Claude Skills by rogue-dev-studio

Canonical multi-agent orchestration: decompose work, dependency graphs, parallel tracks, handoffs, and merge. Absorbs Claude Flow / Ruflo / Loki / Ralph / Paperclip / OpenFang patterns into one portable playbook.

Canonical quality engineering: test strategy, case generation, coverage gates, exploratory checks, and security-tinged QA (incl. Shannon-style pentest track when requested).

Canonical playbook for AI coding assistants and CLI pair-programmers (Claude Code, Kilo, Goose, OpenCode, multi-CLI toolkits). Use when choosing or operating an assistant workflow inside the project.

Generative algorithmic art. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `algorithmic-art` work when listed in TEAM.yaml or explicitly requested.

Expert API design and delivery: resource modeling, versioning, consistent error envelopes, pagination/filtering, idempotency, OpenAPI/contracts, and boundary validation. Use when defining or changing REST (or HTTP) APIs, DTO/request-response shapes, client integration contracts, or when reviewing endpoint consistency before frontend or third-party consumers bind to them.

Expert authentication and authorization engineering: identity lifecycle, session/token handling, password/OTP flows, RBAC/ABAC permission models, default-deny enforcement at every sensitive boundary, and safe audit logging. Use when implementing login/logout, role-permission matrices, policy gates, scoped multi-tenant access, or reviewing authn/authz for APIs and UI routes.

Expert backend application engineering: layered architecture, domain services, validation, transactions, caching boundaries, background jobs, and framework idioms (e.g. Laravel/Node) without leaking business rules into controllers. Use when implementing or refactoring server-side features, services, form requests/DTOs, policies, queues, or integrating persistence with APIs.

Prefer this for any 3D modeling, mesh, scene, render, or Blender request (e.g. "buat model 3D ikan", character, prop). Drive Blender via BlenderMCP (addon :9876 + blender-mcp). Do not offer script-only / trimesh menus first when Blender MCP can be used. Wire mcp/blender if missing.

Canonical browser automation and web UI verification: Playwright, agent browser CLIs, and CDP-based tooling in one playbook.

Design system framework. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `canvas-design` work when listed in TEAM.yaml or explicitly requested.

Canonical spec and requirements skill: 5-phase clarity workflow plus Spec-Kit / markdown-agent spec patterns. Use for PRD, SRS, AC, and implementable specifications before coding.

Video clipper and repurposing ops for creator-approved promotion: consent intake, highlight selection, short-form cuts, captions/branding, attribution, and platform-safe publish handoff. Use when a creator wants clippers to promote their content via clips, Shorts, Reels, or compilations.

AWS, Azure, GCP CLIs. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `cloud-tools` work when listed in TEAM.yaml or explicitly requested.

Expert code review against architecture and coding standards: readability, maintainability, security, performance, layering, Sonar-equivalent cleanliness, comment and formatting discipline, modal safety, and a strict ban on raw SQL or database queries outside the persistence layer. Author/date file headers are identity metadata only and are out of review scope. Use when reviewing pull requests, developer diffs, or E2E Review phase outputs; produces approve/reject with actionable findings for ...

ComfyUI image generation MCP server (GPU required). Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `comfyui` work when listed in TEAM.yaml or explicitly requested.

Persistent memory layer for Claude Code's /compact command. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `compahook` work when listed in TEAM.yaml or explicitly requested.

Canonical container workflows: Docker/Compose development plus MCP-style container management patterns.

Autonomous timed development shift: agents pick backlog work, run maintenance, impact analysis, QA, UI/UX, performance review, and code review in a loop until duration ends. Use for dev shift, maintenance aplikasi, application audit, or autonomous sprint. Trigger: /dev-shift or natural language prompt.

Expert database engineering for application data layers: schema and ERD design, relational modeling, indexing, query performance gates, views, triggers, functions, mapping/junction tables, versioned migrations, seeders, and PostgreSQL/MySQL operational practice. Use for Database Engineer delivery, migration work, integrity constraints, and measurable read/write performance.

.NET development environment. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `dotnet` work when listed in TEAM.yaml or explicitly requested.

Instance agent for mimir fleet management. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `draupnir` work when listed in TEAM.yaml or explicitly requested.

