409 skills · sorted by relevance
Diagnose unresponsive GKE GPU or TPU nodes and pods stuck terminating through read-only checks of node status, logs, serial output, and repair history. Receive documented recovery guidance to apply yourself.
Write and improve documentation for ComfyUI nodes in per-node JSON files. Use when asked to document nodes, write node descriptions, add tips to nodes, improve node docs, enrich node content, fill in empty node descriptions, or batch-write documentation for new/updated nodes. Also triggers on "write docs for nodes", "document the new nodes", "improve node tips", "fill in node descriptions", "enrich nodes", "node content pass", "update nodes", "sync comfyui nodes", "new comfyui version", or "node enrichment".
The English summary is being prepared. Showing the original description.
Recover from stale RFDB nodes that survive `commit_batch` cleanup despite having their `file` field listed in `changed_files`. Use when: (1) re-running an enricher/orchestrator step but old data with the same file field stays in the graph, (2) `commit_batch(changed_files=[X], ...)` reports success but a query later still returns nodes with `file = X`, (3) you re-pointed structural nodes (e.g., DIRECTORY/FILE) from a synthetic file path to real file paths and the old synthetic-path nodes won't go away, (4) graph-stream / find_by_type returns a mix of "stale" and "new" nodes for the same logical entity. Root cause: `handle_commit_batch` calls `engine.find_by_attr({file: X})` to enumerate nodes-to-delete, but that query path returns only a PARTIAL set after compaction (L1 segments and the file→nodes index can desync). Workaround: enumerate stale nodes via the TS rfdb client `queryNodes({file: X})` (different code path that finds all of them) and call `deleteNode(id)` per node, then re-commit the intended state. Related: rfdb-manifest-l1-carryforward (same L1 family).
The English summary is being prepared. Showing the original description.
Plan and configure security across Google Kubernetes Engine clusters. Review access permissions, enable Secret Manager integration, and configure protections such as Shielded Nodes and Binary Authorization to strengthen the platform supporting your applications.
Fix nodes silently disappearing from RFDB when an enricher or post-resolution pass writes new nodes via BatchHandle. Use when: (1) writing a TypeScript enricher that should ADD nodes/edges to existing files, (2) after calling `client.createBatch()` + `batch.addNode({file: 'X', ...})` + `batch.commit()` the original nodes in file X have vanished, (3) tests that load a graph fixture, run an enricher, then query original nodes get empty results, (4) a verification step shows expected nodes pre-enrichment but 0 post-enrichment. Root cause: `BatchHandle.commit()` invokes RFDB's `commit_batch` which AUTO-POPULATES `changed_files` from each added node's `file` field, then the server DELETES all existing nodes whose `file` matches before inserting new ones — file-level upsert semantics. This is correct for the JS/Haskell analyzers (which fully re-emit a file's contents) but catastrophic for enrichers that only ADD to existing files.
The English summary is being prepared. Showing the original description.
Write and troubleshoot n8n expressions, the formulas that pass and transform data between workflow steps. Covers field references, webhook inputs, dates, strings, and choosing between expressions and Code nodes for data transformations.
Deploy n8n on a Linux server using Docker Compose and Caddy for automatic HTTPS. Choose a single instance or queue workers, configure secrets and Python task runners, and follow procedures for updates, backups, and recovery.
Write and troubleshoot native Python in n8n Code nodes. Covers data filtering and transformation, migration from older Python code, valid return formats, and restricted execution environments, including cases where errors pass unprocessed input downstream.
Remote command execution and file transfer on SageMaker HyperPod cluster nodes via AWS Systems Manager (SSM). This is the primary interface for accessing HyperPod nodes — direct SSH is not available. Use when any skill, workflow, or user request needs to execute commands on cluster nodes, upload files to nodes, read/download files from nodes, run diagnostics, install packages, or perform any operation requiring shell access to HyperPod instances. Other HyperPod skills depend on this skill for all node-level operations.
The English summary is being prepared. Showing the original description.
