testgen-flow-requirements-document-generation

<testgen_flow_requirements_document_generation>

<description_and_purpose> Synthesize Issue Tracker data, Wiki documentation, and user answers into a comprehensive, structured requirements document with user stories, functional/non-functional requirements, constraints, and traceability. </description_and_purpose>

<workflow_context>

• Phase 4 of 7 in testgen-flow
• Input: raw-data.md, analysis.md, answers.md
• Output: requirements.md — primary deliverable for test case generation
• Required skills: qa-knowledge (synthesis mode)
• Prerequisite: Phase 0-3 complete with validated user answers
• Priority order for source resolution: User answers > Issue Tracker ticket > Wiki > Analysis insights </workflow_context>

<phase_steps>

1. Load all source data
2. Synthesize requirements
3. Create requirements document
4. Update state file </phase_steps>

<load_sources step="4.1">

1. Read all previous phase outputs:
   • plans/testgen-{TICKET-KEY}/raw-data.md — Issue Tracker + Wiki data
   • plans/testgen-{TICKET-KEY}/analysis.md — identified issues
   • plans/testgen-{TICKET-KEY}/answers.md — user clarifications </load_sources>

<synthesize_requirements step="4.2" subagent="architect" role="Requirements engineer">

1. USE SKILL qa-knowledge (synthesis mode). The mode EMITS into this phase's <create_requirements_document> section contract; the phase OWNS the document skeleton and output path.
2. Source priority: User answers (Phase 3) > Issue Tracker ticket > Wiki docs > Analysis insights
3. Resolve contradictions using user answers; fill gaps using user answers; flag unresolved items as assumptions
4. Generate: user stories (US-N), functional requirements (FR-N), non-functional requirements (NFR-N), constraints (C-N), dependencies (D-N), assumptions (A-N), risks (R-N)
5. Build traceability matrix linking requirements to ticket/Wiki sources </synthesize_requirements>

<create_requirements_document step="4.3">

Create plans/testgen-{TICKET-KEY}/requirements.md. The qa-knowledge synthesis mode emits per its synthesis rules and its synthesis output schemas (owned internally by the skill).

Section contract (phase-owned SSoT) — the table below is the authoritative phase contract the synthesis mode MUST satisfy, not a parallel restatement. The mode's document wrapper uses the same scheme (front-matter + 10 numbered sections). If the emitted skeleton drifts from this table, the phase fails verification and re-invokes rather than accepting a divergent shape; the phase bounds the contract, the skill is the implementation.

#	Section	Per-entry shape (synthesis schema)
Front-matter	Document Control + Executive Summary	(Executive Summary extended below for testgen)
1	User Stories	US-[N] entries (user-stories schema)
2	Functional Requirements	FR-[N] entries (functional-requirements schema)
3	Non-Functional Requirements	NFR-[N] entries (non-functional-requirements schema)
4	Constraints	C-[N] entries (constraints-and-dependencies schema)
5	Dependencies	D-[N] entries (constraints-and-dependencies schema)
6	Out of Scope	Explicit exclusions with rationale
7	Assumptions	A-[N] entries (assumptions-and-risks schema)
8	Risks	R-[N] entries (assumptions-and-risks schema)
9	Traceability Matrix	(Extended below for testgen)
10	Glossary	Domain terms + acronyms

If any section is absent from the emitted document, the artifact is incomplete — re-invoke the skill or repair before declaring step 4.3 complete.

Testgen-specific additions layered on top of the canonical structure:

Executive Summary must include:

## Executive Summary

**Project**: [Project Name]
**Ticket**: [TICKET-KEY]
**Description**: [2-3 sentence overview]

**Scope Summary**:
- [Key capability 1]
- [Key capability 2]

**Sources**:
- Ticket: [TICKET-KEY]
- Wiki: [N] pages
- User Clarifications: [N] questions answered

**Source Resolution**:
- Contradictions Resolved: [Count]
- Gaps Filled: [Count]
- Ambiguities Clarified: [Count]