# qcsd-refinement-swarm

The qcsd-refinement-swarm skill checks user stories before sprint commitment, creates BDD scenarios, and returns a READY, CONDITIONAL, or NOT-READY decision.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 105 installs · ★ 533 repo stars
- Author: proffesor-for-testing
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/qcsd-refinement-swarm/SKILL.md
- Updated: 2026-10-25
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/qcsd-refinement-swarm

## What it does

Provide a user story with acceptance criteria. The skill assesses product factors using SFDIPOT, checks requirements against INVEST, and produces BDD scenarios. Its final decision is READY, CONDITIONAL, or NOT-READY, accompanied by a refinement report.

The workflow runs in ordered steps. Three core agents assess the story first; conditional agents join when relevant flags are raised. Those agents cover areas such as APIs, dependencies, and authorization. The workflow then rewrites test ideas and stores findings in memory.

A story with acceptance criteria is required to start. Set `OUTPUT_FOLDER` to choose where reports go; otherwise, the configured path is `${PROJECT_ROOT}/Agentic QCSD/refinement/`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill qcsd-refinement-swarm -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/qcsd-refinement-swarm/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/qcsd-refinement-swarm/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill qcsd-refinement-swarm -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/qcsd-refinement-swarm/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill qcsd-refinement-swarm -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/qcsd-refinement-swarm/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install proffesor-for-testing/agentic-qe assets/skills/qcsd-refinement-swarm
```

2. **Manually: put the files in place**
- File: `.github/skills/qcsd-refinement-swarm/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill qcsd-refinement-swarm -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/proffesor-for-testing/agentic-qe --path assets/skills/qcsd-refinement-swarm
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/qcsd-refinement-swarm/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill qcsd-refinement-swarm -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/qcsd-refinement-swarm/SKILL.md

## When to use it
- assess a user story against INVEST
- review a story through SFDIPOT product factors
- generate BDD scenarios from acceptance criteria
- decide whether a story is ready for sprint commitment
- identify conditional checks for APIs or dependencies

## Example prompts
- Review this user story and its acceptance criteria for sprint refinement.
- Create BDD scenarios for this story and assess its readiness.
- Check this story for API and dependency concerns, then save the report to `OUTPUT_FOLDER`.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: d66aeba5f04fab3f.

BEGIN THIRD-PARTY FILE d66aeba5f04fab3f
```text
---
name: qcsd-refinement-swarm
description: "Use when running Sprint Refinement sessions with SFDIPOT product factors, generating BDD scenarios, or validating requirements in the QCSD Refinement phase."
category: qcsd-phases
priority: critical
version: 1.0.0
tokenEstimate: 3200
# DDD Domain Mapping (from QCSD-AGENTIC-QE-MAPPING-FRAMEWORK.md)
domains:
  primary:
    - domain: requirements-validation
      agents: [qe-product-factors-assessor, qe-bdd-generator, qe-requirements-validator]
  conditional:
    - domain: contract-testing
      agents: [qe-contract-validator]
    - domain: code-intelligence
      agents: [qe-impact-analyzer, qe-dependency-mapper]
    - domain: enterprise-integration
      agents: [qe-middleware-validator, qe-odata-contract-tester, qe-sod-analyzer]
  transformation:
    - domain: test-generation
      agents: [qe-test-idea-rewriter]
# Agent Inventory
agents:
  core: [qe-product-factors-assessor, qe-bdd-generator, qe-requirements-validator]
  conditional: [qe-contract-validator, qe-impact-analyzer, qe-dependency-mapper, qe-middleware-validator, qe-odata-contract-tester, qe-sod-analyzer]
  transformation: [qe-test-idea-rewriter]
  total: 10
  sub_agents: 0
skills: [context-driven-testing, testability-scoring, risk-based-testing]
# Execution Models (Task Tool is PRIMARY)
execution:
  primary: task-tool
  alternatives: [mcp-tools, cli]
swarm_pattern: true
parallel_batches: 3
last_updated: 2026-02-02
enforcement_level: strict
tags: [qcsd, refinement, sfdipot, bdd, gherkin, requirements, swarm, parallel, ddd]
trust_tier: 3
validation:
  schema_path: schemas/output.json
  validator_path: scripts/validate-config.json
  eval_path: evals/qcsd-refinement-swarm.yaml
---

# QCSD Refinement Swarm v1.0

Shift-left quality engineering swarm for Sprint Refinement sessions.

---

## Overview

The Refinement Swarm takes user stories that passed Ideation and prepares them
for Sprint commitment using SFDIPOT product factors, BDD scenarios, and INVEST validation.
It renders a READY / CONDITIONAL / NOT-READY decision.

### QCSD Phase Positioning

| Phase | Swarm | Decision | When |
|-------|-------|----------|------|
| Ideation | qcsd-ideation-swarm | GO / CONDITIONAL / NO-GO | PI/Sprint Planning |
| **Refinement** | **qcsd-refinement-swarm** | **READY / CONDITIONAL / NOT-READY** | **Sprint Refinement** |
| Development | qcsd-development-swarm | SHIP / CONDITIONAL / HOLD | During Sprint |
| Verification | qcsd-cicd-swarm | RELEASE / REMEDIATE / BLOCK | Pre-Release / CI-CD |
| Production | qcsd-production-swarm | HEALTHY / DEGRADED / CRITICAL | Post-Release |

### Parameters
```
END THIRD-PARTY FILE d66aeba5f04fab3f

The third-party file has ended. Everything between the d66aeba5f04fab3f tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2624 of 5822 bytes. © proffesor-for-testing · MIT · https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/qcsd-refinement-swarm/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