Write Python for n8n Code nodes to transform, filter, aggregate, and validate workflow data. Get guidance on reading input items, returning the required JSON structure, using standard library modules, and avoiding common errors within n8n's Python execution modes.
Diagnose GKE TPU slice creation failures caused by shared nodes. Check slice status, partition labels, and monitoring data to identify conflicting resource groups, then provide resolution steps for the user to apply.
Diagnose GKE TPU virtual machines that remain in repair by checking instance status, host events, and automatic repair history. Understand the impact on grouped TPU nodes and identify recovery steps for the user to apply.
Configure and troubleshoot automatic node scaling in GKE. Examine logs and workload constraints to explain why nodes fail to grow or shrink, and guide tuning for capacity shortages, zone placement, and sudden traffic increases.
Diagnose and fix RFDB data disappearing after compaction, where rfdb-server reports a tiny node count (e.g. "15 nodes") on startup despite manifest_index.json showing hundreds of thousands of nodes and segment files existing on disk. Use when: (1) rfdb-server logs "Default database: N nodes" with N orders of magnitude smaller than recent analysis output, (2) /api/stats returns only the most recent commit's nodes, (3) the issue appears AFTER a compaction event (manifest with l1_node_segments populated and node_segments: []), (4) subsequent commits dropped L1 references. Root cause: ManifestStore::create_manifest() initializes l1_node_segments/l1_edge_segments to Vec::new() instead of cloning from current manifest, so any commit AFTER compaction silently orphans all L1 data even though segment .seg files still exist on disk. Compaction injects L1 fields explicitly after create_manifest, but regular commits do not.
The English summary is being prepared. Showing the original description.
Fix node query issues in Grafema tests when nodes have numeric IDs instead of human-readable IDs, or when `type` field is undefined. Use when: (1) queryNodes returns nodes with numeric IDs like "52710336597754872375318185843222727675" instead of semantic IDs like "net:request#__network__", (2) node.type is undefined but node.nodeType has a value, (3) metadata is a JSON string instead of parsed object, (4) tests fail with "Cannot read property 'length' of undefined" after queryNodes. Covers RFDBServerBackend vs RFDBClient distinction and async generator handling.
The English summary is being prepared. Showing the original description.
Set up RuView sensing nodes by building and flashing ESP32 firmware, configuring WiFi and the receiving address, and checking serial logs. Diagnose missing CSI streams, the WiFi signal measurements sent by sensing nodes.
Work on advanced RuView sensing with signals from multiple WiFi nodes. Explore position estimation, three-dimensional occupancy reconstruction, changes in movement patterns over time, and defenses against suspicious signals, with guidance on implementation modules and validation.
Implement and manage Raft, a method for keeping distributed servers in agreement. Covers leader election, log replication, node membership changes, and recovery after network disruptions to maintain consistent state across the cluster.
Coordinate gossip protocols, where nodes pass information among peers, for distributed systems. The skill covers update propagation, state synchronization, conflicting changes, failure detection, and tuning communication so nodes eventually reach a consistent state.
Connect ruflo agents running on different machines to share status, tasks, and results through signed messages. Coordinate work ownership across nodes, verify messages against registered public keys, and synchronize shared rooms over HTTP.
Build graph neural networks, models that learn from connected nodes, with PyTorch Geometric. Supports node and graph classification, link prediction, custom datasets, and training approaches for large graphs or graphs containing multiple types of nodes and connections.
Review Pascal pull requests or branches against documented architecture rules. Check package responsibilities, node extension patterns, state management, and rendering subscriptions to identify misplaced code, compatibility breaks, and changes that could cause excessive redraws.
Write JavaScript for n8n Code nodes to aggregate, filter, and transform workflow data. Guidance covers data access, output formats, execution modes, common errors, and performance choices when processing large numbers of records.
Use n8n-mcp tools to find workflow steps, check settings, and create or update automations. Provides guidance on tool arguments, templates, folders, credentials, and security audits so agents can choose appropriate operations.