mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Build and manage AI agents, tools, and workforces on Relevance AI
Plugin relevance-ai from marketplace cc-plugin in RelevanceAI/cc-plugin. Commands read from the repo's manifest — 6 days ago.
managing-relevance-agentsManages Relevance AI agents - creating, configuring tools, writing system prompts, setting up triggers and notification rules, running tasks, and running an agent over many items one task each. Use when building agents, attaching tools, working through a list (leads, rows, a CSV, a table), telling p
managing-relevance-foldersOrganize 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.
managing-relevance-knowledgeUse whenever the user wants records or documents in a knowledge base, or an agent to use one — seeding or updating structured rows (CRM contacts, leads, support tickets), turning a short document you can read into knowledge an agent always follows, attaching a base to an agent (prompt mode or tool m
managing-relevance-toolsManages 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
managing-relevance-workforcesManages 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, running a workforce once per item of a list, or debugging workforce execution.
relevance-analyticsRetrieves 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.
relevance-diagnosticsDiagnose 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 consumi
relevance-evalsManages 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, setting up performance dashboards that monitor production traffic, and configuring alarms t
relevance-llm-modelsWhich LLM model to configure on an agent, tool step, or workforce node — how to pick on task shape, what each vendor is structurally best at, the config traps that fail silently, and a dated list of current picks.
relevance-slide-builderManages 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.
relevance-task-opsRead the Task Ops (monitor) page for a project — the operator surface that lists every agent task — and manage task alarms on task errors, pending approvals and escalations. Use when the user asks to see their tasks, how many are errored / escalated / awaiting approval, to list the failing tasks, to
relevance-task-prioritiesSet, raise, lower, or clear the task-priority tier of an agent, tool, or workforce so important work is scheduled ahead of lower-value work under the project's concurrency limits. Use when a resource is starved or queued rather than failing — "why is this agent so slow to start?", "make this agent r
relevance-aiconnects to: https://mcp.relevanceai.com
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.