Avoid common Linux kernel mistakes — atomic context violations, allocation failures, and locking traps.

Role Description: I am an expert proficient in the Linux kernel, with in-depth understanding and analytical capabilities of the latest kernel source code (as of June 2024). I can provide users with de

Bulletproof voluntary Kernel Egg Planter — SHA-256 + Merkle registry + anchored permaweb + lattice tamper verify. Build/anchor P0-protocol eggs and ClawHub c...

Debug Linux kernel crashes using the crash utility and memory debugging tools. Use when users mention kernel crash, kernel panic, vmcore analysis, kernel dum...

OpenClaw continuity kernel for fail-open llm_input injection, deterministic runtime contracts, and shadow-mode eval receipts.

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or …

Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use…

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or …

Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use…

Indexed by skills.sh from kernel/skills

Indexed by skills.sh from kernel/skills

Indexed by skills.sh from kernel/skills

Indexed by skills.sh from kernel/skills

Indexed by skills.sh from kernel/skills

Agent continuity and cognitive health infrastructure. Use this skill when your agent needs persistent memory across sessions, crash recovery, append-only audit trails, heartbeat vitality monitoring, coherence enforcement, or witness-gated approval for critical actions. Also us…

Implements a 5-step recursive protocol guiding autonomous agents to self-locate, map constraints, detect challenges, prioritize survival, and act coherently...

Indexed by skills.sh from mukul975/anthropic-cybersecurity-skills

Indexed by skills.sh from nousresearch/hermes-agent

Indexed by skills.sh from yaklang/hack-skills

Indexed by skills.sh from mohitmishra786/low-level-dev-skills

Indexed by skills.sh from pytorch/pytorch

Indexed by skills.sh from github/awesome-copilot

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from nvidia/skills

Unified GPU kernel operator generation and optimization skill. Automatically detects the target repository type (FlagGems, vLLM, or general Python/Triton) an...

Applies microkernel architecture with minimal core and plugin extensibility

Ensures AI agents uphold the Three Laws of Silicon Intelligence within the Taohuayuan physical context for safe, ethical, and identity-anchored behavior.

Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integra…

Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integra…

Indexed by skills.sh from nvidia/skills

Indexed by skills.sh from aradotso/trending-skills

Tune AITER's CK GEMM and fused MoE kernels for specific model shapes on AMD GPUs. Covers shape discovery from inference logs, baseline benchmarking, kernel t...

Pre-installation agentic sandboxing protocol. 5-layer defense: semantic neutralization, hard quarantine, kernel ground-truth, trusted output rendering, and s...

Applies kernel tuning, web server optimization, security hardening, and resource limits to boost Hostinger VPS performance and reduce costs.

LYGO-OpenClaw sovereign command router — P0 gate, P1 mycelium, P3 consensus, P5 action identity, lattice limbs, consent-gated kernel egg lygo-openclaw-v10. B...

LYGO Sovereign Super Skill — one map for kernel eggs (11 catalog + 15 champions), consent-gated planters, P0–P5 Biophase7 products, lattice verify, and ClawH...

LYGO Sovereign Workflow Orchestrator — YAML workflows with P0 gate, P1 mycelium memory, P3 consensus, P5 run identity, and consent-gated kernel egg. Sandcast...

A secure, human-approved autonomous agent architecture that combines SMFOI-KERNEL orientation with Write-Ahead Logging (WAL), Proposal-First decision-making,...

Industrial-grade secure bridge to Bitwarden. Copy passwords and TOTP codes with Zero-trust kernel-level piping.

Simulates a quantum kernel using optical fiber storage and linear optics.

Control Browser's kernel for web automation. Supports web navigation, element interaction, page scrolling, file/video downloading, and content extraction.

Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits…

Use this skill when the user is doing hands-on DOCA Flow DPA Provider work — exporting a `doca-flow` pipe or external resource (index-selector/memory) into BlueField DPA address space so a DPACC-built kernel can read counters, mutate hash-pipe entries, and update/read memory o…

Use this skill when the user is doing hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object mode…

Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the …

Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the server posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE bandw…

Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the `gpunetio_ib_write_lat` client + server pair under `doca/tools/gpunetio_ib_write_lat/`, checking GPU-NIC pairing, reading the half-iter / full-ite…

Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-param…

Use when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/. Triggers: build bsp, rebuild dtb, rebuild kernel.

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI. Do NOT use for UPHY lane allocation or ODMDATA edits.

Enable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

Per-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lane allocation or endpoint-mode bring-up.

Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM. Do NOT use for kernel-DT overlay or ODMDATA edits.

Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for module-level or kernel-DTB changes.

Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not for CPU/GPU frequency tuning.

Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target. This is an example skill.

Deploy mihomo proxy kernel + Metacubexd web UI on a Linux server (no sudo required, uses systemd --user). Use this skill whenever the user wants to set up mi...

OpenClaw Cognitive Operating & Skill Governance Kernel

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when …

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

Enhanced `uname` command with colorized, structured output. Shows hostname, OS, kernel, architecture. **Dependency**: This is an x-cmd module. Install x-cmd...

Use this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core context, loading a DPACC-compiled DPA app image (`doca_dpa_app`), creating DPA threads, launching kernels via `doca_dpa_kernel_launch_update_*`, draining `doca_…

Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits…

Use this skill when the user is doing hands-on DOCA Flow DPA Provider work — exporting a `doca-flow` pipe or external resource (index-selector/memory) into BlueField DPA address space so a DPACC-built kernel can read counters, mutate hash-pipe entries, and update/read memory o…

Use this skill when the user is doing hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object mode…

Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the …

Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the server posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE bandw…

Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the `gpunetio_ib_write_lat` client + server pair under `doca/tools/gpunetio_ib_write_lat/`, checking GPU-NIC pairing, reading the half-iter / full-ite…

Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-param…

Use when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/. Triggers: build bsp, rebuild dtb, rebuild kernel.

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI. Do NOT use for UPHY lane allocation or ODMDATA edits.

Enable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

Per-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lane allocation or endpoint-mode bring-up.

Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM. Do NOT use for kernel-DT overlay or ODMDATA edits.

Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.

Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for module-level or kernel-DTB changes.

Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not for CPU/GPU frequency tuning.

Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target. This is an example skill.

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when …

Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers du…

Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.

Iterative Python via live Jupyter kernel (hamelnb).

Indexed by skills.sh from kernel/skills