specforge

Execute an approved change request. Creates Phase 2 deltas for approved specs, updates draft specs directly, creates new stories, and updates sprint/release plans. Only works on Approved CRs.

Run a structured backlog refinement session for an epic. Reads the epic and its source specs, guides story decomposition, identifies spec gaps, and records the session.

Create a new change request to formally log a requirement change. Auto-numbers the CR, pre-fills metadata, and guides the user through initial impact assessment.

Scan all specification and delivery artifacts for cross-reference integrity. Reports orphan specs, broken references, coverage gaps, and unresolved TBDs.

Run blast-radius analysis on a change request. Traces all direct and cascade impacts across spec and delivery layers. Produces a scored impact report with risk rating and recommendations.

Create a structured meeting note with user requirement extraction. Captures agenda, decisions, action items, and extracts URs into a structured table.

Generate an epic from one or more use cases. Reads the use case spec, auto-fills Spec Traceability, Business Value, and suggests a User Stories breakdown.

Create a release plan from a set of epics. Aggregates epic scope, calculates timeline based on team capacity, and identifies scope conflicts.

Create a new specification document from template. Supports all spec types: srs_overview, object, usecase, screen, businessrule, interface, decision_table, actor, workflow, state_transition, permission_matrix, nfr, architecture, component, data_architecture, security, infrastructure, adr.

Create a sprint plan from ready stories. Populates backlog, calculates capacity summary, and sets up ceremony schedule.

Create a user story with spec traceability pre-filled from its parent epic. Derives acceptance criteria from linked use case steps and business rules.

Create a Phase 2+ delta document for an existing baseline spec. Delta documents describe only changes — additions, modifications, and removals — not full rewrites.

Review a specification document for quality against IEEE 830 / ISO 29148 standards. Delegates to the spec-reviewer agent and returns a scored report.

Performs autonomous impact analysis for a change request. Reads the CR, traces all direct and cascade impacts across both spec and delivery layers, and produces a scored impact report with risk rating and recommendations. Use when a change request needs thorough blast-radius analysis before approval. <example>Analyze impact of CR-0001</example> <example>Run blast-radius analysis for CR-0003_AddPaymentMethod</example>

Decomposes a use case into a complete epic with user stories. Reads the UC spec, analyzes activity flows and exceptions, and generates an epic file plus individual story files with spec traceability and acceptance criteria. Use when you need to convert a specification into sprint-ready delivery artifacts. <example>Decompose UC0002 into an epic and stories</example> <example>Break down UC0005_ManageInventory into sprint-ready stories</example>

Reviews a specification document for quality against IEEE 830, ISO 29148, and BABOK standards. Checks completeness, clarity, testability, traceability, and adherence to SpecForge template structure. Use when a spec is ready for review before approval. <example>Review UC0001_CreateOrder.md for approval readiness</example> <example>Review O03_Product.md and score it</example>

Builds or validates the full Requirements Traceability Matrix (RTM) across the repository. Scans all spec and delivery files, maps cross-references, computes coverage metrics, and identifies gaps. Use when you need a comprehensive traceability report or want to generate/update the RTM document. <example>Build the RTM for this project</example> <example>Check traceability coverage for UC0003</example>

Invoke for any agile delivery task: break a use case (UC) into an epic and user stories, estimate story points for a feature, calculate sprint capacity from team size and availability, adjust a sprint plan when velocity drops, or lay out a release timeline across sprints. Handles the full spec-to-backlog pipeline — mapping UC steps to stories, sizing work items, planning iterations, and running backlog refinement. Trigger on: 'convert to work items', 'break into stories', 'how many points', 'sprint capacity', 'velocity', 'release plan', 'size this', 'make this sprint-ready', 'prioritize the backlog', PTO/availability planning, or any question about fitting features into sprints. Provides two-layer architecture rules, decomposition heuristics, step-to-story mapping, INVEST criteria, story sizing guide, and Given/When/Then acceptance criteria derivation.

Spec out software requirements. Use whenever the user wants to define, document, or design any part of a software system: data models and objects ('define the Item object'), screen layouts and UI specs ('write a screen spec for the dashboard'), use cases and workflows ('how does the user create an order?'), state transitions and lifecycles ('Invoice: Draft → Sent → Paid'), decision tables, business rules, permission matrices ('who can approve purchase orders?'), actor definitions, interface contracts, NFRs, meeting notes with requirement extraction, change requests, impact analyses, phase deltas, SRS overviews, and delivery artifacts like epics, user stories, sprints, release plans, and backlog refinements. Also trigger when the user asks 'what template should I use', wants to modify an approved spec (Phase 2 delta pattern), or is describing system structure, behavior, rules, or requirements and wants a structured document. Provides template selection, auto-numbering, naming conventions, IEEE 830/ISO 29148 quality guidance, dynamic domain discovery, conflict detection, cross-reference validation, and spec lifecycle management.

Trigger whenever the user asks to check, validate, or audit connections between requirements artifacts. This includes: cross-reference checking between screens, specs, and use cases; building traceability matrices; finding orphaned or unlinked specs, stories, or epics; generating coverage reports; or asking questions like 'what's missing', 'what's not covered', 'is everything linked', 'are requirements covered', 'find gaps', 'check my cross-references', or 'what specs don't have stories yet'. Use for any verification of existing spec-to-delivery linkage — not for creating or writing new specs, stories, or use cases. Also use before sprint starts to verify story-to-spec traceability, or after creating new specs to check they're properly linked. Provides forward/backward traceability rules, cross-reference validation, coverage metrics, orphan detection, broken reference scanning, and structured reporting.

1 hook across 1 event