all publishers

mesh-llm

@mesh-llm source repo

31 published skills

  1. ▌
    Distribution Certification · mesh-llm bundle
    Certify a published MeshLLM packaging release end to end across native Linux packages, Homebrew, npm SDK, and OCI images. Use when validating a MeshLLM version or packaging tag, proving that published artifacts install or load and start their packaged runtime, checking release checksums/SBOM/provenance/labels, comparing versions across channels, preserving pre-existing services, cleaning all test state, and producing an evidence-backed overall PASS/FAIL/BLOCKED verdict.
    4k repo stars
  2. ▌
    Skippy Spec Bench · mesh-llm
    Use this skill when testing or benchmarking target/draft GGUF pairs for speculative decoding compatibility, tokenizer agreement, draft acceptance rate, or staged verification behavior.
    4k repo stars
  3. ▌
    Hf Gguf Quant Jobs · mesh-llm bundle
    Use when creating, monitoring, validating, or documenting low-memory Hugging Face Jobs or local runs that quantize split BF16/FP16 GGUF model repos into custom quant GGUF repos with skippy-quantize.
    4k repo stars
  4. ▌
    Release Validation · mesh-llm bundle
    Use this skill when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally built release bundles on user-approved real hosts and private meshes, deciding release readiness, or producing a formal evidence-backed release-validation report.
    4k repo stars
  5. ▌
    Skippy Correctness · mesh-llm
    Use this skill when validating skippy staged execution against full-model execution, adding model families, changing split boundaries, testing activation wire dtypes, or diagnosing mismatch behavior.
    4k repo stars
  6. ▌
    Llama Patch Changes · mesh-llm
    Use when changing mesh-llm's llama.cpp patch queue, upstream pin, prepare/build scripts, or carried RPC, MoE, and mesh-hook llama.cpp patches.
    4k repo stars
  7. ▌
    Skippy Model Package · mesh-llm
    Use this skill when inspecting GGUF models, planning layer ranges, generating or validating skippy package artifacts, fake packages for direct GGUFs, materialized stage cache behavior, or GGUF writer integration.
    4k repo stars
  8. ▌
    Hf Layer Package Jobs · mesh-llm
    Use when changing mesh-llm automation or CLI flows that discover Hugging Face GGUF models, plan CPU Hugging Face Jobs for layer-package splitting, estimate max cost, or publish skippy layer packages/catalog entries.
    4k repo stars
  9. ▌
    Kv Tool Loop Stability · mesh-llm
    Use this skill when certifying mesh-llm KV/cache stability under repeated OpenAI tool-call loops, same-prefix cache reuse, suffix-prefill limits, or native Skippy slot/decode/eviction failures.
    4k repo stars
  10. ▌
    Plugin Web UI Extension · mesh-llm
    Use this skill when maintaining the plugin web UI projection contract, docs, exemplar coverage, or recovery flow for mesh-llm plugin web UI work.
    4k repo stars
  11. ▌
    Telemetry Privacy Review · mesh-llm
    Use this skill when adding, renaming, removing, or reviewing mesh-llm OTLP metrics, telemetry attributes, metrics exporter settings, or telemetry documentation.
    4k repo stars
  12. ▌
    Llama Stage Patch Changes · mesh-llm
    Use this skill when changing mesh-llm's patched llama.cpp Skippy ABI, runtime hooks, model introspection, tensor filtering, activation-frame execution, GGUF writer surface, upstream pin, or patch queue.
    4k repo stars
  13. ▌
    Remote Observable Process · mesh-llm
    Use this skill when starting, supervising, debugging, holding open, or stopping any remote process over SSH that needs an operator-like interactive environment, a TTY, login-shell startup files, long-running observation, logs, readiness checks, or later inspection.
    4k repo stars
  14. ▌
    Skippy Cache Family Bench · mesh-llm
    Use this skill when benchmarking Skippy exact-prefix cache across model families, comparing Skippy against llama-server, producing README benchmark tables, updating crates/skippy-cache/README.md evidence, or diagnosing cache benchmark gaps by family or Hugging Face use case.
    4k repo stars
  15. ▌
    Config Settings Management · mesh-llm
    Use this skill when adding, renaming, removing, validating, or exposing mesh-llm config settings, including built-in settings, plugin config schemas, owner-control apply behavior, CLI validation, and UI configuration surfaces.
    4k repo stars
  16. ▌
    Skippy Family Certification · mesh-llm
    Use this skill when certifying a GGUF model family for skippy stage-split serving, reviewing capability data, promoting family evidence into topology policy, or updating staged split certification docs.
