cc-plugin

Manages Relevance AI agents - creating, configuring tools, writing system prompts, setting up triggers, and running tasks. Use when building agents, attaching tools, debugging execution, or viewing agent results.

Organize Relevance AI agents and tools into folders — create, list, rename, move items between folders, and delete folders. Use when the user wants to tidy a project, group related items, or bulk-organize agents/tools after creating them.

Use whenever the user asks an agent to seed or update a structured-row store (CRM contacts, leads, support tickets) or to inspect knowledge-base metadata. Covers knowledge-base CRUD and row CRUD. File / document-URL ingestion is not available via the tools — direct the user to the Knowledge tab in the Relevance app UI. For Q&A over knowledge, attach the base to an agent and let the built-in `agent_knowledge` tool answer.

Manages Relevance AI tools (studios) - creating transformation workflows, configuring OAuth, setting vendor/brand tool icons, running tools, and recovering versions. Use when building tools, adding steps, setting a tool's icon for a provider, debugging transformations, or restoring previous versions.

Manages Relevance AI workforces (multi-agent systems) - creating workflows, configuring nodes/edges, triggering execution, and debugging runs. Use when building multi-agent pipelines, connecting agents together, or debugging workforce execution.

Retrieves usage analytics for Relevance AI agents and projects. Use when asked about agent/workforce/tool usage, credit spend, error rates, breakdowns, task-status counts, most active agents, execution counts, or usage trends over time.

Diagnose what is wrong in a Relevance AI project and recommend fixes. Use when the user asks to "analyse my project", "diagnose this agent/workforce", "why is X failing?", "what's wrong / what should I fix?", "what's failing?", or "any regressions?". Finds root causes and recommends fixes by consuming the analytics, eval, and error read tools.

Manages evaluations and monitoring for agents and workforces (multi-agent systems) in Relevance AI — creating test cases, defining checks, configuring tool simulations, running evaluations, analysing results, and setting up performance dashboards that monitor production traffic. Use when testing agent or workforce behaviour, setting up automated testing, reviewing eval results, or monitoring production agents for failures.

Read the Task Ops (monitor) page for a project — the operator surface that lists every agent task. Use when the user asks to see their tasks, how many are errored / escalated / awaiting approval, to list the failing tasks, or to open a specific task and read its error.

Manages slideshows, slideshow templates, slideshow versions, and brand kits in Relevance AI. Use when creating presentations, managing brand assets, exporting slides, or working with slide templates.