Skip to main content

Utility skills reference

Utility skills provide supporting capabilities for requirements changes, security auditing, traceability verification, and project observability.

req-change

Manages requirements changes with full pipeline cascade.

Invocation

/sdd:req-change                                       # Interactive mode
/sdd:req-change --file changes/CHANGE-REQUEST.md      # From structured file
/sdd:req-change --dry-run                             # Plan only, no execution
/sdd:req-change --cascade=auto                        # Full pipeline cascade
/sdd:req-change --cascade=plan-only                   # Cascade through planning
/sdd:req-change --maintenance=corrective              # Pre-classify by type

Change types

ADD
change
New capability, feature, or constraintExample: “Necesitamos soporte para bulk export de CVs”
MODIFY
change
Change to existing requirement behavior, threshold, or scopeExample: “El timeout de extraccion debe ser 480s en vez de 360s”
DEPRECATE
change
Remove or sunset existing requirementExample: “Ya no necesitamos el matching por percentil”

Maintenance categories (ISO 14764)

Corrective
category
Bug fix, incorrect behaviorUrgency levels: P0 (Critical), P1 (High), P2 (Medium), P3 (Low)
Adaptive
category
External API change, dependency update, platform migration
Perfective
category
Feature enhancement, new capability
Preventive
category
Tech debt reduction, code health improvement

Execution phases

Phase 0
phase
Inventory & context loadingGlobs spec files, reads REQUIREMENTS.md, glossary, CLARIFICATIONS.md, AUDIT-BASELINE.md, pipeline-state.json. Builds traceability index.
Phase 1
phase
Change request intake & classificationParses input, classifies by type (ADD/MODIFY/DEPRECATE), maintenance category (ISO 14764), urgency (for corrective). Applies SWEBOK 5-Whys for unclear requests.
Phase 2
phase
Impact analysisIdentifies direct impact (MUST change) and indirect impact (SHOULD review). Traces full chain per affected REQ. Detects conflicts (contradicts INVs, ADRs, BDD, RNs). Rates complexity (Low/Medium/High/Very High). Analyzes commit impact via git (if available). Enriches with SDD MCP server data (if available).
Phase 3
phase
Clarification & decisionEvaluates against 7 SWEBOK properties (Unambiguous, Testable, Binding, Atomic, True, Stakeholder vocabulary, Acceptable). Presents questions with options and recommendations. Collects answers. Generates clarification log.
Phase 4
phase
Change plan generationFor ADD: generates new REQ with full template, drafts new UC/API/BDD/INV/ADR/RN. For MODIFY: shows before/after of every affected section. For DEPRECATE: marks REQ as Deprecated, generates migration/sunset plan. Applies Atomic Cross-Check Rule. Groups changes by document.
Phase 5
phase
User review & approvalBatch mode (default with --batch): apply all. Interactive mode: approve/modify/reject per CR.
Phase 6
phase
Change executionApplies changes in order: REQUIREMENTS.md first (source of change), then domain/, invariants, use-cases, workflows, contracts, tests, nfr, adr, runbooks, CLARIFICATIONS.md, CHANGELOG.md. Creates git commits.
Phase 7
phase
Alignment auditFocused mini-audit on affected documents: REQ → Spec Forward Coverage, Spec → REQ Backward Coverage, Traceability Complete, Cross-Refs Valid, Glossary Compliance, Contradiction Check, EARS Compliance, Testability. Auto-fixes if possible.
Phase 8
phase
Change report generationGenerates comprehensive report with: executive summary, changes applied (new/modified/deprecated), new artifacts created, impact analysis, alignment audit results, clarification decisions, context for planning/implementation, recommended next steps.
Phase 9
phase
Pipeline cascade executionComputes invalidation scope (which stages need re-run). Updates pipeline-state.json (marks stale). Executes based on cascade mode (manual/dry-run/plan-only/auto). Generates cascade report (if auto/plan-only).

Cascade modes

--cascade=manual
mode
default:true
Update pipeline-state.json, print recommended commands
--cascade=auto
mode
Invoke downstream skills in sequence: spec-auditor (focused), test-planner, plan-architect (regenerate FASEs), task-generator (incremental), task-implementer (new tasks only)
--cascade=dry-run
mode
Compute scope, no changes to pipeline-state.json
--cascade=plan-only
mode
Cascade through planning but not implementation

Output artifacts

changes/CHANGE-PLAN-{id}.md
file
Detailed change plan with before/after for every affected document
changes/CHANGE-REPORT-{id}.md
file
Comprehensive change report with full context for downstream skills
changes/CASCADE-REPORT-{id}.md
file
(if cascade=auto/plan-only) Execution log of cascaded skill invocations
requirements/REQUIREMENTS.md
file
Updated with new/modified/deprecated requirements
spec/
directory
Updated specifications reflecting requirement changes

security-auditor

Audits specifications for security defects.