    4k repo stars
  17. ▌
    Hf Bf16 Gguf Conversion Jobs · mesh-llm bundle
    Use when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the artifact to Hugging Face.
    4k repo stars
  18. ▌
    Hf Quant And Layer Package Jobs · mesh-llm bundle
    Use when running quantization of a BF16/FP16 GGUF repo and Skippy layer-package creation as one local or Hugging Face Jobs workflow, publishing both artifacts to Hugging Face.
    4k repo stars
  19. ▌
    Manage CI · mesh-llm bundle
    Use this skill as the mandatory starting point whenever inspecting, running, debugging, defining, editing, reviewing, or documenting MeshLLM CI/CD. It governs GitHub Actions workflows and local actions, triggers and routing, runners, caches, artifacts, permissions, releases, deployments, and CI infrastructure.
    4k repo stars
  20. ▌
    Mesh Join · mesh-llm
    Use this skill when creating, joining, publishing, or connecting mesh-llm nodes into a mesh — private meshes with invite tokens, the public mesh via --auto, named/published meshes, client-only nodes, NAT/firewall/bind issues, or verifying multi-node setups.
    4k repo stars
  21. ▌
    Deploy Macos · mesh-llm
    Use this skill when deploying, installing, launching, or serving mesh-llm on a macOS machine (local or remote over SSH), including installing a release, shipping a dev build bundle, codesign/quarantine fixes, choosing a model, and verifying it serves.
    4k repo stars
  22. ▌
    Skippy Bench · mesh-llm
    Use this skill when running benchmark orchestration, local single-stage or split benchmarks, benchmark report flow, or performance-oriented skippy runtime checks.
    4k repo stars
  23. ▌
    Release Notes · mesh-llm
    Use this skill when rewriting, reformatting, or reviewing the notes on a published MeshLLM GitHub release, including the automatic release-notes regrouping job, its deterministic classifier, and its optional agent review pass.
    4k repo stars
  24. ▌
    Skippy Prompt · mesh-llm
    Use this skill when running, debugging, or migrating prompt-owned skippy staged serving, including rsyncing mesh-llm source to lab nodes, building host-native skippy runtimes, choosing CUDA/ROCm/Vulkan/Metal/CPU backends, starting stage servers, attaching the binary prompt REPL, prompt history commands, speculative prompt mode, or prompt-owned process lifecycle.
    4k repo stars
  25. ▌
    Skippy Server · mesh-llm
    Use this skill when running, configuring, debugging, or embedding skippy-server, binary stage transport, OpenAI frontend integration, activation wire dtype settings, stage configs, lifecycle status, or nonblocking telemetry.
    4k repo stars
  26. ▌
    Benchmark Tune · mesh-llm bundle
    Use this skill when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing ctx/batch/ubatch/mmap/mlock/speculative-decoding sweeps, running benchmark tune on local or SSH hosts, collecting JSON evidence, and applying tolerance-aware recommendations. Trigger for requests mentioning benchmark tune, tuning tok/s, ctx_size tradeoffs, mmap or mlock tuning, speculative decoding, MTP, ngram, draft models, or replacing old gpu tune usage.
    4k repo stars
  27. ▌
    Connect Agents · mesh-llm
    Use this skill when connecting agent tools or OpenAI clients to mesh-llm — launching or configuring Goose, Claude Code, OpenCode, Pi, curl, or any OpenAI-compatible client against a local or remote mesh, picking a model, or validating tool-call reliability.
    4k repo stars
  28. ▌
    Deploy Windows · mesh-llm
    Use this skill when installing, deploying, launching, serving, or troubleshooting mesh-llm on a Windows machine — PowerShell install via install.ps1, flavor selection (CUDA/ROCm/Vulkan/CPU), source builds, the contrib helper scripts, and verifying it serves.
    4k repo stars
  29. ▌
    Metrics Server · mesh-llm
    Use this skill when working on benchmark telemetry ingest, metrics-server run lifecycle, OTLP collection, SQLite storage, benchmark report export, or separating telemetry/reporting ownership from staged runtime servers.
    4k repo stars
  30. ▌
    Skippy Metrics · mesh-llm
    Use this skill when working on skippy telemetry attributes, OTLP emission, benchmark metric names, runtime lifecycle telemetry, or separating telemetry/reporting ownership from stage runtime serving.
    4k repo stars
  31. ▌
    Deploy Linux Gpu · mesh-llm
    Use this skill when deploying, installing, launching, or serving mesh-llm on a remote Linux GPU node (rented GPUs like Vast.ai or RunPod, or a self-managed CUDA server), including installing the CUDA build, choosing a model, keeping it alive under a supervisor, and verifying it serves.
    4k repo stars