Build an OKF (Open Knowledge Format) knowledge base from any YouTube channel. Uses Google's OKF standard so any AI can read the output with zero setup. Uses Supadata (managed API, paid). Invoke with /channel-to-kb-supadata @ChannelHandle.
Bulk-import a large RDF graph (code graph, corpus, GitHub history, etc.) into a DKG node's working memory. Use this skill when you need to push more than a few thousand triples in a single import — it codifies the chunking budgets, the assertion-loop shape, the resumability manifest, and the canonical URI rules so…
Profile, benchmark, debug, and optimize AI training workloads on Moore Threads MUSA GPUs while preserving numerical behavior. Use for Torch MUSA, MTT GPUs, mthreads-gmi, Moore Perf System (msys), Moore Perf Compute (mcu), MFU/HFU, FlashAttention/FA2, SDPA, torch.compile, FSDP/FSDP2, MCCL, distributed hangs, low-batch…
A runbook for replaying past data through Dagster pipelines, which are scheduled workflows for processing data. It describes how to use the project’s `dg launch` commands and shared backfill jobs.
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of…
This skill provides guidance for implementing tensor parallelism in PyTorch, specifically column-parallel and row-parallel linear layers. Use when implementing distributed neural network layers that split weights/activations across multiple ranks, working with torch.distributed for model parallelism, or implementing…
Use whenever the user mentions cachedtokens=0,totalcachedtokens,cachereadinputtokens,cachecreationinputtokens,cachewritetokens,promptcachekey,promptcacheoptions,promptcachebreakpoint,previousinteractionid,cachecontrol/cachePoint,TTFT,KV reuse…
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
Use for any task involving the ledidi library — gradient-based design of minimal edits to categorical sequences (DNA/RNA/protein) so that a frozen oracle model predicts a desired output. Triggers on designing or editing a sequence, inserting or knocking out a motif or binding site, hitting a target model output, cell…
A skill for analyzing images with several external vision models. It is activated only when a user starts a request with /skill luma-vision and includes an image.
Guide for using KimiX API utilities covering kimix, kimix.utils, kimix.base, kimix.dag, kimix.network, kimix.server, kimix.parser, kimix.cot, kimix.retrieval, kimix.summarize, and kimiagentsdk.
Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.
A check for whether an API is really serving a Claude model rather than a model with an unclear source or a third-party wrapper. It can run quick checks and, when needed, a deeper review of identity, tools, metadata, and nested responses.
Generate OKF (Open Knowledge Format) v0.2 knowledge bundles from codebases, and look up exact concepts for AI agent context injection. Use this skill whenever the user wants to: index a codebase, generate OKF bundles, extract code knowledge into structured markdown, convert codebases into training data, look up…
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.
Use this skill whenever the user asks to generate, collect, inspect, or prepare early-experience training data (Implicit World Modeling or Self-Reflection, in the sense of arXiv:2510.08558) for an agent environment. Trigger phrases include "rollout", "collect expert trajectories", "generate reflection", "smoke test…
Technical guidance for recognizing human actions in video without training a new machine-learning model or using an LLM. It describes a pipeline that samples video frames, estimates body poses, measures movement, and assigns labels with rules.
Train a custom YOLO object detection model from any YouTube gameplay video. Provide a video URL and target classes, and this skill handles the entire pipeline autonomously — frame extraction, AI-powered labeling, data augmentation, training, and evaluation with iterative improvement.
Default path for any cloud training work in Dat. Use this skill whenever a task needs cloud training, GPU training, model fine-tuning, training evaluation, long-running training compute, or hosted training job orchestration. Also use it to submit prepared packages, handle approval/session handoff, track jobs, cancel…
Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: