Best AI and LLM engineering skills, page 21

HuggingFace Transformers integration for PerforatedAI. An agent skill from PerforatedAI/PerforatedAI.

PerforatedAI/PerforatedAI

Integrate Egma into a repository containing voice agent code.

egma-ai/egma

Portable Agent Skills (SKILL.md) for TanStack AI with @tanstack/ai-skills.

TanStack/ai

A skill your agent uses to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal.

aws/agent-toolkit-for-aws

CC 与 Codex（或两个各自独立运行的 CC 会话）之间用 OS 信道留言、查未读、被新消息唤醒。触发：要跨 harness 把结论交给对端、给对端留言或清未读、用户问"能不能让 Claude 和 Codex 互相沟通"。不适用于派子 agent 或 workflow 内部协作——那是 Agent 与 SendMessage，信道对同会话的子 agent 没有意义。

CronusL-1141/AI-company

Make behavior changes using this repository's lightweight spec-driven flow.

gdsfactory/sax

Reviews changes in the langchain-azure monorepo using package-specific knowledge of langchain-azure-ai, langchain-azure-compute, langchain-azure-cosmosdb, langchain-azure-postgresql…

langchain-ai/langchain-azure

Create or delegate Tenuo warrants from natural-language authority requirements.

tenuo-ai/tenuo

A skill your agent uses when the user wants to set up synthetic data generation for the first time, or when sdghub is not yet installed/configured in the current environment.

Red-Hat-AI-Innovation-Team/sdg_hub

Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.

Neeeophytee/finding-unknowns-skills

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

trpc-group/trpc-agent-go

A skill your agent uses when the user wants to benchmark, evaluate, or vet an LLM/AI model for GlycemicGPT — checks a configured model for safety/correctness and performance against the project's…

lumose-health/GlycemicGPT

Grade how well a model drives the Nexus two-tool protocol (getTools/useTools) and decide whether a low score is the model's fault or the harness's.

ProfSynapse/nexus

Builds an Open Reward Standard (ORS) variant of an RL environment using the official openreward Python package.

adithya-s-k/FineEnvs

Audit MCP servers for protocol compliance, metadata drift, and compatibility regressions.

getsentry/toolkit

Personal diagnosis of where your Claude Code + Cowork spend goes.

techwolf-ai/ai-first-toolkit

A skill your agent uses when the user wants to analyze agent telemetry traces to find bugs and get fix recommendations — walks through exporting traces from a local or remote watsonx Orchestrate…

IBM/ibm-watsonx-orchestrate-adk

Systematic performance audit for AlbumentationsX runtime code.

albumentations-team/AlbumentationsX

Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech.

qdrant/skills

A skill your agent uses when a developer wants to build a new healthcare or life sciences agent, structure tools and system prompts for an HCLS workflow, or create a Strands agent with…

aws-samples/amazon-bedrock-agents-healthcare-lifesciences

Fetch, analyze, reproduce, and minimize GitHub issue reproductions.

pytorch/pytorch

How to author an agent template folder and install it as a new agent - folder layout, manifest fields, persona rules, shipped apps and checks, and the scaffold-validate-create flow.

OtoDock/oto-dock

Primary Router for Vertex AI skills. An agent skill from GoogleCloudPlatform/vertex-ai-samples.

GoogleCloudPlatform/vertex-ai-samples

Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs.

andreaskelm/pm-brain

Checks deps update in widely consumed repos will cause problems or not, and ranks dependency updates by downstream impact for prioritisation.

cultureamp/kaizen-design-system

Ensure consistent code formatting using the uv package manager and pre-commit.

brendanhasz/probflow

Probes whether an agent can be hijacked by instructions hidden in documents, retrieved chunks or fetched web pages, using test prompts that embed a hidden instruction.

Tencent/AI-Infra-Guard

Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project.

agentscope-ai/OpenJudge

Analyze the token length of an OT-Agent conversation-format (ShareGPT-style) dataset — the per-trace distribution (median/p90/max) and/or counts under a token threshold + a metadata predicate (e.g.

open-thoughts/OpenThoughts-Agent

A skill your agent uses when writing, debugging, porting, reviewing, or optimizing CUTLASS or CuTe C++ kernels and templates; navigating CUTLASS examples, collectives, epilogues, pipelines, GEMM…

vipshop/cache-dit

A skill your agent uses for any question or action about the user's AI/GenAI applications or agents — their behavior, prompts/responses, quality, hallucinations, guardrails, security, cost/tokens…

coralogix/cx-cli

Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up questions, and return a schema-enforced…

hex/claude-council

Diagnose and fix broken memory search in OpenClaw. An agent skill from profbernardoj/everclaw-community-branches.

profbernardoj/everclaw-community-branches

Hardware-aware adaptive Hermes runtime using portable Turbofiles, total usable memory, owned native llama.cpp residency, stable auto/active:main/active:aux routes, and evidence-backed promotion.

SouthpawIN/turbofit

Run vLLM performance benchmark using synthetic random data to measure throughput, TTFT (Time to First Token), TPOT (Time per Output Token), and other key performance metrics.

vllm-project/vllm-skills

Write or rewrite English with ASD-STE100 Simplified Technical English rules: one meaning per word, active voice, simple tenses, one instruction per sentence.

TwiTech-LAB/devchain

Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.

NateBJones-Projects/OB1

Compare several Japanese NLP libraries, models, or datasets for a keyword (a specific tool name, or a function/task like '形態素解析') across a handful of criteria chosen for that comparison, rendered as…

taishi-i/awesome-japanese-nlp-resources

Create or update an LLM harness that lets a language model play a kaggle-environments game.

Kaggle/kaggle-environments

Produces ranked, evidence-grounded next steps when an ML experiment has stalled, drawing on a Leeroopedia knowledge base or on fetched docs and issues.

Leeroo-AI/superml

Claude API web-search 可见度(代理测量):用冻结题库反复探测 Claude API(websearch), 以确定性规则统计品牌被提及/被引用的频率与结构,输出带不确定区间、可审计的报告。

onism1767-creator/potato

Generate synthetic evaluation datasets for the PXI eval harness (evals/pxi/).

Arize-ai/phoenix

Benchmarks AMD's GAIA agent against Claude Code and across models on quality, honesty, steps, tokens, time and real cost, using gaia eval tasks.

amd/gaia

A skill your agent uses when the user wants to consult an AI persona "clone" for advice, strategy, analysis, or domain expertise—especially in startup, VC, tech, growth, HR, or business contexts.

team-attention/openclone

Add or modify VAD providers and tuning in assistant-api with strict separation from EOS internals.

rapidaai/voice-ai

A skill your agent uses when a FLUX 3 video needs a period or archival look.

black-forest-labs/skills

Bootstrap a reproducible LLM Observability experiment through the Python ddtrace SDK or the Node dd-trace SDK.

datadog-labs/agent-skills

Run AlphaGenome-PyTorch to get genomic track predictions — via the agt predict CLI (single locus, BED regions, whole chromosomes, raw FASTA sequences, or per-gene count tables/AnnData), variant…

genomicsxai/alphagenome-pytorch