Iterative Development
Audited sprint loop for large ambiguous specs — proof obligations over checked boxes.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 13, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 7032865
This orchestrator is the front door to a 6-skill plugin bundle — copying only its own SKILL.md leaves it calling extracting-requirements, scoping-the-simplest-core, and four other named skills that must ship alongside it. On a toy spec it correctly forced a testable 'proof obligation' per story and refused to let scope grow past a single working end-to-end journey, a discipline a freeform task list skipped entirely.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 4/5
What Iterative Development does
Orchestrates a multi-day autonomous build loop for large or ambiguous specs: extracts requirements as story cards with proof obligations and behavior scenarios, defines a walking skeleton that must close a real end-to-end journey before expanding, then runs audited sprints backed by a growing behavior-evidence corpus. Trigger it on '10+ file spec', 'ambiguous requirements', or 'continue iterative development with the existing plan'; skip it for small bounded tasks, which it explicitly defers to a simpler upfront-planning flow.
How to install Iterative Development
git clone https://github.com/prime-radiant-inc/iterative-development
cd iterative-development
mkdir -p ~/.claude/skills
cp -r skills/iterative-development ~/.claude/skills/iterative-development
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Iterative Development
-
/iterative-developmentAudited sprint loop for large ambiguous specs — proof obligations over checked boxes.
It also activates on plain-language prompts like these:
-
This spec has 10+ files and ambiguous requirements, run it as sprints -
Break this big vague spec into story cards with proof obligations -
Continue the iterative development loop using the existing plan
Frequently asked questions
- Is the Iterative Development skill free?
- Yes. The skill itself is free from prime-radiant-inc/iterative-development. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Iterative Development work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. This orchestrator is the front door to a 6-skill plugin bundle — copying only its own SKILL.md leaves it calling extracting-requirements, scoping-the-simplest-core, and four other named skills that must ship alongside it. On a toy spec it correctly forced a testable 'proof obligation' per story and refused to let scope grow past a single working end-to-end journey, a discipline a freeform task list skipped entirely.
- What is the Iterative Development SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
- How do I install Iterative Development?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Iterative Development with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.