Qcsd Ideation Swarm
- 86 installs
- 433 repo stars
- Updated August 4, 2026
- proffesor-for-testing/agentic-qe
qcsd-ideation-swarm is a Claude Code skill for ai & agent building.
About
qcsd-ideation-swarm is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.
- qcsd-ideation-swarm
- AI & Agent Building
- AI-coding skill
Qcsd Ideation Swarm by the numbers
- 86 all-time installs (skills.sh)
- +3 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #4,996 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill qcsd-ideation-swarmAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 86 |
|---|---|
| repo stars | ★ 433 |
| Last updated | August 4, 2026 |
| Repository | proffesor-for-testing/agentic-qe ↗ |
How do I helps with ai & agent building tasks.?
Helps with ai & agent building tasks.
Who is it for?
Best when you're working on ai & agent building and need structured help with qcsd ideation swarm.
Skip if: Teams with no ai & agent building needs, or anyone wanting a generic chat assistant without this specific workflow.
When should I use this skill?
When you need to helps with ai & agent building tasks., or when qcsd-ideation-swarm is a claude code skill for ai & agent building.
What you get
Structured output aligned to qcsd-ideation-swarm: qcsd-ideation-swarm, AI & Agent Building.
Files
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-allyfollow-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.
skill: qcsd-ideation-swarm
version: 1.0.0
description: >
Evaluation suite for QCSD ideation swarm orchestration.
Tests quality criteria generation, agent coordination, and cross-domain analysis.
models_to_test:
- claude-sonnet-4-6 # Primary (high accuracy expected)
- claude-haiku-4-5 # Fast model (minimum quality floor)
mcp_integration:
enabled: true
namespace: skill-validation
query_patterns: true
track_outcomes: true
store_patterns: true
target_agents:
- qe-learning-coordinator
- qe-queen-coordinator
learning:
store_success_patterns: true
pattern_ttl_days: 90
result_format:
json_output: true
include_timing: true
include_token_usage: true
setup:
required_tools:
- jq
test_cases:
- id: tc001_quality_criteria_generation
description: "Generate quality criteria for epic"
category: qcsd
priority: critical
input:
epic_description: "Build user authentication system with OAuth2"
project_type: "web_application"
expected_output:
must_contain:
- "quality"
- "criteria"
- "security"
validation:
schema_check: true
keyword_match_threshold: 0.8
- id: tc002_risk_assessment
description: "Perform QCSD risk assessment"
category: risk
priority: critical
input:
epic: "Payment processing system"
has_security: true
has_compliance: true
expected_output:
must_contain:
- "risk"
- "security"
- "compliance"
validation:
schema_check: true
- id: tc003_domain_flag_detection
description: "Detect HAS_UI, HAS_SECURITY, HAS_UX flags"
category: flags
priority: high
input:
content: "User dashboard with real-time notifications and payment"
analyze_flags: true
expected_output:
must_contain:
- "HAS_UI"
- "HAS_SECURITY"
validation:
schema_check: true
- id: tc004_agent_coordination
description: "Coordinate multi-agent swarm execution"
category: orchestration
priority: high
input:
domain_flags:
HAS_UI: true
HAS_SECURITY: true
HAS_UX: true
expected_output:
must_contain:
- "agent"
- "coordinate"
validation:
schema_check: true
- id: tc005_comprehensive_analysis
description: "Execute comprehensive QCSD analysis"
category: analysis
priority: medium
input:
epic: "Mobile app with payment and user profiles"
include_all_domains: true
expected_output:
must_contain:
- "analysis"
- "domain"
validation:
schema_check: true
success_criteria:
pass_rate: 0.9
critical_pass_rate: 1.0
avg_reasoning_quality: 0.75
max_execution_time_ms: 300000
metadata:
author: "qe-qcsd-orchestrator"
created: "2026-02-02"
coverage_target: >
QCSD ideation swarm with 5 test cases covering quality criteria generation,
risk assessment, domain flag detection, agent coordination, and comprehensive analysis.
