plugins/cache/nyldn-plugins/octo/9.30.0/skills/octopus-architecture/SKILL.md
System architecture and API design with multi-AI consensus
npx skillsauth add moliboy5000/.claude octopus-architectureInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill uses ENFORCED execution mode. You MUST follow this exact sequence.
MANDATORY: Run the centralized provider check BEFORE displaying the banner:
bash "${HOME}/.claude-octopus/plugin/scripts/helpers/check-providers.sh"
Use the ACTUAL results. PROHIBITED: Showing only "🔵 Claude: Available ✓" without listing all providers.
Display this banner BEFORE orchestrate.sh execution (list ALL providers from check output):
🐙 **CLAUDE OCTOPUS ACTIVATED** - Architecture design mode
🏗️ Architecture: [Brief description of system to design]
Provider Availability:
🔴 Codex CLI: [status from check] - Backend architecture patterns
🟡 Gemini CLI: [status from check] - Alternative approaches
🟢 Copilot CLI: [status from check] - GitHub integration
🟣 Qwen CLI: [status from check] - Additional perspective
🟤 OpenCode CLI: [status from check] - Multi-provider routing
🔵 Claude: Available ✓ - Synthesis and recommendations
💰 Estimated Cost: $0.02-0.08
⏱️ Estimated Time: 3-7 minutes
Validation:
/octo:setupDO NOT PROCEED TO STEP 2 until banner displayed.
You MUST execute this command via the Bash tool:
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh spawn backend-architect "<user's architecture request>"
CRITICAL: You are PROHIBITED from:
This is NOT optional. You MUST use the Bash tool to invoke orchestrate.sh.
After orchestrate.sh completes, verify it succeeded:
# Check for persona output (varies by persona type)
# For spawn commands, check exit code and output
if [ $? -ne 0 ]; then
echo "❌ VALIDATION FAILED: orchestrate.sh spawn failed"
exit 1
fi
echo "✅ VALIDATION PASSED: Architecture design completed"
If validation fails:
~/.claude-octopus/logs/Present the architecture design from the persona execution.
Include attribution:
---
*Multi-AI Architecture Design powered by Claude Octopus*
*Providers: 🔴 Codex | 🟡 Gemini | 🔵 Claude*
Invokes the backend-architect persona for system design during the grasp (define) and tangle (develop) phases.
# Via orchestrate.sh
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh spawn backend-architect "Design a scalable notification system"
# Via auto-routing (detects architecture intent)
${HOME}/.claude-octopus/plugin/scripts/orchestrate.sh auto "architect the event-driven messaging system"
This skill wraps the backend-architect persona defined in:
agents/personas/backend-architect.mdcodexgpt-5.3-codexgrasp, tangleapi-design, microservices, distributed-systems"Design the API contract for the user service"
"Plan the event sourcing architecture"
"Design the caching strategy for the product catalog"
"Create a microservices decomposition plan"
For enhanced structural awareness during architecture design, leverage Claude Code's LSP tools:
Before defining architecture, gather structural context:
lsp_document_symbols - Understand existing module structure
lsp_find_references - Identify current dependencies
lsp_workspace_symbols - Find related patterns across codebase
During design validation:
lsp_goto_definition - Verify interface contracts
lsp_hover - Check type signatures
lsp_diagnostics - Identify type/interface mismatches
// Step 1: Understand existing structure
const symbols = await lsp_document_symbols("src/services/user.ts")
const references = await lsp_find_references("UserService", line=5, char=10)
// Step 2: Identify patterns in codebase
const patterns = await lsp_workspace_symbols("Service")
// Step 3: Design new architecture informed by existing patterns
// ... architecture design ...
// Step 4: Validate design with diagnostics
const issues = await lsp_diagnostics("src/services/*.ts")
This ensures architecture recommendations align with existing codebase patterns and type contracts.
tools
MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the user asks to create, generate, draw, render, sketch, or build a diagram — flowchart, architecture diagram, sequence diagram, ERD or entity-relationship diagram, state diagram or state machine, gantt chart, or timeline. Also trigger when the user mentions Mermaid syntax or wants a system architecture, decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline visualized in FigJam. Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely (mindmaps, pie charts, class diagrams, etc.).
development
DEFAULT PIPELINE for all tasks requiring execution. You (Claude) are the strategic orchestrator. Codex agents are your implementation army - hyper-focused coding specialists. Trigger on ANY task involving code, file modifications, codebase research, multi-step work, or implementation. This is NOT optional - Codex agents are the default for all execution work. Only skip if the user explicitly asks you to do something yourself.
development
This skill should be used when the user asks to analyze a UI screen recording and map interaction states into Figma. Trigger for requests such as "put video frames in Figma", "extract states from my recording", "map interactions from video to Figma", "analyze this screen recording", "create a storyboard from my video", "deconstruct this interaction in Figma", "annotate the UI states in my recording", or "pull the key moments from this video into Figma". Also trigger when the user references a video file (.mp4, .mov, .webm, .avi) together with Figma, design review, interaction analysis, prototypes, or UI states. The skill extracts key visual moments from a video, infers interaction triggers, and builds an annotated Figma Design storyboard using native Figma annotations and uploaded screenshot assets.
development
Generate a FigJam project plan board from a PRD plus codebase context. Interactive flow: research → propose sections → per-section deep research → per-section content + block-shape proposal → create FigJam → skeleton → fill → diagrams → wrap. Each content block (section, nested section, intro callout, table, multi-column text, sticky column, diagram section, metadata strip) has its own subskill reference file. Use when the user asks for 'project plan in FigJam', 'interactive project plan', '/generate-project-plan', or provides a PRD and wants per-section confirmation on content + rendering.