Requirements Author
MicrosoftOfficialPublished by Microsoft
- Skill
- Guidelines
- Business and productivity
- CC-BY-4.0
- No issues found
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The Requirements Author skill provides a structured methodology for managing the lifecycle of Business Requirements Documents (BRD) and Product Requirements Documents (PRD). It defines clear phases for discovery, definition, and governance, ensuring that requirements are testable, traceable, and ready for downstream implementation. The skill includes canonical templates, quality rubrics, and standardized handoff contracts to ensure consistency across project stages and agent sessions.
What it does
- Provides canonical templates for BRD and PRD documentation.
- Defines a multi-phase lifecycle for requirements from discovery to governance.
- Establishes strict quality rubrics and atomicity checklists for acceptance criteria.
- Manages traceability between business goals, functional requirements, and acceptance criteria.
- Standardizes handoff payloads between BRD and PRD phases.
- Maintains version lineage and governance records for approved requirements.
When to use it
- When initiating a new project requiring formal business or product requirements.
- When transitioning from business-level objectives to product-level specifications.
- When you need to ensure requirements are testable, unambiguous, and traceable.
- When establishing a governance process for document approval and version control.
Advantages
- Ensures consistency in documentation structure and naming conventions.
- Reduces ambiguity through rigorous atomicity and quality checks.
- Facilitates seamless handoffs between business and product teams.
- Provides clear audit trails through version lineage and governance logs.
Usage examples
- “Initialize a new BRD for the upcoming project using the canonical template.”
- The agent sets up the BRD structure, applying the required frontmatter and initializing the Discover phase.
- “Validate the current set of acceptance criteria for the PRD.”
- The agent applies the atomicity checklist to ensure each criterion is testable, atomic, and follows the defined quality rubric.
Install
Download the skill as a ZIP:
https://autogineer.com/agent-skills/microsoft/requirements-author/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip requirements-author.zip -d .agents/skills
Documentation by Microsoft
Requirements Author Skill
Overview
This skill defines how to produce and evolve requirements documents across the project lifecycle for two document types: the Business Requirements Document (BRD) and the Product Requirements Document (PRD). Shared requirements-engineering knowledge lives in references/_shared/, while BRD-specific and PRD-specific knowledge live in references/brd/ and references/prd/ so each consuming agent loads only what its document needs.
The canonical BRD template is brd-full.md with its brd-frontmatter-overlay.md, and the canonical PRD template is prd-full.md. The BRD Builder dispatches into the BRD phase anchors (#discover, #define, #govern); the PRD Builder dispatches into the PRD phase anchors (#prd-assess through #prd-finalize).
Use this skill with the references for the active document scope:
Shared (references/_shared/):
BRD scope (references/brd/):
PRD scope (references/prd/):
Handoff Transport Convention
The producing workflow owns each handoff's canonical transport, and the
consumer validates the complete payload regardless of transport. An outcome
hypothesis returns OUTCOME_HYPOTHESIS_TO_BRD_HANDOFF_V1 inline by default
because it is a one-time seed derived from an already persisted source
artifact; the user may instead supply a separately persisted payload path.
BRD Govern persists BRD_TO_PRD_HANDOFF_V1 and returns its path because that
payload is a durable governance record consumed across agent sessions. This
asymmetry is intentional and does not change payload authority or validation.
BRD Lifecycle
| Phase | Primary objective | Entry condition | Exit condition |
|---|---|---|---|
| Discover | Establish business context, stakeholder scope, and problem framing | Request or initiative is in intake | Discover hard gate passes and artifacts are complete |
| Define | Produce complete, testable, and traceable requirements content | Discover artifacts are approved for elaboration | Define hard gate passes with quality evidence |
| Govern | Finalize, approve, and supersede BRD versions under lineage controls | Define package is approved for governance review | Govern hard gate passes and publication artifacts are recorded |
Discover {#discover}
Activities
Capture business context, drivers, imposed constraints, and expected outcomes.
Identify stakeholders, decision owners, and review participants.
Define scope boundaries, assumptions, and dependency surfaces.
Draft initial requirement candidates and map early traceability placeholders.
Validate and disposition an
OUTCOME_HYPOTHESIS_TO_BRD_HANDOFF_V1payload when one is supplied.
Outcome hypothesis intake
Use Outcome Hypothesis-to-BRD Handoff as the canonical contract.
Accept the YAML inline or from a user-supplied artifact path.
Validate the complete payload before copying any value into the BRD.
Reject unsupported versions, incomplete seeds, placeholder values, and invalid provenance. Do not reinterpret a rejected payload as unstructured evidence.
Assign the next stable
BG-###identifier.Record distinct statement, KPI, baseline, target, timeframe, measurement source, and owner values.
Mark each seed field
acceptedorrevised. For a revision, preserve the source value, current BRD value, and rationale.Map assumptions and open questions into their canonical BRD sections. Initialize each imported question to
Openunless Discover explicitly confirms another BRD-owned status. Every deferred question requires a rationale for deferral and one target phase:PRD,Implementation,Operations, orFuture-Release.Record the handoff ID, source path, source SHA-256, and KPI measurement source in the BRD provenance receipt.
Before Discover accepts the handoff, the validated payload is authoritative for imported seed values. Discover may explicitly accept or revise those values. After Discover exits, the BRD is authoritative. A later hypothesis change requires a new validated payload and explicit Discover re-entry.
Hard exit gate
Discover exits only when:
Scope is bounded and stakeholder ownership is explicit.
Core assumptions and constraints are documented and reviewable.