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://agentic-qe.dev/schemas/qcsd-ideation-swarm-output.json",
"title": "QCSD Ideation Swarm Output Schema",
"description": "Schema for QCSD ideation swarm output. Includes quality criteria, risks, test ideas, and multi-agent reports.",
"type": "object",
"required": ["skillName", "version", "timestamp", "status", "trustTier", "output"],
"properties": {
"skillName": {
"type": "string",
"const": "qcsd-ideation-swarm",
"description": "Must be 'qcsd-ideation-swarm'"
},
"version": {
"type": "string",
"pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9]+)?$"
},
"timestamp": {
"type": "string",
"format": "date-time"
},
"status": {
"type": "string",
"enum": ["success", "partial", "failed", "skipped"]
},
"trustTier": {
"type": "integer",
"const": 3
},
"output": {
"type": "object",
"required": ["summary", "qualityCriteria", "risks", "testIdeas"],
"properties": {
"summary": {
"type": "string",
"minLength": 100,
"maxLength": 3000
},
"recommendation": {
"type": "string",
"enum": ["GO", "CONDITIONAL", "NO-GO"],
"description": "Overall ideation recommendation"
},
"qualityCriteria": {
"$ref": "#/$defs/qualityCriteriaAnalysis"
},
"risks": {
"$ref": "#/$defs/riskAnalysis"
},
"testIdeas": {
"$ref": "#/$defs/testIdeasCollection"
},
"agentReports": {
"$ref": "#/$defs/agentReports"
},
"testability": {
"$ref": "#/$defs/testabilityAssessment"
},
"flagDetection": {
"$ref": "#/$defs/flagDetection"
},
"conditionalAnalysis": {
"$ref": "#/$defs/conditionalAnalysis"
},
"executiveSummary": {
"$ref": "#/$defs/executiveSummary"
},
"artifacts": {
"type": "array",
"items": {
"$ref": "#/$defs/artifact"
},
"maxItems": 20
}
}
},
"metadata": {
"$ref": "#/$defs/metadata"
},
"validation": {
"$ref": "#/$defs/validationResult"
},
"learning": {
"$ref": "#/$defs/learningData"
}
},
"$defs": {
"qualityCriteriaAnalysis": {
"type": "object",
"required": ["htsmCategories"],
"properties": {
"htsmVersion": {
"type": "string",
"default": "6.3"
},
"htsmCategories": {
"type": "array",
"items": {
"$ref": "#/$defs/htsmCategory"
},
"minItems": 5,
"maxItems": 10,
"description": "HTSM v6.3 categories analyzed"
},
"prioritySummary": {
"type": "object",
"properties": {
"p0": { "type": "integer", "minimum": 0 },
"p1": { "type": "integer", "minimum": 0 },
"p2": { "type": "integer", "minimum": 0 },
"p3": { "type": "integer", "minimum": 0 }
}
},
"crossCuttingConcerns": {
"type": "array",
"items": { "type": "string" }
}
}
},
"htsmCategory": {
"type": "object",
"required": ["name", "priority"],
"properties": {
"name": {
"type": "string",
"enum": [
"Capability", "Reliability", "Security", "Performance", "Development",
"Usability", "Charisma", "Scalability", "Compatibility", "Installability"
]
},
"priority": {
"type": "string",
"enum": ["P0", "P1", "P2", "P3"]
},
"weight": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"testabilityScore": {
"type": "integer",
"minimum": 0,
"maximum": 100
},
"evidence": {
"type": "array",
"items": {
"$ref": "#/$defs/evidenceItem"
}
},
"qualityImplication": {
"type": "string"
},
"businessImpact": {
"type": "string"
}
}
},
"evidenceItem": {
"type": "object",
"required": ["text", "type"],
"properties": {
"text": { "type": "string" },
"type": {
"type": "string",
"enum": ["direct", "inferred", "claimed"]
},
"source": { "type": "string" },
"line": { "type": "integer" }
}
},
"riskAnalysis": {
"type": "object",
"required": ["risks"],
"properties": {
"methodology": {
"type": "string",
"enum": ["SFDIPOT", "STRIDE", "custom"]
},
"totalRisks": {
"type": "integer",
"minimum": 0
},
"criticalRisks": {
"type": "integer",
"minimum": 0
},
"highestScore": {
"type": "integer",
"minimum": 0,
"maximum": 25
},
"risks": {
