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.
EnglishCanonical quality engineering: test strategy, case generation, coverage gates, exploratory checks, and security-tinged QA (incl. Shannon-style pentest track when requested).
EnglishCanonical 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.
EnglishDomain specialist for API design, development, and best practices. Scope: RESTful API design, GraphQL, API documentation, authentication, authorization, rate limiting, CORS, error handling, pagination, filtering, HATEOAS, API testing, API security. Excludes: database design, business logic, infrastructure, frontend, security beyond API. Triggers: "API", "REST", "GraphQL", "endpoint", "OpenAPI", "Swagger", "CORS".
EnglishAWS, 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.
EnglishPersistent 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.
EnglishCanonical container workflows: Docker/Compose development plus MCP-style container management patterns.
EnglishInstance 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.
EnglishEnd-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.
EnglishFFmpeg 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.
EnglishHaskell 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.
EnglishDocument 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.
EnglishInfrastructure 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.
EnglishJupyter 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.
EnglishCanonical MCP server integration playbook: allowlist, Cursor mcp.json merge, smoke tests, and scaffolding. Use with ai-agents-rogue/mcp packages.
EnglishTypeScript, 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.
EnglishCanonical office/document generation and transformation: Word, PDF, PowerPoint, Excel, and LaTeX.
EnglishAI-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.
EnglishPBR 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.
EnglishPyTorch deep learning framework. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized pytorch-ml work when listed in TEAM.yaml or explicitly requested.
EnglishCanonical remote desktop / GUI access playbook: Guacamole, XFCE/xRDP, and VNC for environments that need a graphical desktop.
EnglishCanonical research and local/remote LLM usage: Ollama, DeepSeek/Perplexity style research MCPs, web/youtube summary, and research swarms.
EnglishSDKMAN - The Software Development Kit Manager for JVM tools. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized sdkman work when listed in TEAM.yaml or explicitly requested.
English
AGENT SKILLS ATLASIncludes Agentic Flow, Agentic Qe, AI Coding Assistants, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Agentic Flow
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.
Agentic Qe
Canonical quality engineering: test strategy, case generation, coverage gates, exploratory checks, and security-tinged QA (incl. Shannon-style pentest track when requested).
AI Coding Assistants
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.
API Engineering
Domain specialist for API design, development, and best practices. Scope: RESTful API design, GraphQL, API documentation, authentication, authorization, rate limiting, CORS, error handling, pagination, filtering, HATEOAS, API testing, API security. Excludes: database design, business logic, infrastructure, frontend, security beyond API. Triggers: "API", "REST", "GraphQL", "endpoint", "OpenAPI", "Swagger", "CORS".
Cloud Tools
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.
Compahook
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.
Container Docker Ops
Canonical container workflows: Docker/Compose development plus MCP-style container management patterns.
Draupnir
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.
E2E Delivery
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.
FFmpeg Processing
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.
Haskell
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.
Import to Ontology
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.
Infra Tools
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 Notebooks
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.
LLM Gateway Routing
LLM gateway and routing configuration using OpenRouter and LiteLLM. Invoke when: - Setting up multi-model access (OpenRouter, LiteLLM) - Configuring model fallbacks and r
MCP Integrations
Canonical MCP server integration playbook: allowlist, Cursor mcp.json merge, smoke tests, and scaffolding. Use with ai-agents-rogue/mcp packages.
Node.js Devtools
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.
Office Document Tools
Canonical office/document generation and transformation: Word, PDF, PowerPoint, Excel, and LaTeX.
Ontology Enrich
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.
Pbr Rendering
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.
PyTorch Ml
PyTorch deep learning framework. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized pytorch-ml work when listed in TEAM.yaml or explicitly requested.
Remote Desktop Access
Canonical remote desktop / GUI access playbook: Guacamole, XFCE/xRDP, and VNC for environments that need a graphical desktop.
Research and Local LLM
Canonical research and local/remote LLM usage: Ollama, DeepSeek/Perplexity style research MCPs, web/youtube summary, and research swarms.
Sdkman
SDKMAN - The Software Development Kit Manager for JVM tools. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized sdkman work when listed in TEAM.yaml or explicitly requested.
Showing 24 of 29 skills. Use the list’s page controls above to explore the rest.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Agentic Flow skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.