Seed artifacts needed for Define are present and internally consistent.
Any outcome-hypothesis handoff has passed validation, every imported seed field has an explicit disposition, and its provenance receipt is complete.
Output artifacts
Discover summary and scope statement.
Stakeholder inventory with role and ownership mapping.
Initial assumption and constraint register.
Seed requirement and traceability scaffold for Define.
Outcome-hypothesis receipt and field dispositions when a handoff was supplied.
Define {#define}
Activities
Author full BRD content using brd-full.md and the canonical naming rules.
Refine business goals and requirement sets with clear acceptance intent.
Build and verify author-maintained traceability links across FR, AC, BG, and BR records.
Perform quality assessment using the BRD quality reporting contract.
Hard exit gate
Define exits only when:
Requirement content is complete, unambiguous, and testable.
Traceability links satisfy the active ID schema and naming policy.
FR-to-AC coverage meets the active
fr_to_ac_coverage_threshold_pctor has a recorded blocker.Quality findings are generated and reviewed against the defined rubric.
Output artifacts
Full BRD draft package with structured sections.
Author-maintained traceability matrix aligned to naming and ID conventions.
BRD quality findings and consolidated quality report payloads.
Define gate decision record with reviewer notes.
Govern {#govern}
Activities
Prepare final BRD for approval with version metadata and lineage fields.
Bump approved BRDs from draft
0.x.yversions to1.0.0or higher.Resolve or disposition remaining quality findings.
Publish approved BRD outputs and downstream handoff payloads.
Maintain supersession chain when issuing replacement BRD versions.
Govern handoff production
Before emitting BRD_TO_PRD_HANDOFF_V1, the BRD Builder applies the coverage and waiver validation rules in BRD-to-PRD Handoff, including zero-FR coverage handling. It records the following values from the signed-off BRD and final quality review:
A lowercase SHA-256 hash of the exact BRD artifact bytes at signoff.
Counts for FR, NFR, BR, CON, AC, and BG identifiers using id-schema.md.
FR-to-AC and FR-to-BG coverage metrics from the author-maintained traceability matrix.
The final
BRD_QUALITY_REPORT_V1reference, overall status, and Govern decision.Signoff approvers, roles, decisions, approval timestamps, comments, and active waivers.
Waiver records for any accepted FR-to-AC threshold gap or FR-to-BG target gap.
After validation succeeds, write the complete YAML payload to .copilot-tracking/brd-sessions/<brd-name>.handoff.yml, record that path in BRD session state, and return the path with a compact Govern summary. Do not rely on an inline chat payload as the downstream transport.
Hard exit gate
Govern exits only when:
Approval status and required reviewers are recorded.
Version and lineage metadata are valid and complete.
The final quality report authorizes Govern exit.
Handoff artifacts are published for downstream consumers.
Output artifacts
Approved BRD release artifact.
BRD-to-PRD handoff payload.
Governance decision log with approval evidence.
Supersession linkage record for replaced BRD versions.
Status taxonomy
Use the following status values for BRD lifecycle tracking:
draft: Actively authored or revised.in-review: Under formal review and gate validation.approved: Accepted for governed use.superseded: Replaced by a newer approved BRD.
Quality rubric pointer
Apply the BRD quality rubric and payload contracts from BRD Quality Formats together with guidance in Requirements Definition. Treat rubric results as gate evidence for Define and Govern decisions. The BRD Quality Reviewer emits both standard findings and the consolidated quality report.
Supersession lineage rules
A BRD can supersede one or more earlier BRDs when scope is merged.
A BRD can be superseded by only one approved successor version.
Every supersession event records
supersedesandsuperseded_bylinks.Supersession preserves historical artifacts for auditability.
PRD Lifecycle
The PRD Builder agent runs a seven-phase lifecycle. Each phase has its own section anchor below so the agent loads only the guidance for the active phase.
| Phase | Section anchor | Primary objective |
|---|---|---|
| Assess | #prd-assess | Determine whether enough context exists to create PRD files. |
| Discover | #prd-discover | Establish the PRD title, scope, and product goals. |
| Create | #prd-create | Generate the PRD file and state file once context is clear. |
| Build | #prd-build | Gather detailed requirements iteratively. |
| Integrate | #prd-integrate | Incorporate references, documents, and external materials. |
| Validate | #prd-validate | Ensure completeness and quality before approval. |
| Finalize | #prd-finalize | Deliver the complete, actionable PRD. |
PRD Assess {#prd-assess}
Activities
Determine whether enough product context exists to create PRD artifacts.
Identify the initiative, problem statement, and primary target users.
Check for an upstream
BRD_TO_PRD_HANDOFF_V1artifact path and ingest its coverage and waiver context when present.Check for an upstream feasibility-to-PRD handoff. Follow Feasibility-to-PRD Handoff to recognize it by
kind, verify required metadata, verdict field presence, and a readable workspace-relative study path. Treat feasibility as supplementary evidence and preserve approved BRD scope.For a new session, carry the handoff kind, path, ingest timestamp, verdict, and study revision identifier in the Assess output until Create writes the state file. When state already exists, update its feasibility-specific metadata object directly. Keep raw candidate content in the handoff artifact.
Decide whether to gather more context or proceed to file creation.
Hard exit gate
Assess exits only when:
A meaningful kebab-case PRD name can be derived.
Problem framing and primary users are identified.
Any available BRD handoff artifact has been read, its payload validated, and its coverage metrics recorded.
Any available feasibility handoff is recognized by
kind, has readable workspace-relative paths, a valid verdict shape, and normalized metadata ready for Create or persisted in existing state.