"type": "array",
"items": {
"$ref": "#/$defs/risk"
},
"minItems": 5,
"maxItems": 50
},
"riskDistribution": {
"type": "object",
"properties": {
"technical": { "type": "integer" },
"business": { "type": "integer" },
"quality": { "type": "integer" },
"integration": { "type": "integer" }
}
}
}
},
"risk": {
"type": "object",
"required": ["id", "description", "category", "likelihood", "impact", "score"],
"properties": {
"id": {
"type": "string",
"pattern": "^R\\d{3}$"
},
"description": { "type": "string", "minLength": 10 },
"category": {
"type": "string",
"enum": ["technical", "business", "quality", "integration"]
},
"likelihood": {
"type": "integer",
"minimum": 1,
"maximum": 5
},
"impact": {
"type": "integer",
"minimum": 1,
"maximum": 5
},
"score": {
"type": "integer",
"minimum": 1,
"maximum": 25
},
"mitigation": { "type": "string" },
"owner": {
"type": "string",
"enum": ["Dev", "QE", "Product", "Ops", "Security"]
}
}
},
"testIdeasCollection": {
"type": "object",
"required": ["ideas"],
"properties": {
"total": {
"type": "integer",
"minimum": 0
},
"ideas": {
"type": "array",
"items": {
"$ref": "#/$defs/testIdea"
},
"minItems": 5,
"maxItems": 100
},
"byCategory": {
"type": "object",
"properties": {
"functional": { "type": "integer" },
"nonfunctional": { "type": "integer" },
"exploratory": { "type": "integer" },
"regression": { "type": "integer" }
}
}
}
},
"testIdea": {
"type": "object",
"required": ["id", "title", "type"],
"properties": {
"id": {
"type": "string",
"pattern": "^TI-\\d{3}$"
},
"title": { "type": "string", "minLength": 10 },
"description": { "type": "string" },
"type": {
"type": "string",
"enum": ["functional", "nonfunctional", "exploratory", "regression", "security", "accessibility", "performance"]
},
"priority": {
"type": "string",
"enum": ["critical", "high", "medium", "low"]
},
"linkedRisks": {
"type": "array",
"items": { "type": "string" }
},
"linkedCriteria": {
"type": "array",
"items": { "type": "string" }
},
"automation": {
"type": "string",
"enum": ["automated", "manual", "hybrid"]
}
}
},
"agentReports": {
"type": "object",
"required": ["coreAgents"],
"properties": {
"coreAgents": {
"type": "array",
"items": {
"$ref": "#/$defs/agentReport"
},
"minItems": 3,
"maxItems": 3,
"description": "Must have exactly 3 core agents"
},
"conditionalAgents": {
"type": "array",
"items": {
"$ref": "#/$defs/agentReport"
},
"maxItems": 3
},
"totalAgents": {
"type": "integer",
"minimum": 3,
"maximum": 6
}
}
},
"agentReport": {
"type": "object",
"required": ["agentId", "domain", "status"],
"properties": {
"agentId": {
"type": "string",
"pattern": "^qe-[a-z][a-z0-9-]*$"
},
"domain": {
"type": "string",
"enum": [
"requirements-validation", "coverage-analysis", "security-compliance",
"visual-accessibility", "cross-domain"
]
},
"status": {
"type": "string",
"enum": ["completed", "partial", "failed", "skipped"]
},
"reportPath": { "type": "string" },
"executionTimeMs": { "type": "integer", "minimum": 0 },
"findingsCount": { "type": "integer", "minimum": 0 }
}
},
"testabilityAssessment": {
"type": "object",
"required": ["score"],
"properties": {
"score": {
"type": "integer",
"minimum": 0,
"maximum": 100
},
"grade": {
"type": "string",
"pattern": "^[A-F][+-]?$"
},
"principles": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": { "type": "string" },
"score": { "type": "integer", "minimum": 0, "maximum": 10 },
"evidence": { "type": "string" }
}
},
"minItems": 10,
"maxItems": 10
},
"blockers": {
"type": "array",
"items": { "type": "string" }
}
}
},
"flagDetection": {
"type": "object",
"required": ["HAS_UI", "HAS_SECURITY", "HAS_UX"],
"properties": {
"HAS_UI": {
"type": "boolean"
},
"HAS_SECURITY": {
"type": "boolean"
},
