Best AI and LLM engineering skills, page 10

Launch an autonomous THINK→EXECUTE→REFLECT experiment loop on a GPU project

Xiangyue-Zhang/auto-deep-researcher-24x7

Record real OpenAI/Anthropic HTTP back-and-forth (requests + responses, including streaming text/event-stream) and print paste-ready Swift fixtures for SwiftAgent unit tests (ReplayHTTPClient) using…

SwiftedMind/SwiftAgent

Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the…

amd/skills

Mine a per-kernel optimization trace — a git repository capturing successive versions of one kernel being optimized — into structured, gate-validated optimization-experience records for the GPU…

alibaba/atrex-kernel-agent

Explains how cognee stores session memory by session_id and bridges it into the permanent graph with improve(), including the stages, results and settings.

topoteretes/cognee

Plans and audits runs of the HypoGeniC and HypoRefine packages, which propose hypotheses from labeled text datasets, with local checks before any model call.

K-Dense-AI/scientific-agent-skills

A skill your agent uses when adding support for a new model to VeOmni.

ByteDance-Seed/VeOmni

Help users create and configure openma managed agents through conversation.

openma-ai/open-managed-agents

Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…

Comfy-Org/comfy-skills

Evolve an agent harness through Gear using measured seed and held-out evaluations.

rsi-gear/gear

Adds Olakai monitoring to an existing LLM application with minimal code changes, then configures custom KPIs so the dashboard tracks business outcomes instead of just token counts.

andrewyng/context-hub

Defines practical standards for implementation-focused coding agents.

repowise-dev/claude-code-prompts

Toolbox for markerless animal pose estimation with DeepLabCut.

NeuroAIHub/BrainPilot

A skill your agent uses when handling a GitHub issue in this repository: raw issue shaping, implementability reassessment, fast/full classification, parent/child orchestration, execution snapshots…

kxn/codex-remote-feishu

A skill your agent uses for hipfire quant calibration, imatrix-driven experiments, KLD/PPL quality evaluation, k-map/format selection, MQ/HFQ/HFP/MFP tradeoff work, ParoQuant-style weight transform…

warpfront/hipfire

Weekly multi-agent audit for serious bugs (data integrity, silent caps, staleness, timestamp math, trust boundaries).

VasiHemanth/tokentelemetry

Integrate and use Jev, TypeSafe AI's System One decision model, in production codebases.

disler/ten-levels-of-jev

A skill your agent uses when writing, debugging, porting, reviewing, or optimizing CUDA C++ or PTX kernels; investigating CUDA Runtime or Driver API behavior; profiling kernels with Nsight Systems…

vipshop/cache-dit

Create cross-platform agent skills from workflow descriptions.

FrancyJGLisboa/agent-skills-platform

Dummy skill to test OpenCode TUI toast UI (and optional system notification) via caspiantesttoast.

TryCaspian/caspian-sdk

Behavioral guardrails for LLM-assisted coding. An agent skill from alirezarezvani/ClaudeForge.

alirezarezvani/ClaudeForge

Save what we just did as a reusable skill. An agent skill from IyadhKhalfallah/clauditor.

IyadhKhalfallah/clauditor

Use iDeer as a daily paper-reading workflow for chatbot-first users such as Codex, Gemini, or ChatGPT.

AI45Lab/iDeer

Add a new step under src/nemotron/steps/<category/<stepid/ — manifest (step.toml), runner glue, configs, and per-step README.md.

NVIDIA-NeMo/Nemotron

Audit an agent's context layout against the four places: system prompt, tools, history, tail.

undefined-ui/second-brain-os

使用本地 Bilibili RAG 服务进行检索与问答。用户询问 B 站收藏夹内容、视频要点总结、来源追溯、入库状态时使用。内容问答时优先通过 sessionid 与 folderids 限定范围，避免空范围导致 fallback。

via007/bilibili-rag

A skill your agent uses when building, modifying, or reviewing Phoenix LiveView tables with LiveTable, including schema-backed tables, context-owned data providers, joined queries, filters…

gurujada/live_table

A skill your agent uses when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft/m365-copilot-eval CLI.

microsoft/work-iq

Turn the current conversation's workflow into a reusable agent skill.

Undertone0809/rudder

Scaffold, wire, and verify a neocarta CLI command that wraps a source/format connector (the neocarta <source <verb integration that follows building the library connector).

neo4j-labs/neocarta

Generate, benchmark, validate, and troubleshoot LongCat-Video-Avatar 1.5 videos with draw-things-cli.

drawthingsai/draw-things-community

Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.

ModelCloud/GPTQModel

Call the free Agnes text model API for chat completions, streaming answers, coding help, tool-calling experiments, and OpenAI-compatible text generation.

kangarooking/agnes-free-model-skills

mlx-serve benchmarking methodology — bench.sh/llmprobe usage, comparison-trap rules (same-methodology cells only, spec-decode variance, thermal lies, engine naming), perf-claim etiquette.

ddalcu/mlx-serve

Analyzes a video file with Google Gemini and returns a structured markdown report covering top-level summary, scene-by-scene breakdown, audio transcript (or honest "silent" note), visual details…

mikefutia/claude-vision

Systematically reduce the shipped bundle size of a JS/TS library without sacrificing code readability or breaking consumer APIs.

kcsujeet/ilamy-calendar

Build complete, working voice agent applications using the gradbot framework.

gradium-ai/gradbot

A skill your agent uses when adding, renaming, removing, validating, or exposing mesh-llm config settings, including built-in settings, plugin config schemas, owner-control apply behavior, CLI…

Mesh-LLM/mesh-llm

Interactive click-to-segment using Segment Anything 2 — AI-assisted labeling for Annotation Studio

SharpAI/DeepCamera

Searches the web and queries premium AI models through Perplexity's own web interface, tracking quota carefully across quick, Pro and Deep Research tiers.

jacob-bd/perplexity-web-mcp

Builds AI agents on the Convex agent component: threads, messages, tools that call queries and mutations, streaming, RAG with vector search, and workflows for multi step jobs.

waynesutton/builder-skills

Optimize an AI agent's harness for MCP-Atlas benchmark. An agent skill from A-EVO-Lab/a-evolve.

A-EVO-Lab/a-evolve

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model.

JimLiu/science-skills

Interactive scaffold generator for Orloj multi-agent systems.

OrlojHQ/orloj

LLM and ML development best practices with LangChain and transformers.

meleantonio/ChernyCode

Add a new model export format to AutoRound (e.g., autoround, autogptq, autoawq, gguf, llmcompressor).

intel/auto-round

Creates a Solutions page in the QVAC documentation website from a real use case, generalizing the case into reusable guidance and registering the page in the site navigation.

tetherto/qvac

Create, track, and read team goals via Hivemind from openclaw.

activeloopai/hivemind