Output artifacts
Assess summary noting context sufficiency.
Derived working title for the PRD.
Ingested handoff context when a BRD handoff payload exists.
Feasibility verdict, evidence summary, constraints, gaps, and normalized handoff metadata when a feasibility handoff exists. Negative verdicts create no candidate dispositions.
PRD Discover {#prd-discover}
Activities
Ask focused questions to establish the PRD title, scope, and product goals.
Explore the problem space using Product Discovery and MVP Framing.
Capture target users, candidate success metrics, and explicit non-goals using Metrics Frameworks.
Hard exit gate
Discover exits only when:
Title and scope are explicit.
Primary users and candidate success metrics are named.
In-scope and out-of-scope boundaries are recorded.
Output artifacts
Discovery summary.
Scope and non-goals statement.
Candidate success metrics.
PRD Create {#prd-create}
Activities
Generate the PRD file from prd-full.md and create the session state file once title and context are clear.
Populate the skeleton with the established scope, users, and goals.
Seed the iterative requirement and metric structure for Build.
When Assess produced normalized feasibility metadata, write its fields atomically to the new state file as
feasibilityHandoff, carryingkind,path,ingestedAt,verdict, andstudyRevisionId. State written before this contract may carryschemaVersioninstead ofkind; read it without error and rewrite the object to the current shape on the next feasibility metadata update. Do not persist raw candidate content.
Hard exit gate
Create exits only when:
The PRD file and state file exist.
The skeleton matches the canonical PRD structure.
Initial scope and goals are seeded.
Any normalized feasibility metadata from Assess is present in the newly created state before Build begins.
Output artifacts
PRD draft skeleton.
PRD session state file.
Seeded scope and goals sections.
Feasibility handoff metadata persisted when supplied.
PRD Build {#prd-build}
Activities
Gather detailed functional and non-functional requirements iteratively.
When
feasibilityHandoffis present, read candidate content from its workspace-relative path. Stop if ingestion was reported but metadata is absent or the path is unreadable.Give every forward-verdict feasibility candidate exactly one PRD-owned disposition:
accepted-fr,accepted-nfr,accepted-constraint,retained-gap,rejected, ordeferred. Treat concern hints as advisory evidence only.Allocate final
FR-###,NFR-###, orCON-###identifiers only after authoring and accepting the PRD statement. Preserve source handoff ID, source candidate ID, evidence references, disposition, rationale, and resulting PRD ID in the Feasibility Candidate Disposition register.Preserve signed-off BRD authority. Record and explicitly resolve BRD and feasibility conflicts, or retain them as Build gaps when current evidence cannot support a responsible resolution.
Author acceptance criteria using EARS Acceptance and the Connextra Template.
Classify non-functional requirements with the NIST 800-160 NFR taxonomy and check stories against INVEST.
Maintain author traceability across requirements, goals, and metrics using Traceability Naming, Traceability Matrix, and id-schema.md.
Hard exit gate
Build exits only when:
Requirements are complete, testable, and traceable.
Acceptance criteria follow EARS or Given-When-Then form.
Non-functional requirements are categorized.
Coverage meets the active thresholds or records a blocker.
Every forward-verdict feasibility candidate has exactly one disposition row, every accepted row names its final PRD ID, and negative verdicts have no candidate rows.
Output artifacts
Full PRD requirement set.
Author-maintained traceability matrix.
Acceptance criteria and NFR classifications.
Feasibility Candidate Disposition register when a forward feasibility handoff exists.
PRD Integrate {#prd-integrate}
Activities
Incorporate user-provided references, documents, and external materials.
Reconcile incoming content with existing requirements and resolve conflicts.
Link supporting evidence to requirements and metrics.
Hard exit gate
Integrate exits only when:
Provided references are incorporated or explicitly deferred.
Conflicts between sources are resolved.
Supporting evidence is linked.
Output artifacts
Updated PRD sections with integrated references.
Reference and evidence linkage record.
PRD Validate {#prd-validate}
Activities
Assess completeness and quality before approval.
Run the PRD Quality Reviewer to emit
PRD_STANDARD_FINDINGS_V1andPRD_QUALITY_REPORT_V1per PRD Quality Formats.Review findings against the rubric and resolve or disposition gaps.
Hard exit gate
Validate exits only when:
Quality findings and the consolidated report are generated.
The report authorizes Validate exit via
gate_decisions.validate_exit.Coverage and quality thresholds are met or waived.
Output artifacts
PRD quality findings and report payloads.
Validate gate decision record.
PRD Finalize {#prd-finalize}
Activities
Deliver the complete, actionable PRD.
Resolve remaining findings and record version and approval metadata.
Run a Finalize drift check and publish downstream artifacts.
Hard exit gate
Finalize exits only when:
Approval status and required reviewers are recorded.
The final quality report authorizes Finalize exit via
gate_decisions.finalize_exit.No unresolved blocking findings remain.
Output artifacts
Approved PRD release artifact.
Finalize decision log with approval evidence.
References
The skill bundles reference documents under references/, organized into three scopes: shared requirements-engineering knowledge in references/_shared/, BRD-specific knowledge in references/brd/, and PRD-specific knowledge in references/prd/. Load a reference body only when its phase activity requires it; each body links to its own sub-references (standards pointers, scoring sheets, and worked examples).