"HAS_UX": {
"type": "boolean"
},
"HAS_VIDEO": {
"type": "boolean"
},
"evidence": {
"type": "object",
"properties": {
"ui": { "type": "array", "items": { "type": "string" } },
"security": { "type": "array", "items": { "type": "string" } },
"ux": { "type": "array", "items": { "type": "string" } },
"video": { "type": "array", "items": { "type": "string" } }
}
}
}
},
"conditionalAnalysis": {
"type": "object",
"properties": {
"accessibility": {
"$ref": "#/$defs/accessibilityAnalysis"
},
"security": {
"$ref": "#/$defs/securityAnalysis"
},
"qualityExperience": {
"$ref": "#/$defs/qxAnalysis"
}
}
},
"accessibilityAnalysis": {
"type": "object",
"properties": {
"wcagLevel": { "type": "string", "enum": ["A", "AA", "AAA"] },
"uiComponents": { "type": "array", "items": { "type": "string" } },
"findings": { "type": "array", "items": { "type": "object" } }
}
},
"securityAnalysis": {
"type": "object",
"properties": {
"strideCategories": {
"type": "array",
"items": { "type": "string" }
},
"authRequirements": { "type": "string" },
"dataProtection": { "type": "array", "items": { "type": "object" } },
"compliance": { "type": "array", "items": { "type": "string" } }
}
},
"qxAnalysis": {
"type": "object",
"properties": {
"pact": {
"type": "object",
"properties": {
"people": { "type": "string" },
"activities": { "type": "string" },
"contexts": { "type": "string" },
"technologies": { "type": "string" }
}
},
"personas": { "type": "array", "items": { "type": "object" } },
"userJourneys": { "type": "array", "items": { "type": "string" } },
"qxRisks": { "type": "array", "items": { "type": "object" } }
}
},
"executiveSummary": {
"type": "object",
"required": ["recommendation"],
"properties": {
"recommendation": {
"type": "string",
"enum": ["GO", "CONDITIONAL", "NO-GO"]
},
"rationale": { "type": "string", "minLength": 50 },
"metrics": {
"type": "object",
"properties": {
"htsmCoverage": { "type": "integer", "minimum": 0, "maximum": 10 },
"testabilityScore": { "type": "integer", "minimum": 0, "maximum": 100 },
"acCompleteness": { "type": "integer", "minimum": 0, "maximum": 100 },
"criticalRisks": { "type": "integer", "minimum": 0 }
}
},
"immediateActions": {
"type": "array",
"items": { "type": "string" }
},
"developmentActions": {
"type": "array",
"items": { "type": "string" }
},
"preReleaseActions": {
"type": "array",
"items": { "type": "string" }
},
"followUpRecommendations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"action": { "type": "string" },
"skill": { "type": "string" },
"reason": { "type": "string" }
}
}
}
}
},
"artifact": {
"type": "object",
"required": ["type", "path"],
"properties": {
"type": {
"type": "string",
"enum": ["report", "htsm-analysis", "risk-matrix", "test-ideas", "executive-summary"]
},
"path": { "type": "string", "maxLength": 500 },
"format": {
"type": "string",
"enum": ["html", "md", "json"]
},
"description": { "type": "string" }
}
},
"metadata": {
"type": "object",
"properties": {
"executionTimeMs": { "type": "integer", "minimum": 0 },
"agentId": { "type": "string", "pattern": "^qe-[a-z][a-z0-9-]*$" },
"targetUrl": { "type": "string" },
"epicId": { "type": "string" },
"fetchMethod": {
"type": "string",
"enum": ["playwright", "webfetch", "websearch-fallback"]
}
}
},
"validationResult": {
"type": "object",
"properties": {
"schemaValid": { "type": "boolean" },
"contentValid": { "type": "boolean" },
"confidence": { "type": "number", "minimum": 0, "maximum": 1 },
"warnings": { "type": "array", "items": { "type": "string" } },
"errors": { "type": "array", "items": { "type": "string" } }
}
},
"learningData": {
"type": "object",
"properties": {
"patternsDetected": { "type": "array", "items": { "type": "string" } },
