loop → PAR code-quality review with boxing-in check → fix loop → mark complete. This is a fork of superpowers:subagent-driven-development with the plan-file reading phase stripped and the final end-of-plan reviewer removed.

When to Use

Invoked by running-an-iteration with a list of tasks. Tasks are passed in memory, not via a file.

Per-Task Cycle

For each task in the provided list:

1. Dispatch implementer

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

Frequently asked about Implementing Tasks

What else does prime-radiant-inc publish alongside Implementing Tasks?
Implementing Tasks 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 Iterative Development. Each one is a separate skill with its own page in this directory, installs the same way Implementing Tasks 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 Implementing Tasks compare to other AI Engineering skills?
Implementing Tasks ranks #3113 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 Implementing Tasks against them. Open each page to compare what they document and how they install.