Shared references (references/_shared/)
requirements-definition.md - Requirement categories, canonical statement form, acceptance-criteria formats, and quality dimensions.
stakeholder-analysis.md - Mendelow Power/Interest grid and RACI accountability variants.
process-modeling.md - Optional process, decision, and structural diagram guidance.
prioritization-schemes.md - Required MoSCoW prioritization scheme.
traceability-naming.md - Requirement, goal, and decision identifier routing plus traceability conventions.
id-schema.md - Canonical prefix, digit, and adjacent identifier rules.
traceability-matrix.md - Author-maintained FR-to-AC, FR-to-BG, and BR-to-FR matrix views.
design-decisions.md - Registry for
DD-###design decision codes.quality-rubric.md - Operational status taxonomy (
RISK/CAUTION/COVERED/NOT_APPLICABLE) and the gate decision rule.standards-excerpts.md - Cite-only registry of third-party standards (ISO, IIBA, PMI, ISTQB) referenced by name.
BRD references (references/brd/)
brd-quality-formats.md - Producer and consumer map for the BRD data contracts.
requirements-quality-rubric.md - Combined per-requirement, per-NFR-category, and per-business-goal scoring sheets.
handoff-payload-schema.md - BRD-author view of the BRD-to-PRD handoff payload.
PRD references (references/prd/)
product-discovery.md - Problem-space exploration and discovery questioning for PRD scope.
mvp-framing.md - MVP framing and scope-boundary guidance.
metrics-frameworks.md - JTBD, HEART, and AARRR success-metric frameworks.
ears-acceptance.md - EARS acceptance-criteria patterns for PRD requirements.
nist-800-160-nfr.md - NIST 800-160 non-functional requirement taxonomy.
invest.md - INVEST quality criteria for user stories.
connextra-template.md - Connextra user-story template.
prd-quality-formats.md - Producer and consumer map for the PRD data contracts.
feasibility-to-prd-handoff.md - Consumer rules for feasibility Assess ingestion, Create persistence, Build disposition, BRD coexistence, and source traceability.
Templates
Templates under templates/ are selected by the document frontmatter and canonical document shape.
brd-full.md - Canonical BRD template covering every section from Executive Summary through Sign-Off.
brd-frontmatter-overlay.md - Schema for BRD YAML frontmatter, including
diagram_format, lineage, coverage thresholds, and requirement-prefix overrides.diagram-mermaid.md - Mermaid flowchart fragment; the default diagram format.
diagram-ascii.md - ASCII process-diagram fragment for low-fidelity Discover-phase sketches.
prd-full.md - Canonical PRD template covering every section from product overview through acceptance and metrics.
Data Contracts
Payload contracts govern quality assessment and downstream handoff for each document type. The quality and BRD handoff payloads carry a fixed schema_version; consumers fail fast on any other value, so those constants MUST NOT change. The feasibility-to-PRD handoff instead carries a plain kind marker, because its producer and consumer ship together and no version negotiation applies.
BRD data contracts:
| Contract | schema_version | Reference |
|---|---|---|
| Standard findings | BRD_STANDARD_FINDINGS_V1 | brd-standard-findings-v1.md |
| Quality report | BRD_QUALITY_REPORT_V1 | brd-quality-report-v1.md |
| BRD-to-PRD handoff | BRD_TO_PRD_HANDOFF_V1 | brd-to-prd-handoff-v1.md |
PRD data contracts:
| Contract | schema_version | Reference |
|---|---|---|
| Standard findings | PRD_STANDARD_FINDINGS_V1 | prd-standard-findings-v1.md |
| Quality report | PRD_QUALITY_REPORT_V1 | prd-quality-report-v1.md |
Upstream PRD input contracts:
| Contract | Identifier | Reference |
|---|---|---|
| BRD-to-PRD handoff | schema_version: BRD_TO_PRD_HANDOFF_V1 | brd-to-prd-handoff-v1.md |
| Feasibility-to-PRD handoff | kind: feasibility-to-prd-handoff | feasibility-to-prd-handoff.md |
The PRD lifecycle consumes both upstream contracts during Assess. BRD input supplies approved business context, coverage, and waivers. Feasibility input supplies a confirmed verdict, evidence, constraints, gaps, and candidate proposals for PRD Build. Neither contract bypasses PRD authoring.
Mandatory Load Directives
The BRD Builder and PRD Builder agents each enforce a phase → section load contract. Each phase MUST load its section of this skill before executing phase work, and MUST append the section anchor to state.phaseSkillsLoaded.
BRD Builder directives:
| Phase | Section anchor | Required phaseSkillsLoaded entry |
|---|---|---|
| Discover | #discover | brd-author#discover |
| Define | #define | brd-author#define |
| Govern | #govern | brd-author#govern |
PRD Builder directives:
| Phase | Section anchor | Required phaseSkillsLoaded entry |
|---|---|---|
| Assess | #prd-assess | prd-author#assess |
| Discover | #prd-discover | prd-author#discover |
| Create | #prd-create | prd-author#create |
| Build | #prd-build | prd-author#build |
| Integrate | #prd-integrate | prd-author#integrate |
| Validate | #prd-validate | prd-author#validate |
| Finalize | #prd-finalize | prd-author#finalize |
The agent reads sections of this skill file and records the entry in state.phaseSkillsLoaded before any phase work executes. phaseSkillsLoaded is durable load history, not proof that the guidance is present in the current model context. Within one live context, re-entering a phase whose section was already read does not require reloading. After a cold start, resume, or context summarization, the agent reloads the current phase section even when its entry is recorded.
