Skip to main content
skill CX Codex

qcsd-ideation-swarm — Claude Code skill: what it does, how to install

qcsd-ideation-swarm runs Quality Criteria sessions during PI or sprint planning using HTSM v6.3 and Risk Storming. Delivers a GO, CONDITIONAL, or NO-GO verdict before development begins.

MIT 107 installs ★ 533 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add proffesor-for-testing/agentic-qe --skill qcsd-ideation-swarm -a claude-code
Open on GitHub

What qcsd-ideation-swarm does

The skill handles the ideation phase of the QCSD lifecycle to validate requirements early. Step execution uses a micro-file architecture where instructions load sequentially. Step one identifies flags across seven integration categories. Step two immediately deploys three mandatory agents: qe-quality-criteria-recommender, qe-risk-assessor, and qe-requirements-validator.

Triggered flags activate conditional agents in batch two for domains like security, accessibility, or middleware. When auditing websites through the URL parameter, a 5-tier browser cascade handles page retrieval down to web search fallback. Rule E1 strictly blocks decision synthesis if core agents are skipped.

All metrics compile into an executive summary and an HTML report. If an execution stops mid-run, it resumes cleanly using --from-step.

What it helps with

  • assess requirements testability before sprint development starts
  • run Risk Storming sessions based on HTSM v6.3 criteria
  • generate a structured GO, CONDITIONAL, or NO-GO decision
  • audit web pages using a 5-tier browser fallback cascade

Example prompts for the agent

  • Run qcsd-ideation-swarm on the current sprint planning user story
  • Execute qcsd-ideation-swarm with parameter URL to audit the target site
  • Resume the ideation swarm workflow using --from-step 4

How to install qcsd-ideation-swarm

1Skills CLI (Vercel)

npx skills add proffesor-for-testing/agentic-qe --skill qcsd-ideation-swarm -a claude-code

2Manually: put the files in place

~/.claude/skills/qcsd-ideation-swarm/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/qcsd-ideation-swarm/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about qcsd-ideation-swarm

How to install qcsd-ideation-swarm in Claude Code?

Run npx skills add proffesor-for-testing/agentic-qe --skill qcsd-ideation-swarm -a claude-code. The file will be written to ~/.claude/skills/qcsd-ideation-swarm/SKILL.md.

What does qcsd-ideation-swarm do?

It evaluates backlog stories and websites using Risk Storming and HTSM v6.3 criteria. The swarm returns a GO, CONDITIONAL, or NO-GO decision before coding starts.

Which agents run in the first batch?

Batch one always spawns qe-quality-criteria-recommender, qe-risk-assessor, and qe-requirements-validator. Rule E1 forbids replacing these core agents with summaries.

