Loading...
Loading...
Found 24 Skills
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
Design lightweight eval harnesses for coding or workflow agents, especially when testing whether agents follow steering docs, use tools correctly, preserve user edits, recover from failures, and produce the intended artifact.
Deploy prompt-based Azure AI agents from YAML definitions to Azure AI Foundry projects. Use when users want to (1) create and deploy Azure AI agents, (2) set up Azure AI infrastructure, (3) deploy AI models to Azure, or (4) test deployed agents interactively. Handles authentication, RBAC, quotas, and deployment complexities automatically.
Create and run LangWatch experiments for pre-deployment batch testing. Use when the user wants to test an agent against a dataset, compare prompts or models, benchmark quality, detect regressions, or add a CI quality gate. Do not use for production monitoring or guardrails.
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
Creates, modifies, and manages Claude Code subagents by writing agent files with YAML frontmatter, system prompts, and tool configurations. Use when you need to "create an agent", "modify an agent", "set up a specialist", "I need an agent for [task]", "agent to handle [domain]", or "configure agent tools". Covers agent file format, YAML frontmatter, system prompts, tool restrictions, MCP integration, model selection, and testing.
End-to-end interactive workflow — pick a product, then either run existing tasks and environments (Path A) or set up new ones from docs, suggested tasks, credentials, and templates (Path B). Builds the experiment, attaches signals, and optionally triggers the first iteration. Trigger when users say: "set up an experiment", "create an experiment", "I want to run an experiment", "run my tasks", "setup experiment", "new experiment", "configure an experiment", or "experiment setup".
Build AI agents with Pydantic AI — tools, capabilities, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add tools/capabilities, stream output, define agents from YAML, or test agent behavior.
Integrate a raw customer agent repo with Veris end to end. Installs or verifies veris-cli, logs in, creates or reuses a Veris environment, analyzes the repo, generates or updates `.veris/veris.yaml`, `.veris/Dockerfile.sandbox`, `.veris/.dockerignore`, configures runtime env vars, and can finish with `veris env push`. Use when a repo has no Veris setup yet, or when an existing `.veris/` integration is stale and needs to be refreshed.
Drive comprehensive test creation for a feature, spec, module, or PR. Decide what must be tested, pick the testing strategy at the lowest sufficient cost, drive the test producers to author the tests, run them, and record the session — what was tested, by what test type, and what passed — in specs/<feature>/test-spec.md and test-report.md. Drives the producers create-yaml-tests and create-agent-tests.
Use when creating specialized subagents for Claude Code plugins or the Task tool - covers description writing for auto-delegation, tool selection, prompt structure, and testing agents