"reward": { "type": "number", "minimum": 0, "maximum": 1 },
"ideationPatterns": {
"type": "array",
"items": {
"type": "object",
"properties": {
"pattern": { "type": "string" },
"recommendation": { "type": "string" },
"outcome": { "type": "string" }
}
}
}
}
}
}
}
{
"skillName": "qcsd-ideation-swarm",
"skillVersion": "1.0.0",
"requiredTools": [
"jq"
],
"optionalTools": [],
"schemaPath": "schemas/output.json",
"requiredFields": [
"skillName",
"status",
"output"
],
"requiredNonEmptyFields": [],
"mustContainTerms": [],
"mustNotContainTerms": [],
"enumValidations": {
".status": [
"success",
"partial",
"failed",
"skipped"
]
}
}
Step 1: Analyze Epic Content (Flag Detection)
Prerequisites
- Ideation swarm skill invoked
- Epic / feature description provided (or URL for URL mode)
- OUTPUT_FOLDER determined
Instructions
URL Mode Check
If a URL was provided, this step also includes the URL-based content fetch cascade. Use the Read tool to read steps/01a-url-fetch.md for the URL fetch protocol if applicable.
Flag Detection (Check ALL flags)
HAS_UI = FALSE
Set TRUE if epic contains ANY of: UI, frontend, visual, design,
component, screen, page, form, button, modal, dialog, dashboard,
widget, interface, display, view, layout, CSS, styling
HAS_SECURITY = FALSE
Set TRUE if epic contains ANY of: authentication, authorization,
encryption, security, OWASP, token, OAuth, credentials, privacy,
compliance, vulnerability, access control
HAS_UX = FALSE
Set TRUE if epic contains ANY of: user experience, usability,
interaction design, user flow, journey, persona, accessibility,
responsive, mobile-first, navigation, onboarding
HAS_MIDDLEWARE = FALSE
Set TRUE if epic mentions middleware, ESB, message broker, MQ,
Kafka, RabbitMQ, integration bus, API gateway, pub/sub
HAS_SAP_INTEGRATION = FALSE
Set TRUE if epic mentions SAP, RFC, BAPI, IDoc, OData,
S/4HANA, EWM, ECC, ABAP, CDS view, Fiori
HAS_AUTHORIZATION = FALSE
Set TRUE if epic mentions SoD, segregation of duties,
role conflict, authorization object, RBAC, permission matrix
HAS_VIDEO = FALSE
Set TRUE if epic mentions video content, media playback,
streaming, video player, captions, subtitlesOutput flag detection results.
Success Criteria
- [ ] All flags evaluated with evidence
- [ ] Expected agent count calculated
Navigation
- On success: proceed to Step 2 by reading
steps/02-core-agents.md
Step 2: Spawn Core Agents (Parallel Batch 1)
Prerequisites
- Step 1 completed with flags
Instructions
Spawn ALL THREE core agents in ONE message
| Agent | Domain | Role |
|---|---|---|
| qe-quality-criteria-recommender | requirements-validation | HTSM v6.3 quality criteria analysis |
| qe-risk-assessor | coverage-analysis | Risk storming and risk-based testing |
| qe-requirements-validator | requirements-validation | Requirements completeness validation |
Agent 1: Quality Criteria Recommender
Apply HTSM v6.3 (10 quality categories) to the epic. Generate quality criteria with priorities. Save to: ${OUTPUT_FOLDER}/02-quality-criteria.md
Agent 2: Risk Assessor
Perform risk storming: identify risks, assess likelihood and impact, recommend risk-based test strategies. Save to: ${OUTPUT_FOLDER}/03-risk-assessment.md
Agent 3: Requirements Validator
Validate epic completeness, identify gaps, assess testability. Save to: ${OUTPUT_FOLDER}/04-requirements-validation.md
Success Criteria
- [ ] All THREE agents spawned
Navigation
- On success: proceed to Step 3 by reading
steps/03-batch1-results.md
Step 3: Wait for Batch 1 & Extract Results
Prerequisites
- Step 2: All 3 core agents spawned
Instructions
WAIT for all three. Extract: quality criteria count, risk count, testability score, requirements completeness, critical gaps identified.
