Loading...
Loading...
Found 6,294 Skills
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.
Install and use China-focused education Agent Skills for textbook sync, exam prep, mistake review, daily practice, and teacher workflows with Hermes Agent
Research computing toolkit for optoelectronic information science and engineering, MATLAB/Octave, Python scientific analysis, signal processing, image processing, statistics, simulation, optimization, publication figures, sensor/time-series data, citation lookup, and common scientific libraries. Use when the user asks for MATLAB code, scientific Python, data analysis, plots, simulations, formulas, statistics, machine learning, optical/physical/materials computation, or reproducible research workflows.
Mend integration. Manage data, records, and automate workflows. Use when the user wants to interact with Mend data.
Use this skill whenever the user needs to manage VMs in VMware/vSphere/ESXi — it's the entry point for all VM operations. Directly handles: power on/off, clone, snapshot, migrate, deploy from OVA or templates, run commands inside VMs, batch operations, cluster management, and vCenter alarm acknowledgment. Always use this skill for any "power on", "clone", "deploy", "migrate", "batch", "guest exec", "alarm", or VM lifecycle task when the context is explicitly VMware, vSphere, or ESXi. Do NOT use for read-only queries (use vmware-monitor), NSX networking (use vmware-nsx), storage/iSCSI/vSAN (use vmware-storage), or Kubernetes cluster lifecycle (use vmware-vks). For multi-step workflows use vmware-pilot. For load balancing/AVI/AKO use vmware-avi.
Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
Batch Account Authorization Workflow: Orchestrate account list + staff list + API calls to complete batch authorization of stores to employees. Suitable for batch assigning store permissions when new employees join.
Ghostty submodule and GhosttyKit workflow rules for cmux. Use when modifying the ghostty submodule, rebuilding GhosttyKit.xcframework, updating the parent submodule pointer, or documenting fork conflict notes.
THE workflow for picking up and carrying ONE ticket/card forward, for an autonomous worker agent or for a human doing it locally. Resolves the repo's tracker from the AFK registry (~/.claude/afk.json; GitHub Projects or Linear), picks one ticket by priority, routes by status x label (interview / human walkthrough / execute), loads LEARNINGS.md as binding constraints, implements test-first, verifies end-to-end and simplifies the diff (the /go finish), then branches to a PR for the reviewer. Use when the user says "pick up <id>", "work on issue <id>", invokes /engineer, invokes /pickup, says "pickup", or at the very start of working any card.
Transform research questions into constructs, design, samples, measurement, analysis, falsification, and execution plans. Use when the user asks for "design research", "can this method answer the question?", "help me create a research proposal", or requests the rw-research-design workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Author, audit, and improve Grafana SKILL.md files against Anthropic's published Agent Skills guidance and the four-dimension rubric the grafana/skills CI gate uses (conciseness, actionability, workflow clarity, progressive disclosure). Applies the canonical SKILL.md structure (YAML frontmatter + body + references/ + scripts/ + assets/), the "pushy description" trigger pattern, the three-level progressive-disclosure model, and the validate-fix-rerun feedback loop. Use when creating a new skill in this repo, when reviewing a skill PR, when a skill's Tessl review score is below 75 (the merge gate), when a skill's description isn't getting picked up by agents, when restructuring a long SKILL.md into a bundle, or when the user asks how to write, improve, optimize, audit, or fix a skill - even if they don't say "skill" explicitly (e.g. "this isn't triggering", "Tessl scored this 72", "split this doc").