Source Attribution
The bundled reference bodies cite third-party standards and frameworks by name and clause only; no upstream prose is reproduced or paraphrased. Where a reference names a standard's characteristics or categories, the accompanying review criteria, anchors, and indicators are original Microsoft content under CC BY 4.0, not reproductions of the standard's definitions; the authoritative definitions live in the cited standards. The cite-only registry in standards-excerpts.md is the single place new standards citations are added. Standards referenced by name include ISO/IEC/IEEE 29148:2018, ISO/IEC 25010:2023, IIBA BABOK v3, PMI Business Analysis for Practitioners, the ISTQB Glossary, OMG BPMN / DMN / UML, the Cucumber Gherkin pattern, and MoSCoW prioritization, each the property of its respective rights holder.
License
This skill is original Microsoft content licensed under CC BY 4.0.
Files
- ATTRIBUTION.mdAdded by AutoGineer981 B
- LICENSEAdded by AutoGineer16.6 KiB
- SKILL.md28.0 KiB
- references/_shared/atomicity-checklist.md5.8 KiB
- references/_shared/design-decisions.md2.0 KiB
- references/_shared/diagram-format-selector.md5.5 KiB
- references/_shared/given-when-then.md5.5 KiB
- references/_shared/id-schema.md6.9 KiB
- references/_shared/iso-29148-quality-attrs.md4.7 KiB
- references/_shared/mendelow-matrix.md5.3 KiB
- references/_shared/moscow.md3.6 KiB
- references/_shared/prioritization-schemes.md6.8 KiB
- references/_shared/process-modeling.md6.0 KiB
- references/_shared/quality-rubric.md5.4 KiB
- references/_shared/raci-patterns.md7.7 KiB
- references/_shared/requirements-definition.md13.2 KiB
- references/_shared/rpi-research-integration.md14.7 KiB
- references/_shared/smart-rubric.md5.6 KiB
- references/_shared/stakeholder-analysis.md7.9 KiB
- references/_shared/standards-excerpts.md11.9 KiB
- references/_shared/traceability-matrix.md5.2 KiB
- references/_shared/traceability-naming.md6.1 KiB
- references/brd/brd-quality-formats.md4.5 KiB
- references/brd/brd-quality-report-v1.md16.8 KiB
- references/brd/brd-standard-findings-v1.md13.5 KiB
- references/brd/brd-to-prd-handoff-v1.md12.6 KiB
- references/brd/handoff-payload-schema.md8.2 KiB
- references/brd/iso-25010-nfr-taxonomy.md5.5 KiB
- references/brd/iso-29148-quality-gate.md8.6 KiB
- references/brd/istqb-testability.md5.3 KiB
- references/brd/outcome-hypothesis-to-brd-handoff-v1.md11.7 KiB
- references/brd/requirements-quality-rubric.md14.0 KiB
- references/prd/connextra-template.md4.4 KiB
- references/prd/ears-acceptance.md4.9 KiB
- references/prd/feasibility-to-prd-handoff.md4.4 KiB
- references/prd/invest.md4.1 KiB
- references/prd/metrics-frameworks.md4.3 KiB
- references/prd/mvp-framing.md3.6 KiB
- references/prd/nist-800-160-nfr.md6.5 KiB
- references/prd/prd-quality-formats.md4.4 KiB
- references/prd/prd-quality-report-v1.md17.6 KiB
- references/prd/prd-standard-findings-v1.md14.6 KiB
- references/prd/product-discovery.md7.1 KiB
- templates/brd/brd-frontmatter-overlay.md7.5 KiB
- templates/brd/brd-full.md13.6 KiB
- templates/brd/diagram-ascii.md2.3 KiB
- templates/brd/diagram-mermaid.md989 B
- templates/prd/prd-full.md13.5 KiB
references/prd/prd-quality-report-v1.md
description: 'PRD_QUALITY_REPORT_V1 schema - PRD-level quality report emitted by PRD Quality Reviewer with gate decisions, thresholds, summaries, and recommendations'
PRD Quality Report — PRD_QUALITY_REPORT_V1
This document defines the PRD_QUALITY_REPORT_V1 payload emitted by the PRD Quality Reviewer subagent (prd-quality-reviewer). One payload is produced per Validate-exit, Finalize-exit, Finalize drift, or on-request PRD quality run in the same invocation as the paired PRD_STANDARD_FINDINGS_V1 payload. The PRD payload mirrors the BRD-side BRD_QUALITY_REPORT_V1 shape, diverging only where the PRD lifecycle gates, NFR taxonomy, and identifier set differ.
Purpose
The payload provides the PRD Builder orchestrator with the only quality gate decision record. It owns gate_decisions.validate_exit, gate_decisions.finalize_exit, and the threshold-to-decision rules that convert reviewer findings into gate outcomes.
Format
The payload is YAML.