Source text

SKILL.md · MIT
---
name: qcsd-ideation-swarm
description: "Use when running Quality Criteria sessions during PI/Sprint planning with HTSM v6.3, Risk Storming, or Testability analysis in the QCSD Ideation phase."
category: qcsd-phases
priority: critical
version: 7.5.1
tokenEstimate: 3500
# DDD Domain Mapping (from QCSD-AGENTIC-QE-MAPPING-FRAMEWORK.md)
domains:
  primary:
    - domain: requirements-validation
      agents: [qe-quality-criteria-recommender, qe-requirements-validator]
    - domain: coverage-analysis
      agents: [qe-risk-assessor]
  conditional:
    - domain: security-compliance
      agents: [qe-security-auditor]
    - domain: visual-accessibility
      agents: [qe-accessibility-auditor]
    - domain: cross-domain
      agents: [qe-qx-partner]
    - domain: enterprise-integration
      agents: [qe-middleware-validator, qe-sap-rfc-tester, qe-sod-analyzer]
# Agent Inventory
agents:
  core: [qe-quality-criteria-recommender, qe-risk-assessor, qe-requirements-validator]
  conditional: [qe-accessibility-auditor, qe-security-auditor, qe-qx-partner, qe-middleware-validator, qe-sap-rfc-tester, qe-sod-analyzer]
  total: 9
  sub_agents: 0
skills: [testability-scoring, risk-based-testing, context-driven-testing, holistic-testing-pact]
# Execution Models (Task Tool is PRIMARY)
execution:
  primary: task-tool
  alternatives: [mcp-tools, cli]
swarm_pattern: true
parallel_batches: 2
last_updated: 2026-01-28
# v7.5.1 Changelog: Added prominent follow-up recommendation box at end of swarm execution (Phase URL-9)
# v7.5.0 Changelog: Added HAS_VIDEO flag detection with /a11y-ally follow-up recommendation for video caption generation
# v7.4.0 Changelog: Automated browser cascade via scripts/fetch-content.js with 30s per-tier timeouts
# v7.2.0 Changelog: Added 5-tier browser cascade (Vibium -> agent-browser -> Playwright+Stealth -> WebFetch -> WebSearch)
html_output: true
enforcement_level: strict
tags: [qcsd, ideation, htsm, quality-criteria, risk-storming, testability, swarm, parallel, ddd]
trust_tier: 3
validation:
  schema_path: schemas/output.json
  validator_path: scripts/validate-config.json
  eval_path: evals/qcsd-ideation-swarm.yaml
---

# QCSD Ideation Swarm v7.0

Shift-left quality engineering swarm for PI Planning and Sprint Planning.

---

## Overview

The Ideation Swarm assesses stories and URLs before development begins, using HTSM v6.3
quality criteria, Risk Storming, and Testability analysis. It renders a
GO / CONDITIONAL / NO-GO decision and is the first gate in the QCSD lifecycle.

### 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

- `URL`: Website to analyze (required for URL mode)
- `OUTPUT_FOLDER`: Where to save reports (default: `${PROJECT_ROOT}/Agentic QCSD/{domain}/`)

### Unique Features

- **URL Mode**: Automated 5-tier browser cascade for live website analysis
- **HAS_VIDEO Flag**: Detects video content and recommends `/a11y-ally` follow-up
- **HTML Output**: Generates HTML reports when `html_output: true`
- **Browser Cascade**: Vibium -> agent-browser -> Playwright+Stealth -> WebFetch -> WebSearch-fallback

---

## ENFORCEMENT RULES - READ FIRST

| Rule | Enforcement |
|------|-------------|
| **E1** | You MUST spawn ALL THREE core agents (qe-quality-criteria-recommender, qe-risk-assessor, qe-requirements-validator) in Step 2. No exceptions. |
| **E2** | You MUST put all parallel Task calls in a SINGLE message. |
| **E3** | You MUST STOP and WAIT after each batch. No proceeding early. |
| **E4** | You MUST spawn conditional agents if flags are TRUE. No skipping. |
| **E5** | You MUST apply GO/CONDITIONAL/NO-GO logic exactly as specified in Step 5. |
| **E6** | You MUST generate the full report structure. No abbreviated versions. |
| **E7** | Each agent MUST read its reference files before analysis. |
| **E8** | You MUST execute Step 7 learning persistence. No skipping. |

**PROHIBITED BEHAVIORS:**
- Summarizing instead of spawning agents
- Skipping agents "for brevity"
- Proceeding before background tasks complete
- Providing your own analysis instead of spawning specialists
- Omitting report sections or using placeholder text

---

## Step Execution Protocol

This skill uses a micro-file step architecture. Each step is a self-contained file
loaded one at a time to avoid "lost in the middle" context degradation.

