Answer questions about Stigmer from the official documentation at stigmer.ai/docs. Use this skill whenever someone asks what Stigmer is, how a concept works (Agent, Skill, MCP Server, Session, Workflow, Datastore, Environment, Organization, approval flows), or how to do something with the product, CLI, or SDKs. It carries the map of the documentation and the answering methodology; the content itself is read live from the published docs, so answers are never based on a stale snapshot.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Basic arithmetic helper skill.
Create and edit Stigmer Agent YAML files conforming to the agentic.stigmer.ai/v1 API. Use this skill when the user wants to create a new AI agent, modify an existing agent definition, or get help authoring Agent YAML for the Stigmer platform. Triggers on requests like: "create an agent", "write an agent YAML", "define an agent for X", "help me build an agent that does Y", "add an MCP server to my agent", "add a sub-agent", or "modify my agent's instructions".
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks to use the Claude API, Anthropic SDKs, or Managed Agents (/v1/agents, /v1/sessions, /v1/environments). DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.
Review code changes with a structured methodology covering correctness, security, performance, and maintainability. Use this skill when asked to review a pull request, diff, code change, merge request, or patch. Also applies when asked to audit code quality, identify bugs in a changeset, or provide feedback on someone's code. Triggers on requests like: "review this PR", "look at this diff", "check this code for issues", "what do you think of this change", "audit this for security", or "give me feedback on my implementation".