schema_version: PRD_QUALITY_REPORT_V1
report_id: <REPORT_ID>
generated_at: <ISO_8601_TIMESTAMP>
prd:
id: <PRD_ID>
version: <PRD_VERSION>
phase: <PRD_PHASE>
artifact_path: <PRD_ARTIFACT_PATH>
overall_status: <OVERALL_STATUS>
decision_thresholds:
iso_29148_core_min_score: <MIN_CORE_SCORE>
fr_to_ac_min_pct: <FR_AC_MIN_PCT>
fr_to_goal_target_pct: <FR_GOAL_TARGET_PCT>
gate_decisions:
validate_exit: <GATE_DECISION>
finalize_exit: <GATE_DECISION>
summary_counts:
RISK: <RISK_COUNT>
CAUTION: <CAUTION_COUNT>
COVERED: <COVERED_COUNT>
NOT_APPLICABLE: <NA_COUNT>
severity_breakdown:
CRITICAL: <CRITICAL_COUNT>
HIGH: <HIGH_COUNT>
MEDIUM: <MEDIUM_COUNT>
LOW: <LOW_COUNT>
standards_assessed:
- skill_name: <STANDARD_SKILL_NAME>
skill_version: <STANDARD_SKILL_VERSION>
overall_status: <STANDARD_OVERALL_STATUS>
findings_ref: <FINDINGS_PAYLOAD_PATH>
findings_count: <FINDINGS_COUNT>
category_summaries:
iso_29148:
average_score: <AVERAGE_SCORE>
weakest_attribute: <ATTRIBUTE_NAME>
weakest_attribute_score: <ATTRIBUTE_SCORE>
nist_800_160:
covered_categories: <COVERED_COUNT>
missing_categories:
- <CATEGORY_NAME>
smart:
goals_total: <GOALS_TOTAL>
goals_passing: <GOALS_PASSING>
pass_rate_pct: <PASS_RATE_PCT>
fr_ac_coverage:
fr_total: <FR_TOTAL>
fr_with_ac: <FR_WITH_AC>
coverage_pct: <COVERAGE_PCT>
threshold_pct: <THRESHOLD_PCT>
fr_goal_coverage:
fr_total: <FR_TOTAL>
fr_with_goal: <FR_WITH_GOAL>
goal_total: <GOAL_TOTAL>
coverage_pct: <COVERAGE_PCT>
target_pct: <TARGET_PCT>
waiver_required: <BOOLEAN>
top_findings:
- finding_id: <FINDING_ID>
standard: <STANDARD_SKILL_NAME>
severity: <FINDING_SEVERITY>
status: <FINDING_STATUS>
location:
section: <PRD_SECTION>
line_range: <LINE_RANGE>
finding: <FINDING_DESCRIPTION>
recommendation: <RECOMMENDATION>
recommendations:
- id: <RECOMMENDATION_ID>
priority: <RECOMMENDATION_PRIORITY>
target_section: <PRD_SECTION>
action: <RECOMMENDATION_ACTION>
related_finding_ids:
- <FINDING_ID>
warnings:
- id: <WARNING_ID>
severity: <WARNING_SEVERITY>
message: <WARNING_MESSAGE>
related_finding_ids:
- <FINDING_ID>
notes: <REPORT_NOTES>Field definitions
Top-level metadata
schema_version(string, required) — MUST bePRD_QUALITY_REPORT_V1.report_id(string, required) — Unique identifier for this report. Recommended form:<prd_id>-quality-<ISO_8601_basic_timestamp>.generated_at(string, required) — ISO 8601 timestamp (UTC) when the report was generated.
prd (object, required)
Same shape as prd in PRD_STANDARD_FINDINGS_V1, minus partition_id. Reports are always PRD-level.
id,version,phase,artifact_path— required strings; see PRD Standard Findings V1 for definitions.
overall_status (string, required)
One of:
PASS— No reviewer finding hasstatus: RISKorstatus: CAUTION, and all threshold rules are met.NEEDS_REVIEW— One or more reviewer findings hasstatus: CAUTION, or a warning-level threshold rule needs acknowledgement or waiver, and no blocking threshold rule is breached.FAIL— One or more reviewer findings hasstatus: RISK, or any blocking threshold rule is breached.
decision_thresholds (object, required)
Thresholds the PRD Quality Reviewer applied when deriving gate_decisions from the paired findings payload.
iso_29148_core_min_score(integer, required) — Minimum acceptable score for core ISO 29148 attributes. MUST be2unless a future schema version changes the threshold.fr_to_ac_min_pct(number, required) — Minimum FR-to-AC coverage percentage required by the active PRD frontmatter. Default is80.0when the PRD does not override it.fr_to_goal_target_pct(number, required) — Target FR-to-product-goal coverage percentage. MUST be100.0; gaps are waivable only through Finalize signoff.
gate_decisions (object, required)
validate_exit(string, required) — One ofAPPROVED,APPROVED_WITH_COMMENTS,BLOCKED,NOT_EVALUATED. MUST beBLOCKEDwhenoverall_statusisFAIL.finalize_exit(string, required) — One ofAPPROVED,APPROVED_WITH_COMMENTS,BLOCKED,NOT_EVALUATED. MUST beNOT_EVALUATEDwhen the PRD phase is any ofAssess,Discover,Create,Build,Integrate, orValidate.
summary_counts (object, required)
Integer counts of findings by status from the paired PRD_STANDARD_FINDINGS_V1 payload. Same key set as PRD_STANDARD_FINDINGS_V1.summary_counts. Each value MUST be ≥ 0.
severity_breakdown (object, required)
Integer counts of RISK and CAUTION findings by severity from the paired PRD_STANDARD_FINDINGS_V1 payload. COVERED and NOT_APPLICABLE findings (severity N/A) are excluded.