**Execute steps sequentially by reading each step file with the Read tool.**

### Steps

1. **Flag Detection** -- `steps/01-flag-detection.md` -- Fetch URL content (browser cascade), detect all 7 flags (HAS_UI, HAS_SECURITY, HAS_UX, HAS_VIDEO, HAS_MIDDLEWARE, HAS_SAP_INTEGRATION, HAS_AUTHORIZATION)
2. **Core Agents** -- `steps/02-core-agents.md` -- Spawn qe-quality-criteria-recommender, qe-risk-assessor, qe-requirements-validator in parallel
3. **Batch 1 Results** -- `steps/03-batch1-results.md` -- Wait for core agents, extract all metrics
4. **Conditional Agents** -- `steps/04-conditional-agents.md` -- Spawn flagged conditional agents in parallel
5. **Decision Synthesis** -- `steps/05-decision-synthesis.md` -- Apply GO/CONDITIONAL/NO-GO logic
6. **Report Generation** -- `steps/06-report-generation.md` -- Generate executive summary and full report
7. **Learning Persistence** -- `steps/07-learning-persistence.md` -- Store findings to memory, save persistence record, include video follow-up recommendation
8. **Final Output** -- `steps/08-final-output.md` -- Display completion summary with all scores and follow-up recommendations

### Execution Instructions

1. Use the Read tool to load the current step file (e.g., `Read({ file_path: ".claude/skills/qcsd-ideation-swarm/steps/01-flag-detection.md" })`)
2. Execute the step's instructions completely
3. Verify all success criteria are met before proceeding
4. Pass the step's output as context to the next step
5. If a step fails, halt and report the failure point -- do not skip ahead

### Resume Support

To resume from a specific step: specify `--from-step N` and the orchestrator will
skip to step N. Ensure you have the required prerequisite data from prior steps.

---

## Agent Inventory

| Agent | Type | Domain | Batch |
|-------|------|--------|-------|
| qe-quality-criteria-recommender | Core (always) | requirements-validation | 1 |
| qe-risk-assessor | Core (always) | coverage-analysis | 1 |
| qe-requirements-validator | Core (always) | requirements-validation | 1 |
| qe-accessibility-auditor | Conditional (HAS_UI) | visual-accessibility | 2 |
| qe-security-auditor | Conditional (HAS_SECURITY) | security-compliance | 2 |
| qe-qx-partner | Conditional (HAS_UX) | cross-domain | 2 |
| qe-middleware-validator | Conditional (HAS_MIDDLEWARE) | enterprise-integration | 2 |
| qe-sap-rfc-tester | Conditional (HAS_SAP_INTEGRATION) | enterprise-integration | 2 |
| qe-sod-analyzer | Conditional (HAS_AUTHORIZATION) | enterprise-integration | 2 |

**Total: 9 agents (3 core + 6 conditional)**

**Note**: The Ideation swarm has 8 steps (not 9) because it has no separate final
analysis agent step. The HAS_VIDEO flag triggers a follow-up recommendation for
`/a11y-ally` but does not spawn an additional agent.

---

## Quality Gate Thresholds

| Metric | GO | CONDITIONAL | NO-GO |
|--------|-----|-------------|-------|
| Testability Score | >= 70% | 40 - 69% | < 40% |
| Risk Score | LOW/MEDIUM | HIGH (mitigatable) | CRITICAL |
| Requirements Completeness | >= 80% | 50 - 79% | < 50% |
| Quality Criteria Coverage | >= 7/10 categories | 4-6/10 categories | < 4/10 categories |

---

## Report Filename Mapping

| Agent | Report Filename | Step |
|-------|----------------|------|
| qe-quality-criteria-recommender | `02-quality-criteria.md` | 2 |
| qe-risk-assessor | `03-risk-assessment.md` | 2 |
| qe-requirements-validator | `04-requirements-validation.md` | 2 |
| qe-accessibility-auditor | `05-accessibility-audit.md` | 4 |
| qe-security-auditor | `06-security-audit.md` | 4 |
| qe-qx-partner | `07-ux-assessment.md` | 4 |
| qe-middleware-validator | `08-middleware-assessment.md` | 4 |
| qe-sap-rfc-tester | `09-sap-assessment.md` | 4 |
| qe-sod-analyzer | `10-sod-compliance.md` | 4 |
| Learning Persistence | `11-learning-persistence.json` | 7 |
| Synthesis | `01-executive-summary.md` | 6 |