Invocation

/sdd:security-auditor                                 # Full security audit
/sdd:security-auditor --scope=auth,payment            # Scope to modules

Security defect categories

Detects security-specific defects beyond general spec-auditor categories.

Output artifacts

audits/SECURITY-AUDIT-BASELINE.md
file
Security-specific audit report

traceability-check

Verifies traceability chain integrity.

Invocation

/sdd:traceability-check                               # Full verification
/sdd:traceability-check --from=REQ-EXT-001            # Start from specific artifact

Checks

Forward coverage
check
Every REQ has at least one spec implementing it
Backward coverage
check
Every spec traces back to at least one REQ
Chain completeness
check
REQ → UC → WF → API → BDD → INV → ADR links all valid
Orphan detection
check
No artifacts without traceability

Output artifacts

audits/TRACEABILITY-REPORT.md
file
Traceability verification report with gaps and broken links

pipeline-status

Displays current pipeline state and stage status.

Invocation

/sdd:pipeline-status                                  # Full status
/sdd:pipeline-status --verbose                        # Detailed output

Output

Reads pipeline-state.json and displays:
  • Stage statuses (done/pending/stale)
  • Last run timestamps
  • Stale reasons
  • Next recommended action

session-summary

Generates session activity report.

Invocation

/sdd:session-summary                                  # Generate summary of current session

Output artifacts

session/SESSION-{timestamp}.md
file
Session activity reportSections:
  • Skills invoked
  • Artifacts created/modified
  • Decisions made
  • Pipeline state changes
  • Time spent per phase

setup

Initializes SDD directory structure.

Invocation

/sdd:setup                                            # Initialize directories
/sdd:setup --template=minimal                         # Minimal structure
/sdd:setup --template=full                            # Full structure with examples

Created directories

requirements/
directory
Requirements documents
spec/
directory
Technical specifications with subdirectories: domain/, use-cases/, workflows/, contracts/, tests/, nfr/, adr/, runbooks/
plan/
directory
Implementation plans and FASE files
task/
directory
Task documents
audits/
directory
Audit reports and baselines
changes/
directory
Change requests and reports

Output artifacts

pipeline-state.json
file
Initialized pipeline state with all stages pending
CLAUDE.md
file
(if not exists) Project context template

sync-notion

Bidirectional synchronization with Notion databases.

Invocation

/sdd:sync-notion                                      # Interactive setup
/sdd:sync-notion --pull                               # Pull from Notion
/sdd:sync-notion --push                               # Push to Notion
/sdd:sync-notion --sync                               # Bidirectional sync

Configuration

Requires sync-notion/config.json:
{
  "notionToken": "secret_...",
  "databaseId": "...",
  "mapping": {
    "requirements": "Requirements Database",
    "tasks": "Tasks Database"
  }
}

Sync protocol

--pull
mode
Fetches from Notion, updates local SDD artifacts, marks conflicts
--push
mode
Sends local changes to Notion, creates/updates pages and database rows
--sync
mode
Bidirectional: pulls first, resolves conflicts, then pushes

Output artifacts

sync-notion/SYNC-REPORT-{timestamp}.md
file
Sync activity reportSections:
  • Items pulled from Notion
  • Items pushed to Notion
  • Conflicts detected and resolution
  • Sync statistics

code-index

Builds symbol-level code intelligence graph.

Invocation

/sdd:code-index                                       # Full indexing
/sdd:code-index --scope=src/api                       # Scope to paths
/sdd:code-index --incremental                         # Update only changed files

Indexed data

Symbols
data
Functions, classes, interfaces, types with signatures and locations
Call graph
data
Caller-callee relationships
Import graph
data
Module dependencies
Refs annotations
data
Code → spec traceability via Refs: comments

Output artifacts

.sdd/code-index.json
file
Symbol table and call graph in MCP-compatible format

MCP integration

Enables sdd_context, sdd_impact, and sdd_search MCP tools for:
  • reconcile — enriched impact analysis
  • req-change — commit impact analysis
  • reverse-engineer — code analysis

dashboard

Generates HTML visualization of project state.

Invocation

/sdd:dashboard                                        # Generate dashboard
/sdd:dashboard --serve                                # Generate and serve locally

Visualizations

Pipeline status
view
Stage status, progress bar, next action
Traceability graph
view
Interactive graph: REQ → UC → WF → API → BDD → INV
Health metrics
view
Coverage percentages, defect counts, test coverage
Findings summary
view
Dead code, tech debt, audit findings
Recent activity
view
Timeline of skill invocations and artifact changes

Output artifacts

dashboard/index.html
file
Interactive HTML dashboard with embedded data
dashboard/assets/
directory
CSS, JavaScript, and visualization libraries

Build docs developers (and LLMs) love