CRITICAL,HIGH,MEDIUM,LOW(integer, required, ≥ 0).
standards_assessed (array, required)
Single-element reviewer assessment array. The array shape is retained for compatibility with existing consumers, but PRD Quality Reviewer MUST emit exactly one entry representing its combined requirements quality review. It is not a multi-subagent fan-in list.
skill_name(string, required) — Reviewer rubric skill bundle name. Userequirements-qualityfor the combined PRD quality review.skill_version(string, required) —spec_versionof the reviewer rubric skill.overall_status(string, required) — Mirrors the pairedPRD_STANDARD_FINDINGS_V1.overall_status.findings_ref(string, optional) — Workspace-relative path to the persistedPRD_STANDARD_FINDINGS_V1payload, when persisted by the orchestrator. Omit when the report and findings are returned inline.findings_count(integer, required, ≥ 0).
category_summaries (object, required)
Rollup statistics derived from the paired PRD_STANDARD_FINDINGS_V1 payload.
iso_29148(object, required when any assessed standard emitsiso_29148_attributes; otherwise OPTIONAL).average_score(number, required) — Mean of the nine per-attribute scores, rounded to two decimals.weakest_attribute(string, required) — Name of the lowest-scoring attribute. Ties resolved by listed order:necessary,appropriate,unambiguous,complete,singular,feasible,verifiable,correct,conforming.weakest_attribute_score(integer, required, 0–3).
nist_800_160(object, required when any assessed standard emitsnist_800_160_nfr_categories; otherwise OPTIONAL).covered_categories(integer, required, 0–10).missing_categories(array of strings, required) — Names of categories whose presence boolean isfalse. Empty array when all ten categories are covered.
smart(object, required when any assessed standard emitssmart_product_goals; otherwise OPTIONAL).goals_total(integer, required, ≥ 0).goals_passing(integer, required, 0 ≤ value ≤goals_total).pass_rate_pct(number, required, 0.0–100.0) —100 * goals_passing / goals_totalwhengoals_total > 0;100.0otherwise.
fr_ac_coverage(object, required when any assessed standard emitsfr_ac_coverage; otherwise OPTIONAL).Same shape as
PRD_STANDARD_FINDINGS_V1.fr_ac_coverage.threshold_pct(number, required) — Threshold applied for Validate-exit decisioning.
fr_goal_coverage(object, required when the PRD contains functional requirements or product goals; otherwise OPTIONAL).fr_total(integer, required, ≥ 0).fr_with_goal(integer, required, 0 ≤ value ≤fr_total) — Count of functional requirements linked to at least one product goal.goal_total(integer, required, ≥ 0) — Count of product goals detected in the PRD.coverage_pct(number, required, 0.0–100.0) —100 * fr_with_goal / fr_totalwhenfr_total > 0;0.0whenfr_total == 0.target_pct(number, required) — Target coverage percentage, normally100.0.waiver_required(boolean, required) —truewhencoverage_pctis belowtarget_pct.
top_findings (array, required)
Up to ten findings selected for executive surfacing. Selection rule: take all RISK findings first (ordered by severity then by appearance in the underlying payloads), then CAUTION findings, up to ten total.
Each entry:
finding_id(string, required) — Same value as in the sourcePRD_STANDARD_FINDINGS_V1.findings[].finding_id.standard(string, required) — Source reviewer rubric skill name.severity(string, required) —CRITICAL,HIGH,MEDIUM,LOW.N/Ais forbidden intop_findings.status(string, required) —RISKorCAUTION.COVEREDandNOT_APPLICABLEare forbidden intop_findings.location,finding,recommendation— same shape as inPRD_STANDARD_FINDINGS_V1.findings.
recommendations (array, required)
Zero or more prioritized actions the author should take before re-requesting the gate. Each entry consolidates one or more underlying findings into a single coaching item.
id(string, required) — Unique within the payload. Recommended form:REC-<sequence>.priority(string, required) —P0,P1,P2,P3.P0MUST be used when any related finding has severityCRITICAL;P1when any related finding has severityHIGH.target_section(string, required) — PRD section the author should revise.action(string, required) — Concrete revision instruction.related_finding_ids(array of strings, required, length ≥ 1) — Finding IDs fromPRD_STANDARD_FINDINGS_V1.findings[].finding_id.
warnings (array, optional)
Zero or more non-finding warnings the orchestrator or author should consider. Use warnings for calibration caveats, waivable coverage gaps, partial source availability, or drift context that does not belong to a single finding.
id(string, required) — Unique within the payload. Recommended form:WARN-001.severity(string, required) — One ofINFO,WARNING,ADVISORY.message(string, required) — Concise warning text.related_finding_ids(array of strings, optional) — Finding IDs fromPRD_STANDARD_FINDINGS_V1.findings[].finding_id.
notes (string, optional)
Free-form reviewer commentary (for example calibration warnings, missing source caveats, or drift review context).
Validation rules
schema_versionMUST equalPRD_QUALITY_REPORT_V1.overall_statusMUST be consistent with the paired findings payload and threshold rules:FAILifsummary_counts.RISK > 0.FAILif any core ISO 29148 attribute (necessary,unambiguous,singular, orverifiable) scores belowdecision_thresholds.iso_29148_core_min_score.FAILifcategory_summaries.fr_ac_coverage.coverage_pctis belowdecision_thresholds.fr_to_ac_min_pct.NEEDS_REVIEWif no fail condition is present andsummary_counts.CAUTION > 0.NEEDS_REVIEWif no fail condition is present andcategory_summaries.fr_goal_coverage.waiver_requiredistrue.PASSotherwise.