Success Criteria
- [ ] All metrics extracted
Navigation
- On success: proceed to Step 4 by reading
steps/04-conditional-agents.md
Step 4: Spawn Conditional Agents (Parallel Batch 2)
Prerequisites
- Step 3 completed, flags from Step 1
Instructions
| Flag | Agent | Output File |
|---|---|---|
| HAS_UI | qe-accessibility-auditor | 05-accessibility-audit.md |
| HAS_SECURITY | qe-security-auditor | 06-security-audit.md |
| HAS_UX | qe-qx-partner | 07-ux-assessment.md |
| HAS_MIDDLEWARE | qe-middleware-validator | 08-middleware-validation.md |
| HAS_SAP_INTEGRATION | qe-sap-rfc-tester | 09-sap-assessment.md |
| HAS_AUTHORIZATION | qe-sod-analyzer | 10-sod-analysis.md |
If ALL flags FALSE, skip to Step 5.
Success Criteria
- [ ] All flagged agents completed
Navigation
- On success: proceed to Step 5 by reading
steps/05-decision-synthesis.md
Step 5: Synthesize Results & Determine Recommendation
Prerequisites
- Core and conditional results available
Instructions
Apply GO/CONDITIONAL/NO-GO logic EXACTLY
NO-GO conditions (ANY triggers NO-GO):
- Testability score < 30%
- Critical requirements gaps with no mitigation
- Security risks rated Critical with no mitigation path
- No measurable acceptance criteria
GO conditions (ALL required):
- Testability score >= 70%
- All HTSM categories assessed
- Risk assessment complete with mitigations
- Requirements validation passed
- No unresolved critical issues
Default: CONDITIONAL
Success Criteria
- [ ] FINAL RECOMMENDATION: GO / CONDITIONAL / NO-GO
Navigation
- On success: proceed to Step 6 by reading
steps/06-report-generation.md
Step 6: Generate Ideation Report
Prerequisites
- Step 5 completed
Instructions
Generate the Ideation Report (HTML if html_output flag is set, otherwise Markdown). Save to ${OUTPUT_FOLDER}/01-executive-summary.md (or .html).
Include: Executive Summary, Quality Criteria (HTSM), Risk Assessment, Requirements Validation, conditional sections, Recommended Actions, Follow-up Recommendations.
Success Criteria
- [ ] Complete report saved
Navigation
- On success: proceed to Step 7 by reading
steps/07-learning-persistence.md
Step 7: Store Learnings & Persist State
Prerequisites
- Step 6 completed
Instructions
ALWAYS RUN.
Store ideation findings:
aqe memory store \
--key "qcsd-ideation-${epicId}-${Date.now()}" \
--namespace "qcsd-ideation" \
--value '{...}' \
--jsonSave to ${OUTPUT_FOLDER}/11-learning-persistence.json.
Follow-up Recommendations
If HAS_VIDEO is TRUE, output a prominent box recommending /a11y-ally for video caption generation.
Success Criteria
- [ ] Persistence completed
Navigation
- On success: proceed to Step 8 by reading
steps/08-final-output.md
Step 8: Final Output & Completion Summary
Prerequisites
- All steps completed
Instructions
Display completion summary with: GO / CONDITIONAL / NO-GO recommendation, testability score, quality criteria count, risk count, requirements validation result, and all deliverables.
If HAS_VIDEO was TRUE, display prominent follow-up recommendation for /a11y-ally.
Success Criteria
- [ ] Summary displayed
Navigation
- Terminal step.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What does qcsd-ideation-swarm do?
qcsd-ideation-swarm is a Claude Code skill for ai & agent building.
When should I use qcsd-ideation-swarm?
When you need to helps with ai & agent building tasks., or when qcsd-ideation-swarm is a claude code skill for ai & agent building.
What are the main capabilities?
qcsd-ideation-swarm; AI & Agent Building; AI-coding skill.
AI & Agent Buildingagents