---

## Execution Model Options

| Model | When to Use | Agent Spawn |
|-------|-------------|-------------|
| **Task Tool** (PRIMARY) | Claude Code sessions | `Task({ subagent_type, run_in_background: true })` |
| **MCP Tools** | MCP server available | `fleet_init({})` / `task_submit({})` |
| **CLI** | Terminal/scripts | `swarm init` / `agent spawn` |

---

## Key Principle

**Quality is built in from the start, not tested in at the end. This swarm ensures
stories are viable, testable, and risk-assessed before any code is written.**

© proffesor-for-testing · MIT · proffesor-for-testing/agentic-qe

Similar skills

All skills for Testing and QA →
research-ideation EvoScientist Guides research ideation from literature grounding and multi-persona brainstorming to ELO ranking and structured research proposals. CX Codex +1 502installs idea-generation-and-ideation social-media-skills idea-generation-and-ideation runs an audience-driven content ideation system using the SPARK framework. Builds a scored bank of 100+ ideas from raw customer signals instead of generic AI brainstorming. CX Codex +1 1,300installs swarm backnotprop A skill for Claude Code, Cursor, Codex, GitHub Copilot, Gemini CLI, and OpenCode that fans out N parallel subagents, drains their results, and returns a single consolidated report. Triggered by /swarm or the phrase "swarm this" in chat. CX Codex +1 10,300installs Swarm Orchestration ruvnet Swarm Orchestration — a skill for managing agent swarms with parallel execution, dynamic topology, and automatic load balancing. Use when a single agent is not enough and you need to orchestrate specialists of different types. CX Codex +1 2,100installs swarm-advanced ruvnet swarm-advanced — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that brings multi-agent swarm patterns to your workflow. Coordinates parallel research, development, and testing across specialized agents. CX Codex +1 1,200installs collaborative-ideation qodex-ai collaborative-ideation runs the brainstorm step by step: one question at a time, a few approaches, a design in sections, then a committed file under docs/plans/. CX Codex +1 154installs

From the same set73

The whole set →
enterprise-integration-testing Enterprise integration testing skill for SAP, middleware, and WMS setups. It coordinates cross-system checks across RFC, IDoc, OData, and ESB flows. CX Codex +1 113installs holistic-testing-pact holistic-testing-pact builds testing strategies around PACTS principles and holistic quadrants. It structures quality planning for classical, AI-assisted, and autonomous agent setups. CX Codex +1 111installs observability-testing-patterns observability-testing-patterns is a Claude Code skill with patterns for checking dashboards, alert thresholds, log aggregation, and APM tracing during monitoring tests. CX Codex +1 109installs sfdipot-product-factors The sfdipot-product-factors skill turns requirements into ranked test ideas using seven SFDIPOT dimensions. Use it to assess epics, user stories, or a test strategy. CX Codex +1 108installs middleware-testing-patterns The middleware-testing-patterns skill helps design checks for message routing, transformations, DLQs, and error handling in ESBs and brokers. Use it when testing integration flows. CX Codex +1 107installs qcsd-development-swarm qcsd-development-swarm evaluates in-sprint code quality using an agent swarm that inspects TDD adherence, complexity, and test gaps to decide SHIP, CONDITIONAL, or HOLD. CX Codex +1 105installs 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. CX Codex +1 105installs qcsd-cicd-swarm The qcsd-cicd-swarm Claude Code skill checks CI/CD pipelines before release and assesses deployment readiness. It reviews regression risk and flaky tests, then returns a RELEASE, REMEDIATE, or BLOCK decision. CX Codex +1 104installs

Project sponsors

Companies that keep this analytics open