CMEM Pro
claudeCMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Plan and implement DataSQRL data pipelines with the Dockerized DataSQRL Code Agent.
Plugin datasqrl from marketplace datasqrl in DataSQRL/datasqrl-plugin. Commands read from the repo's manifest — 2 days ago.
deployUse when the user wants to deploy a DataSQRL project to DataSQRL Cloud, ship or release it, create a deployment, check how a deployment is going, or read its logs. Also use when they ask to sign in to DataSQRL Cloud or which organizations and projects they have.
implementUse when the user has reviewed a DataSQRL plan and explicitly approved implementing it - for example by saying it looks good, to go ahead, or to implement it. Runs the DataSQRL Code Agent in implementation mode over that plan, the full autonomous implement, compile, test, verify and refine loop.
patchUse for a small, well-scoped change to an existing DataSQRL project. Runs the DataSQRL Code Agent in patch mode, which implements the requested changes, updates the tests and documentation they affect, runs the tests and refines if tests fail. Patch mode is not for anything complex or requiring larg
planUse when DataSQRL requirements exist and the next step is a plan, or when the user asks to plan a DataSQRL pipeline or data catalog. Runs the DataSQRL Code Agent in planning mode over a requirements document or a requirements string, producing a reviewable, checkbox-tracked adr/plan_<ts>.md. Takes a
progressUse when the user asks anything about the DataSQRL Code Agent run for the current project - whether it is still running or has finished, how far it has come, or asks to stop it. Works from any session at any time, including one that did not start the run. Explains and reports; does not fix or invest
promoteUse when the user wants to make an existing DataSQRL Cloud deployment the project's main one - promote it to main, make it the primary or live deployment, or point production at it. Only for DataSQRL Cloud deployments, not for promoting a git branch, a release or a build artifact.
requirementsUse when writing, gathering or improving the requirements for a DataSQRL pipeline or data catalog, before planning. Use whenever the user describes what they want built but has no requirements document (in working project) yet, or asks to turn notes, a ticket, an API doc or a conversation into DataS
resolve-issueUse when the user wants a GitHub issue on a DataSQRL project resolved, fixed or implemented - they give an issue URL or number, or refer to an issue the DataSQRL Cloud assistant filed. Reads the issue, runs the DataSQRL Code Agent over it from the project's directory in the lane the fix needs, and h
startUse when the user wants to build, extend, change, or plan a DataSQRL data pipeline or data catalog based on user requirements or an existing ticket. Use whenever the user need data engineering, such as materializing tables in a data lake, processing data in realtime or batch, exposing transformed da
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Agent teams, swarm coordination, Monitor streams, and worktree isolation
2 skills · 2 commands · 2 agents
Easily deploy managed PostgreSQL (pg), Kafka, OpenSearch, Clickhouse and other databases, streaming and apps. Free tier available, up and running in minutes.
1 skill · 1 MCP server
Schema validation, data quality monitoring, streaming validation pipelines, and input validation for backend APIs
1 agent
Internal BizOps domain. v2.8.0 ships 7 skills: orchestrator + process-mapper (BPMN/bottleneck/cycle-time, Lean+TOC) + vendor-management (scorecard+SLA+3rd-party risk, NIST SP 800-161/ISO 27036) + capacity-planner (Erlang-C queueing math for ops teams, NOT engineering) + internal-comms (ADKAR+Kotter 8-step, NOT marketing) + knowledge-ops (SOP+runbook+KB hygiene with 5W2H, context: fork) + procurement-optimizer (UNSPSC spend categorization + supplier consolidation). Orchestrator uses context: fork to route inquiries via Matt Pocock grill discipline (one question per turn, recommended answer, canon-cited challenge). Every SKILL.md ships a Forcing-question library section. 18 stdlib Python tools, 24+ reference docs. Distinct from business-growth (external sales) and c-level-advisor (strategic).
7 skills · 8 commands · 1 agent
Skills for building apps with the AG-UI .NET SDK: streaming chat (stateless vs hosted agents), server tools, client tools, human-in-the-loop (approvals & interrupts), shared state, multimodal messages, reasoning traces, protobuf transport, and troubleshooting.
9 skills
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.