End-to-end software house delivery. Use whenever the user asks to build a feature, fix a non-trivial bug, start a project, or run the full workflow. Orchestrates all roles and executes through Release unless blocked. Skip when WORKMODE is manual unless user/command forces E2E.

General engineering technical interviews: backend, frontend, fullstack, mobile, DevOps tracks — live coding, debugging, system design light, take-home briefs, rubrics, and candidate practice. Not HR-specific; use for technical interview, technical test, mock interview, live coding, system design interview, persiapan tes teknis, simulasi interview engineer, take-home review rubric.

FFmpeg media processing. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `ffmpeg-processing` work when listed in TEAM.yaml or explicitly requested.

Expert frontend application engineering: accessible UI structure, state and data-fetching discipline, form/validation UX, responsive layouts, performance budgets, and integration with API contracts. Use when building or refining SPA/web screens, design-system consumption, client-side routing, or fixing UI reliability (loading, empty, and error states).

GitHub CLI authentication and workflow configuration. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `github-cli` work when listed in TEAM.yaml or explicitly requested.

GitLab CLI for merge requests, issues, pipelines, and CI/CD. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `glab` work when listed in TEAM.yaml or explicitly requested.

Go development environment. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `golang` work when listed in TEAM.yaml or explicitly requested.

Haskell with GHC, Cabal, Stack, and HLS. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `haskell` work when listed in TEAM.yaml or explicitly requested.

Adobe Illustrator via MCP (npx illustrator-mcp-server). Use when the user needs vector art, artboards, exports, or Illustrator automation from the agent. Requires mcp/illustrator wired and Illustrator desktop installed/running.

ImageMagick processing MCP server. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `imagemagick` work when listed in TEAM.yaml or explicitly requested.

Document to ontology import. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `import-to-ontology` work when listed in TEAM.yaml or explicitly requested.

Infrastructure and DevOps tooling (Terraform, K8s, Config Mgmt). Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `infra-tools` work when listed in TEAM.yaml or explicitly requested.

Jupyter notebook execution MCP server. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `jupyter-notebooks` work when listed in TEAM.yaml or explicitly requested.

JVM languages (Java, Kotlin, Scala). Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `jvm` work when listed in TEAM.yaml or explicitly requested.

KiCad PCB design MCP server. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `kicad` work when listed in TEAM.yaml or explicitly requested.

Canonical LLM gateway/routing/proxy playbook: multi-provider failover, token reduction proxies, and cost wrappers.

Canonical MCP server integration playbook: allowlist, Cursor mcp.json merge, smoke tests, and scaffolding. Use with ai-agents-rogue/mcp packages.

Global mise configuration and settings. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `mise-config` work when listed in TEAM.yaml or explicitly requested.

Claude monitoring and usage tracking tools (UV, claude-monitor, claude-usage-cli). Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `monitoring` work when listed in TEAM.yaml or explicitly requested.

NGSpice circuit simulation MCP server. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `ngspice` work when listed in TEAM.yaml or explicitly requested.

TypeScript, ESLint, Prettier. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `nodejs-devtools` work when listed in TEAM.yaml or explicitly requested.

Node.js development environment. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `nodejs` work when listed in TEAM.yaml or explicitly requested.

Expert application observability: structured logging, correlation IDs, health checks, metrics/SLIs, error tracking, and safe diagnostics without leaking secrets or excess PII. Use when adding logging/monitoring for services, diagnosing production-like failures, defining health/readiness endpoints, or improving operational visibility in Phase 2+ quality work.

Canonical office/document generation and transformation: Word, PDF, PowerPoint, Excel, and LaTeX.

AI-powered ontology enrichment. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `ontology-enrich` work when listed in TEAM.yaml or explicitly requested.

OpenClaw - Multi-channel AI gateway for messaging platforms with browser Control UI. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `openclaw` work when listed in TEAM.yaml or explicitly requested.

PBR material generation MCP server (GPU required). Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `pbr-rendering` work when listed in TEAM.yaml or explicitly requested.

Adobe Photoshop via MCP (uvx photoshop-mcp-server). Use when the user needs PSD edits, layers, exports, or Photoshop automation from the agent. Requires mcp/photoshop wired and Photoshop desktop installed/running.

PHP development environment. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `php` work when listed in TEAM.yaml or explicitly requested.