AI Skills
Installable SKILL.md packages that extend AI coding agents with reliable workflows and domain-specific judgment — ranked by installs, sourced from skills.sh.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
watch
Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
phoenix-evals
Build and run evaluators for AI/LLM applications using Phoenix.
lint-and-validate
MANDATORY: Run appropriate validation tools after EVERY code change. Do not finish a task until the code is error-free.
adev-writing-guide
Comprehensive writing guide for Angular documentation (adev). Covers Google Technical Writing standards, Angular-specific markdown extensions, code blocks, and components. You MUST use this skill any time you plan to create, edit, or review documentation files in `adev/` or `adev/src/content`.
apollo-router-plugin-creator
>
content-optimization
When the user wants to optimize content for SEO—word count, H2 keywords, keyword density, multimedia, tables, lists. Also use when the user mentions "content length," "word count," "keyword stuffing," "H2 keywords," "keyword density," "tables," "bullet points," or "content structure." For keywords, use keyword-research.
analytics-tracking-automation
AI-powered GA4 + GTM event tracking automation — analyzes sites, designs event schemas, syncs GTM containers, runs preview verification, and publishes tracking implementations.
nemo-automodel-distributed-training
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
agent-ops-cicd-github
Agent skill for ops-cicd-github - invoke with $agent-ops-cicd-github
sf-industry-commoncore-integration-procedure
>
generative-engine-optimization
When the user wants to optimize for AI search visibility (ChatGPT, Claude, Perplexity, AI Overviews). Also use when the user mentions "GEO," "AEO," "generative engine optimization," "AI search visibility," "LLM optimization," "GitHub GEO," "Grokipedia," "optimize for ChatGPT," "AI Overviews," "Bing Copilot," "Yandex AI," "Perplexity optimization," "GEO strategy," or "AI search optimization." For third-party publishing strategy (which platforms to use), use parasite-seo. For GitHub repos, README, and Awesome lists, use github. For Medium.com only, use medium-posts. For Grokipedia edits, use grokipedia-recommendations. For traditional Google SERP strategy, use seo-strategy.
cpq-builder
>
data-engineering-study-material
Comprehensive study guide covering data engineering concepts, tools, and best practices for learning and reference
cs-note
把"短到不值得起一份文件、但 AI 每次启动 CodeStable 技能都必须知道"的项目碎片知识追加到 `.codestable/attention.md` 的固定分节里——比如编译特殊 flag、运行前要先起的服务、路径陷阱、命令别名、环境变量约定。触发：用户说"记一笔"、"加到 attention.md"、"项目要 X 才能编译"、"以后每次都得 Y"，或刚踩到一个一句话能讲清的项目特殊设置。
flags
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.
nemotron-retrieval-recipes
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
reference-compiler-cli
Explains the mental model and architecture of the code under `packages/compiler-cli`. You MUST use this skill any time you plan to work with code in `packages/compiler-cli`
sf-datacloud-connect
>
built-in-metrics
Instrument an existing codebase with LaunchDarkly config tracking. Walks the four-tier ladder (managed runner → provider package → custom extractor + trackMetricsOf → raw manual) and picks the lowest-ceremony option that still captures duration, tokens, and success/error.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
faceswap
|
sf-datacloud-prepare
>
agent-coordination
>
embeddings
>
altimate-data-engineering-skills
Claude Code skills for analytics and data engineers working with dbt, Snowflake, and data pipelines
safe-action-hooks
Use when executing next-safe-action actions from React client components -- useAction, useOptimisticAction, handling status/callbacks (onSuccess/onError/onSettled), execute vs executeAsync, or optimistic UI updates
find-models
Find AI models on Replicate using search and curated collections.
typography-scale
Create a modular typography scale with size, weight, and line-height relationships.
layers-observed-behaviour
Techniques for planning user research and synthesising it into grounded, confidence-rated findings about what users actually do