rvDNA — genomic substrate for ruLake. Adds the rvdna-mcp wire (5 tools: find, call_variants, translate, score, lineage) plus 5 slash commands. v0.0.1 ships witnessed stubs; the RaBitQ inner loop, variant index, and codon table land in v0.1.
Plugin rulake-rvdna from marketplace rulake-marketplace in ruvnet/RuLake. Commands read from the repo's manifest — yesterday.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
/rulake-rvdna:rvdna-call-variantsrvDNA T0 — variant calls for a region in a pinned collection. Returns whatever variants the registered RVDNA file's VariantTensor section holds for the region. Empty array if no variant data registered (genuine answer, not a stub). Witness-anchored.
/rulake-rvdna:rvdna-findrvDNA T0 — real brute-force L2 kNN over a pinned genomic collection. Returns a witnessed bundle pointer plus the matching segments. Deterministic; ties broken by lower id (matches the ADR-157 kernel-conformance contract).
/rulake-rvdna:rvdna-lineagervDNA — internal capability tier. Reveals lineage / provenance metadata for a registered rvDNA collection (e.g. assembly version, source URI, build epoch). Gated by --capabilities internal.
/rulake-rvdna:rvdna-scorervDNA T0 — deterministic FNV-1a score in [0.0, 1.0] over (witness, region). Region-sensitive, witness-sensitive, reproducible across operators. Production scorer model wires here in v0.2.
/rulake-rvdna:rvdna-translatervDNA T0 — real codon-table DNA → protein translation. Standard genetic code (64 codons → 20 amino acids + 3 stop codons). Case-insensitive, skips Ns + whitespace, stops at first stop codon. Witness-anchored.
rvdna-mcpruns: rvdna-mcp stdio --demo-collection --capabilities read,internal
Killer-path install: bundles rulake-core + rulake-substrates + rulake-witness with the deterministic retrieval path enabled and kernels off by default. The 90% case — one command gets retrieval working end-to-end.
8 commands · 3 MCP servers
Self-learning, self-optimizing agentic memory. Wraps the witness-anchored ruLake cache as a working-memory surface — remember/recall/forget verbs, hit-ratio tuning, drift detection, audit-driven optimization. Memory that gets faster the more it's used.
1 skill · 8 commands
ruQu — quantum simulation substrate for ruLake. Adds the ruqu-mcp wire (5 tools: simulate, verify, replay, optimize, qec_schedule) plus 5 slash commands. Picks the right backend (StateVector / Stabilizer / TensorNetwork / Hardware-stub) per circuit.
5 commands · 1 MCP server
The eight rulake_* MCP tools and the rulake_query decision layer plus /rulake-discover advisory tool. Wires to the live demo at https://rulake-mcp.ruv.io/ by default; switch to stdio for production.
1 skill · 2 commands
ADR-157 accelerator plane: AVX-512 host SIMD and wgpu portable GPU. Off-by-default; operator opt-in. Includes /rulake-kernel-status and /rulake-kernel-bench commands.
2 commands
SHAKE-256(32) bundle verification and witness viewer CLI. /rulake-verify and /rulake-bundle-info commands.
2 commands
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Install the "AAS Data Analytics & Business Intelligence" workflow plugin from Agentic Awesome Skills.
16 skills
Databricks skills for the CLI, Apps, Lakebase, Model Serving, Lakeflow Jobs, Spark Declarative Pipelines, Declarative Automation Bundles (DABs), and classic-to-serverless migration.
37 skills · 2 commands · hooks
The official CCXT MCP server plus the ccxt-mcp usage skill — market data, balances and opt-in trading across 100+ crypto exchanges and prediction markets, with keys kept local.
1 MCP server
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.