iterative-development - GitLite

KO | EN

gitlite — search

#rag #artificial-intelligence #llm #vue #data-science #macos #list #bash #json #chatgpt

iterative-development

(★ 173)

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

파일 탐색기

ZIP 다운로드

- plugin.json
- run_validation_suite.sh
- validate_skill.py
- - auditor-subagent-prompt.md
  - SKILL.md
- - extraction-subagent-prompt.md
  - SKILL.md
- - code-quality-reviewer-prompt.md
  - implementer-subagent-prompt.md
  - SKILL.md
  - spec-compliance-reviewer-prompt.md
- - SKILL.md
- - scope-reviewer-prompt.md
  - SKILL.md
- - SKILL.md
- - behavior-evidence-formats.md
  - par-reviewer-wrapper.md
  - parallel-adversarial-review.md
- - extracted-stories-sample.json
  - iteration-log.example.md
  - iteration-log.invalid.md
  - requirements-index.example.md
  - requirements-index.invalid.md
  - roadmap.example.md
  - roadmap.invalid.md
- - README.md
- __init__.py
- test_aggregate_stories.py
- test_artifact_validator.py
- test_check_citations.py
- test_chunk_spec.py
- test_extraction_pipeline.py
- test_skill_validator.py
.gitignore
ABOUT.md
catalog-info.yaml
LICENSE
README.md

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

명령어 용어집

이 문서에서 사용된 명령어를 모아봤습니다. 낯선 명령어가 있다면 펼쳐서 확인해보세요.

🔍

`pytest`

설명 보기 ▼

Python 테스트 실행.
더 많은 정보: <https://docs.pytest.org/en/latest/how-to/usage.html>.

pytest {{path/to/test_file1.py path/to/test_file2.py ...}}

특정 파일에서 테스트 실행:

pytest -k {{expression}}

특정 [k]eyword 표현식과 일치하는 테스트 실행:

pytest {{[-x|--exitfirst]}}

테스트가 실패하거나 오류가 발생하면 즉시 종료:

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

A Claude Code plugin that drives an autonomous, audited implementation loop for projects with large, comprehensive, or ambiguous specs. Pairs with [superpowers](https://github.com/obra/superpowers).

## When to use it

Use this plugin when:

- Your spec is large, comprehensive, or ambiguous (10+ files, 100+ requirements).
- You want the product in a working, testable state at every iteration boundary.
- You want an autonomous audited loop rather than a single upfront plan.
- The `superpowers:writing-plans` → `superpowers:subagent-driven-development` flow has lost the plot on this project before.

Do **not** use it for small, bounded projects — `superpowers:writing-plans` is simpler and more appropriate.

## What it does

The top-level `iterative-development` skill orchestrates the full lifecycle:

1. **Extract requirements** — chunks the spec, dispatches parallel extraction subagents, and produces stories with proof obligations plus behavior scenarios. Aggregates into per-epic files, a behavior-scenarios corpus, and a coverage ledger.
2. **Scope the simplest core** — defines the walking skeleton iteration (ITER-0000) and an ordered roadmap of follow-on iterations. The walking skeleton must close at least one real journey scenario, not just compile.
3. **Run iterations** — sentinel baseline → scope review → decompose code + evidence tasks → implement → impacted + sentinel scenario runs → wrap up.
4. **Audit progress** — paired auditors run a three-tier review (deep evidence, impacted behavior, sentinel corpus) using parallel adversarial review (PAR). Gaps feed back into the backlog.
5. **Terminate** — when the roadmap is drained and a final behavior-evidence audit passes, the loop exits.

Completion means the product has passing behavior evidence at the correct seam for every externally observable requirement — not just that stories are marked done.

## Skills

| Skill | Role |
|---|---|
| `iterative-development` | Top-level orchestrator for the autonomous loop. |
| `extracting-requirements` | Chunk + parallel-extract + aggregate stories and scenarios from spec collateral. |
| `scoping-the-simplest-core` | Define walking skeleton and roadmap. |
| `running-an-iteration` | Execute one sprint end-to-end. |
| `implementing-tasks` | Per-task implementer with evidence discipline. |
| `auditing-progress` | PAR-based audits at iteration and corpus level. |

## Installation

Install from the Prime Radiant marketplace:

```
/plugin marketplace add prime-radiant-inc/prime-radiant-marketplace
/plugin install iterative-development@prime-radiant-marketplace
```

Restart Claude Code after installing.

## Running the tests

```
./scripts/run_validation_suite.sh
```

Individual test files can be run with `pytest tests/`.

## Relationship to superpowers

This plugin depends conceptually on skills from the `superpowers` plugin (brainstorming, TDD, parallel adversarial review, verification-before-completion). Install `superpowers` alongside `iterative-development` for the intended experience.

## License

Apache License 2.0. See [LICENSE](LICENSE).