agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Add graph-backed memory and context retrieval to agent workflows
Use Cognee to ingest project knowledge into graph and vector memory so agents can retrieve durable context across sessions and workflows.
Governance layer for Claude Code Agent Teams — durable auditability, operational controls, and evidence trails for AI-assisted development.
Governance framework for AI agent team coordination, audit trails, and boundary enforcement.
workflow-init
Install and configure Vercel Workflow DevKit before it exists in node_modules. Use when the user asks to "install workflow", "set up workflow", "add durable workflows", "configure workflow devkit", or "init workflow" for Next.js, Express, Hono, Fastify, NestJS, Nitro, Nuxt, Astro, SvelteKit, or Vite.
duroxide-code-coverage
Measure and improve code coverage in the Duroxide durable execution runtime. Use when asked about coverage, testing coverage, running llvm-cov, or improving test coverage percentages.
codex-upcoming-features
Fetch and summarize upcoming unreleased Codex features using a durable local clone synced from GitHub, with source-file mining as primary evidence. Use when asked for latest upcoming/openai-codex features, what is coming next but not in the latest stable release, or a live release-gap summary with links and as-of timestamp.
Mnemolog MCP
Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.
continual-learning
Orchestrate continual learning by delegating transcript mining to agents-memory-updater and writing durable memory to local JSON (never root AGENTS.md Learned sections). USE WHEN continual learning, mine prior chats, maintain agent memory, or the stop hook triggers this skill.
Durable UI
Durable UI is the practice of making client-side state and interactions resilient. State should survive page reloads, browser sessions, and â where appropriate â be shareable via URL. Interactive elements like dropdowns and modals should be dismissable in the ways users expect (click outside, Es
oly
Use when starting a long-running or interactive CLI command with oly, especially when it may need later input, should be detachable, or should keep durable logs for supervision and resume.
agent-learnings
Log durable agent learnings as JSON entries for reuse across tasks.
engram
Local-first personal AI identity and memory layer for MCP-compatible coding tools (Claude Code, Codex, Cursor, and others). Use this skill when the user wants to continue from a previous session ("continue from last session", "pick up where we left off"), recall a past decision ("what did we decide", "what was our reasoning"), persist something durable ("remember this", "save a lesson", "save a decision", "save a playbook"), search prior knowledge ("search what we know about X", "have we hit this before"), export their identity or context ("export my identity card", "give me my context"), or maintain local-first cross-tool identity and memory that the user owns and approves. Engram stores user-approved lessons, decisions, playbooks, and project context as local JSON; the AI suggests, the user decides what becomes permanent.
auto-memory
Extract durable learnings and preferences from conversations for automatic memory capture.
sigma_ingest
Extract durable ktx wiki knowledge from staged Sigma data model specs and workbook summaries. Load for WorkUnits with unitKey sigma-data-models or sigma-workbooks.
getting-started
First-time setup for Durable Streams. Install @durable-streams/client, create a stream with DurableStream.create(), read with stream(), subscribe to live updates, resume from saved offsets. Covers offset semantics ("-1", "now", opaque tokens), LiveMode (false, true, "long-poll", "sse"), and StreamResponse consumption (.json(), .text(), .subscribeJson()).
c-00-initialize-coordination-root
Initialize the Agents Remember memory and coordination folders for a fresh clone or incomplete setup. Defaults to repo-local ar-memory durable memory plus local ar-coordination state; use external-memory scaffolding only when the developer explicitly asks for it.
swarmvault
Operate SwarmVault knowledge bases from the CLI: initialize vaults, shape swarmvault.schema.md, ingest sources, compile/query/lint/watch/hook, and expose the vault over MCP when agents need durable markdown, graph, and search artifacts on disk.
durable-functions-dotnet
Build durable, fault-tolerant workflows using Azure Durable Functions with .NET isolated worker and Durable Task Scheduler backend. Use when creating serverless orchestrations, activities, entities, or implementing patterns like function chaining, fan-out/fan-in, async HTTP APIs, human interaction, monitoring, or stateful aggregators. Applies to Azure Functions apps requiring durable execution, state persistence, or distributed coordination with built-in HTTP management APIs and Azure integration.
autoskill
Analyze coding sessions to detect corrections and preferences, then propose targeted improvements to Skills used in the session. Use this skill when the user asks to "learn from this session", "update skills", or "remember this pattern". Extracts durable preferences and codifies them into the appropriate skill files.