ISO 29148 score
1maps toCAUTIONin general rubric scoring, but any core ISO 29148 attribute below2is blocking through this report's threshold rules.gate_decisions.validate_exitMUST beBLOCKEDwhenoverall_statusisFAIL.gate_decisions.validate_exitMUST beAPPROVED_WITH_COMMENTSwhenoverall_statusisNEEDS_REVIEW.gate_decisions.validate_exitMAY beAPPROVEDonly whenoverall_statusisPASS.gate_decisions.finalize_exitMUST beNOT_EVALUATEDwhenprd.phaseis any ofAssess,Discover,Create,Build,Integrate, orValidate.gate_decisions.finalize_exitMUST beBLOCKEDwhenprd.phaseisFinalize,overall_statusisFAIL, and no approved waiver covers the blocking condition.gate_decisions.finalize_exitMUST beAPPROVED_WITH_COMMENTSwhenprd.phaseisFinalize, no blocking condition remains, and warnings or waivable coverage gaps remain.summary_counts.*MUST equal the corresponding counts in the pairedPRD_STANDARD_FINDINGS_V1payload.severity_breakdown.*MUST equal the count ofRISKandCAUTIONfindings at each severity in the paired findings payload.standards_assessedMUST have exactly one entry when produced byPRD Quality Reviewer.Every
recommendations[].idMUST be unique within the payload.Every
recommendations[].related_finding_ids[]value MUST exist as afindings[].finding_idin the pairedPRD_STANDARD_FINDINGS_V1payload.Every
warnings[].id, when present, MUST be unique within the payload.top_findingsMUST contain onlyRISKandCAUTIONitems; length MUST be ≤ 10.
Example payload
schema_version: PRD_QUALITY_REPORT_V1
report_id: PRD-2026-014-quality-20260612T141055Z
generated_at: "2026-06-12T14:10:55Z"
prd:
id: PRD-2026-014
version: 0.4.0
phase: Validate
artifact_path: docs/prds/2026/prd-checkout-redesign.md
overall_status: FAIL
decision_thresholds:
iso_29148_core_min_score: 2
fr_to_ac_min_pct: 80.0
fr_to_goal_target_pct: 100.0
gate_decisions:
validate_exit: BLOCKED
finalize_exit: NOT_EVALUATED
summary_counts:
RISK: 3
CAUTION: 4
COVERED: 14
NOT_APPLICABLE: 2
severity_breakdown:
CRITICAL: 0
HIGH: 2
MEDIUM: 4
LOW: 1
standards_assessed:
- skill_name: requirements-quality
skill_version: "1.0"
overall_status: RISK
findings_ref: .copilot-tracking/quality/2026-06-12/PRD-2026-014/req-qual-findings.yml
findings_count: 23
category_summaries:
iso_29148:
average_score: 2.44
weakest_attribute: unambiguous
weakest_attribute_score: 1
nist_800_160:
covered_categories: 6
missing_categories:
- scalability_and_elasticity
- maintainability_and_operability
- observability
- compatibility_and_interoperability
smart:
goals_total: 3
goals_passing: 2
pass_rate_pct: 66.67
fr_ac_coverage:
fr_total: 18
fr_with_ac: 15
coverage_pct: 83.33
threshold_pct: 80.0
fr_goal_coverage:
fr_total: 18
fr_with_goal: 16
goal_total: 3
coverage_pct: 88.89
target_pct: 100.0
waiver_required: true
top_findings:
- finding_id: req-qual-001
standard: requirements-quality
severity: HIGH
status: RISK
location:
section: "6. Functional Requirements"
line_range: L142-L148
finding: FR-001 uses the unqualified term "fast" without a measurable threshold.
recommendation: Restate FR-001 with a quantitative latency target (for example "render the cart within 1 second of update").
- finding_id: req-qual-002
standard: requirements-quality
severity: HIGH
status: RISK
location:
section: "1. Executive Summary"
line_range: L48-L52
finding: Product goal GOAL-001 has no measurable success metric and fails SMART Measurable.
recommendation: Add a numeric KPI to GOAL-001 (for example "increase checkout completion rate by 8%").
- finding_id: req-qual-003
standard: requirements-quality
severity: MEDIUM
status: CAUTION
location:
section: "7. Non-Functional Requirements"
finding: The Observability category contains no NFR naming required logs, metrics, traces, or alerting thresholds.
recommendation: Add an NFR defining checkout funnel instrumentation and alert thresholds.
recommendations:
- id: REC-1
priority: P1
target_section: "6. Functional Requirements"
action: Quantify every NFR-style adverb (fast, often, large) currently embedded in FR statements; move performance constraints to the NFR section with measurable thresholds.
related_finding_ids:
- req-qual-001
- id: REC-2
priority: P1
target_section: "1. Executive Summary"
action: Add SMART-compliant KPIs to GOAL-001 and re-confirm GOAL-002 timeline anchors.
related_finding_ids:
- req-qual-002
- id: REC-3
priority: P2
target_section: "7. Non-Functional Requirements"
action: Add NFRs covering observability, scalability, maintainability, and interoperability before Finalize.
related_finding_ids:
- req-qual-003
warnings:
- id: WARN-001
severity: WARNING
message: FR-to-product-goal coverage is below the 100% Finalize target and requires an approved waiver before signoff.
related_finding_ids:
- req-qual-002
notes: Scalability, maintainability, observability, and interoperability NFR categories are absent; flagged for stakeholder discussion before Finalize (no automatic block).License
This reference file is original Microsoft content licensed under CC BY 4.0. The schema definition and validation rules are HVE-Core IP and may be reused under the same license.
Requirements and compatibility
Written for: GitHub Copilot, Claude Code
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Needs: Claude Code frontmatter
Security
No issues found by our static scan· No issues found
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Published by
- Microsoft
- Publisher
- Microsoft (Official)
- Source
- microsoft/hve-core · .github/skills/project-planning/requirements-author · commit f425e94
- Licence
- Creative Commons Attribution 4.0 International (redistribution allowed)
- LICENSE (written by AutoGineer)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Microsoft or Microsoft.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download requirements-author.zip