Agent skill

system-dev

Guides AI-assisted systems design using INCOSE principles. Creates and manages a Design Registry with typed slots for components, interfaces, contracts, and requirement references. Use when the user mentions system design, design registry, component decomposition, interface resolution, behavioral contracts, traceability, impact analysis, or /system-dev commands.

View SKILL.md on GitHub Repository
Stars 6
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/ddunnock/claude-plugins/tree/main/skills/system-dev

SKILL.md

System Design (AI-Assisted)

Manage a Design Registry of typed, versioned slots (components, interfaces, contracts, requirement-refs) with schema validation, change journaling, and traceability to upstream requirements.

Overview

The system-dev skill provides a structured workflow for AI-assisted systems design:

  1. Initialize a .system-dev/ workspace with /system-dev:init
  2. Create design elements (components, interfaces, contracts, requirement-refs) as typed slots
  3. Validate every write against JSON Schema (Draft 2020-12)
  4. Version each slot with monotonic integers and optimistic locking
  5. Journal all changes in an append-only JSONL log with RFC 6902 diffs
  6. Query slots by type, field filters, and version history
  7. Trace design decisions back to upstream requirements

Commands

Command Description Details
/system-dev:init Create .system-dev/ workspace commands/init.md
/system-dev:status Show registry summary commands/status.md
/system-dev:create Create a new design slot commands/create.md
/system-dev:read Read a slot by ID commands/read.md
/system-dev:update Update an existing slot commands/update.md
/system-dev:query List slots with filters commands/query.md
/system-dev:history Show slot version history commands/history.md
/system-dev:view Assemble a contextual view commands/view.md
/system-dev:diagram Generate D2/Mermaid diagrams commands/diagram.md

Slot Types

Type ID Prefix Purpose
component comp- System/subsystem building blocks
interface intf- Connections between components
contract cntr- Behavioral obligations on interfaces
requirement-ref rref- References to upstream requirements
diagram diag- Generated D2/Mermaid diagram source from view data

For field details, see references/slot-types.md.

Design Registry Structure

.system-dev/
  registry/
    components/       # One JSON file per component slot
    interfaces/       # One JSON file per interface slot
    contracts/        # One JSON file per contract slot
    requirement-refs/ # One JSON file per requirement-ref slot
    diagrams/         # One JSON file per diagram slot
  journal.jsonl       # Append-only change journal
  index.json          # Slot index (ID -> path, type, version)
  config.json         # Workspace configuration
  view-specs/         # Declarative view specification configs

Key Behaviors

  • Explicit init required: Run /system-dev:init before any other command. No auto-init.
  • Schema validation on every write: All creates and updates validated against JSON Schema.
  • Monotonic versioning: Each slot tracks an integer version (v1, v2, v3...) for optimistic locking.
  • Atomic writes: Write-to-temp + rename ensures no partial writes on crash.
  • Append-only journal: Every mutation recorded with timestamp, agent, diff, and summary.

Progressive Disclosure

  • Command workflows: See commands/ for detailed step-by-step workflows
  • Slot type reference: See references/slot-types.md for field specifications
  • Agent definitions: See agents/ for agent configurations (added in later phases)
  • Schema files: See schemas/ for JSON Schema definitions

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

ddunnock/claude-plugins

streaming-output

Stream long-form content to markdown files with resume capability. Writes content incrementally with section markers, enabling recovery if context limits are hit. Use when generating long documents (over 1000 lines), B-SPEC or specification writing, multi-section reports, any task where context compaction may occur mid-generation, or when user explicitly requests streaming output. Commands: init, write, status, resume, finalize, repair.

6 0
Explore
ddunnock/claude-plugins

fishbone-diagram

Create comprehensive Fishbone (Ishikawa/Cause-and-Effect) diagrams for structured root cause brainstorming. Guides teams through problem definition, category selection (6Ms, 8Ps, 4Ss, or custom), cause identification, sub-cause drilling, prioritization via multi-voting, and 5 Whys integration. Generates visual SVG diagrams and professional HTML reports. Use when brainstorming potential causes, conducting root cause analysis, facilitating quality improvement sessions, analyzing defects or failures, structuring team problem-solving, or when user mentions "fishbone", "Ishikawa", "cause and effect diagram", "6Ms", "cause analysis", or "brainstorming causes".

6 0
Explore
ddunnock/claude-plugins

streaming-output-mcp

Stream structured content to persistent SQLite storage with automatic session break recovery. Core principle: The content IS the state. Every stream_write is automatically persistent. Supports multi-format export (Markdown, HTML, JSON, YAML, CSV, Text) and 7 document templates. Commands: /stream-init, /stream-status, /stream-read, /stream-write, /stream-export. ALWAYS call stream_status after session breaks to check for resume_from and preserved_context.

6 0
Explore
ddunnock/claude-plugins

fmea-analysis

Conduct Failure Mode and Effects Analysis (FMEA) for systematic identification and risk assessment of potential failures in designs, processes, or systems. Supports DFMEA (Design), PFMEA (Process), and FMEA-MSR (Monitoring & System Response). Uses AIAG-VDA 7-step methodology with Action Priority (AP) risk assessment replacing traditional RPN. Use when analyzing product designs for potential failures, evaluating manufacturing process risks, conducting proactive risk assessment, preparing for APQP/PPAP submissions, investigating field failures, or when user mentions "FMEA", "failure mode", "DFMEA", "PFMEA", "severity occurrence detection", "RPN", "Action Priority", "design risk analysis", or needs to identify and prioritize potential failure modes with their causes and effects.

6 0
Explore
ddunnock/claude-plugins

problem-definition

Guide RCCA/8D problem definition using 5W2H and IS/IS NOT analysis. Transforms scattered failure data into precise, measurable problem statements that bound investigation scope without embedding cause or solution. Use when defining problems for root cause analysis, writing D2 sections of 8D reports, analyzing nonconformances, investigating failures, or when user mentions problem definition, problem statement, RCCA, 8D, failure analysis, or corrective action.

6 0
Explore
ddunnock/claude-plugins

kepner-tregoe-analysis

Conduct Kepner-Tregoe (KT) Problem Solving and Decision Making (PSDM) analysis using the four rational processes - Situation Appraisal, Problem Analysis, Decision Analysis, and Potential Problem Analysis. Use when performing structured root cause analysis, making complex decisions, evaluating alternatives with weighted criteria, conducting IS/IS NOT specification analysis, anticipating implementation risks, troubleshooting complex issues, or when user mentions "Kepner-Tregoe", "KT method", "IS/IS NOT", "situation appraisal", "decision analysis", "MUSTS and WANTS", "potential problem analysis", or needs systematic problem-solving methodology. Includes specification matrices, decision scoring, quality rubrics, and professional report generation.

6 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results