1.7K skills · sorted by relevance
Assess Docker, containerd, and Podman environments for weaknesses that could expose the host system. The skill organizes checks for excessive permissions, exposed runtime sockets, and known vulnerabilities, alongside indicators defenders can monitor.
Set up NVIDIA infrastructure for synthetic data generation on MicroK8s or Azure AKS. Coordinate Kubernetes, inference services, and OSMO workflow execution, with prerequisite checks, deployment validation, capacity planning, and failure investigation before workloads are retried.
Compare ways to distribute AI inference across multiple instances, including replicas and separate input-processing and generation stages. Estimate capacity, throughput, delays, state-transfer costs, and recovery overhead to support routing and scaling decisions.
Compare batching, request scheduling, and memory management for a single model serving instance. Assess concurrent request capacity, response times, generation speed, and GPU time per result that meets the required quality and deadline.
Model ongoing requests and multi-step agent work to estimate capacity, latency, and cost per completed task. Break execution into stages, account for queues and retries, and produce workload tables with average and peak resource budgets.
Build servers and clients for A2A, an open protocol that lets AI agents communicate across frameworks. Publish agent capabilities, exchange tasks and results, stream progress, and add notifications for workflows involving multiple agents.
Provide language-specific reference files for test analysis skills. The catalog helps agents recognize test methods, assertions, skipped tests, waiting patterns, setup and cleanup hooks, external dependencies, and tagging capabilities across different frameworks.
Coordinate work across independent Squad installations by discovering their capabilities and delegating tasks across repositories. It guides context sharing, acceptance criteria, and progress tracking, while distinguishing persistent Squad teams from temporary groups of agents.
Inspect available APIs in Open-Science and find files, session status, and agent conversations within the current project. Check which host features are available before using them, and trace the inputs behind generated file versions.
Guide site integration work from capability discovery and authentication choices through implementation and validation. Cover account features, administrative resources, check-ins, or native editor usability, while documenting evidence, supported behavior, and paths that remain unverified.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Generate images, reference-based edits, and video clips from stills through configured APIs or local Codex and Grok tools. Check available generation options, configure keys, track estimated costs, and resume interrupted jobs.
Check which paid advertising integrations NotFair offers, connect ad accounts, and configure MCP connections for agent access. Verify available tools and whether a platform supports reading or changes, and investigate access problems.
Discover the tools, workflows, specialist agents, and hooks available in a configured workspace. Interactive guidance and topic-specific commands help you choose relevant capabilities, inspect usage examples, and understand customization options.
Prepare documentation for a medical device quality management system under ISO 13485. Review existing documents for gaps, draft quality manuals and procedures, and organize device files with prioritized actions for certification preparation.
Integrate WebMCP tools, app capabilities that AI agents can call, directly into an existing web application. Inspect its source code, preserve existing validation and permissions, and verify tool discovery, execution, and actual changes in application state.
Assess whether a DOCA application needs low-level communication controls beyond its higher-level APIs. For those cases, guide queue configuration, libibverbs migration, and error diagnosis using installed headers, version checks, and device capability queries.
Not for writing library code (name that library skill). Use this skill whenever another DOCA skill says "prefer the structured tool per doca-structured-tools-contract", or when the user wants a one-shot answer that consolidates info multiple manual commands would produce — DOCA env / version / devices / capabilities / validate / host vs DPU state. Trigger even when the user does not explicitly mention "structured tool" or "doca-env --json" — typical implicit phrasings include "is there one command that tells me everything about my DOCA install", "what version is X capability available since", "every PF/VF/SF visible on this BlueField with PCIe address", "will this pipe pass validate before commit", "diff host vs DPU state", or "why does the agent give a one-line answer on host A and five commands on host B". Refuse and route elsewhere for general DOCA orientation, specific library API how-to, or install-from-scratch guidance — those belong to the per-library skill, doca-public-knowledge-map, or doca-setup.
The English summary is being prepared. Showing the original description.
Helps inspect comch communication channels between a host and a BlueField DPU using the DOCA admin tool. Explains server and connection tables and checks discrepancies with application state through a read-only inventory scan.
Use this skill when the user is invoking doca_flow_dpa_perf on DPA-capable hardware (ConnectX-7 minimum supported, ConnectX-8 recommended, or BlueField-3) to measure rule update / disable rates on the DPA-offloaded DOCA Flow path — picking the active / passive device split, choosing workload-shape axes (burst, queue, completion threshold, workers, hash pipe algo, PSL tables), or reading Kops/sec iteration stats and the optional self-test. Trigger even when the user does not explicitly mention "doca_flow_dpa_perf" or "DPA Provider" — typical implicit phrasings include "how fast can the DPA program path-selector entries", "baseline rule-update rate on ConnectX-8", "tool reports zero ops on my BlueField", "self-test sentinel never shows on tcpdump", or "is my BlueField-2 DPA-capable". Refuse and route elsewhere for the host / DPU-CPU Flow path (doca-flow-perf), Flow pipeline tuning (doca-flow-tune), writing doca-flow / doca-dpa applications, or DOCA install — those belong to other skills.
The English summary is being prepared. Showing the original description.
Build and solve routing problems in Python with cuOpt, including delivery fleets, round trips, and pickup-delivery tasks. Define vehicle capacities, arrival windows, and visit order constraints, then inspect routes, total cost, and orders that cannot be served.
Historical reference for script-owned loop capacity requests. Do not use from provider sessions.
The English summary is being prepared. Showing the original description.
[omh] Parallel tool-call capability in doubt: report the version and whether MCP parallel tool calls are enabled, then apply the diff for parallel tool calls only after approval; an update only on request. Use when the user says: parallel-tools, parallel tools, hermes parallel tools setup, update hermes for parallel tools, check parallel tool support, enable parallel tool calls, verify parallel tools capability, check hermes version for parallel tools.
The English summary is being prepared. Showing the original description.
[omh] Explaining OMH itself: current-source-first documentation for OMH itself: product identity, public capability catalog, model routing, local state, and long-term memory. Use when the user says: product-docs, OMH documentation, oh-my-hermes documentation, what is OMH, what is oh-my-hermes, how does OMH work, OMH capability catalog, OMH skill catalog.
The English summary is being prepared. Showing the original description.