Search

Find skills by name, source, slug, or description across the full catalog.

Feature your product here Catalog & search unit · reach builders installing agent skills View pricing →

#

Skill

Source

Installs

design-taste-frontend nexu-io/open-design/design-taste-frontend Anti-slop frontend skill for landing pages, portfolios, and redesigns. The reads the brief, infers the right de…

nexu-io/open-design

claude-spec-interviewer stark-ai-de/-skills/claude-spec-interviewer Interview fuzzy Claude Code coding requests into user-verified implementation specs with source challenge, ADR gate, …

stark-ai-de/-skills

options-analytics--langgraph reason-machines/data-skills/options-analytics--langgraph Build AI s for real-time financial options analysis with LangGraph, ChromaDB RAG, and Polygon.io data

reason-machines/data-skills

hermes-tweet wshobson/s/hermes-tweet Install and operate Hermes Tweet, a Hermes plugin for X/Twitter research, timeline reading, tweet analysis, and…

dataset-curation wshobson/s/dataset-curation Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw da…

aws-sms-voice Official aws/-toolkit-for-aws/aws-sms-voice Onboards RCS Business Messaging and Notify OTP via the pinpoint-sms-voice-v2 AWS CLI. Covers creating a branded RCS t…

aws/-toolkit-for-aws

presentation-design jwynia/-skills/presentation-design Design and evaluate presentations that communicate effectively. Use when designing a presentation, creating slides, g…

eval-harness-first wshobson/s/eval-harness-first Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibrat…

lora-qlora-recipes wshobson/s/lora-qlora-recipes Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or revie…

-ci redwoodjs/local-ci/-ci Run GitHub Actions CI locally with CI to validate changes before pushing. Use when testing, running checks, or …

redwoodjs/local-ci

finetuning-method-selection wshobson/s/finetuning-method-selection Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretrainin…

skill-lookup f/prompts.chat/skill-lookup Search, retrieve, and install Skills from the prompts.chat registry using MCP tools. Use when the user asks to …

claude-api affaan-m/ecc/claude-api claude-api — an installable skill for AI s, published by affaan-m/ecc.

hermes-history-ingest ar9av/obsidian-wiki/hermes-history-ingest Ingest Hermes history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sess…

ar9av/obsidian-wiki

turbo-transforms goldsky-io/goldsky-/turbo-transforms Write SQL, TypeScript, and dynamic table transforms for Turbo pipelines. Covers: decoding EVM logs with _gs_log_decod…

goldsky-io/goldsky-

chrome-extension-wxt tenequm/skills/chrome-extension-wxt Build Chrome extensions using WXT framework with TypeScript, React, Vue, or Svelte.

bump-release paulrberg/-skills/bump-release Cut a release: bump versions, write changelogs, commit, tag.

paulrberg/-skills

elite-longterm-memory nextfrontierbuilds/elite-longterm-memory/elite-longterm-memory Ultimate AI memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud …

nextfrontierbuilds/elite-longterm-memory

preference-optimization wshobson/s/preference-optimization Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/…

onnx-webgpu-converter jakerains/skills/onnx-webgpu-converter Convert HuggingFace transformer models to ONNX format for inference with Transformers.js and WebGPU. Use when…

jakerains/skills

checkpoint-promotion wshobson/s/checkpoint-promotion Gate fine-tuned checkpoints with drift budgets, paired comparison, and forgetting checks before promotion. Use after …

quantized-export wshobson/s/quantized-export Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix,…

grpo-rlvr-training wshobson/s/grpo-rlvr-training Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use…

trace-to-training-data wshobson/s/trace-to-training-data Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failu…

pptx-slide-specification wshobson/s/pptx-slide-specification Use when authoring or repairing a coordinate-explicit JSON specification for an editable PPTX deck.

vision-sft wshobson/s/vision-sft Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a vis…

pptx-visual-assets wshobson/s/pptx-visual-assets Use when selecting and placing approved supporting icons, images, SVGs, diagrams, or infographics in an editable PPTX…

pptx-deck-context wshobson/s/pptx-deck-context Use when preparing the narrative, sources, and design context for a new editable PPTX deck.

spark-memory-thermal-ops wshobson/s/spark-memory-thermal-ops Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom…

spark-training-gotchas wshobson/s/spark-training-gotchas Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DG…

spark-environment-setup wshobson/s/spark-environment-setup Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing …

critical-thinking-logical-reasoning sammcj/ic-coding/critical-thinking-logical-reasoning Critically analyse the reasoning in written content (articles, blogs, transcripts, reports), not code. Use only when …

sammcj/ic-coding

pptx-reference-deck-analysis wshobson/s/pptx-reference-deck-analysis Use when analyzing a reference PPTX for read-only structure, theme, typography, layout rhythm, diagnostics, derived t…

pptx-quality-gates wshobson/s/pptx-quality-gates Use when validating or repairing an editable PPTX deck for geometry, accessibility, native editability, source lineag…

qianwen-find-skills qianwen-ai/qianwen-ai/qianwen-find-skills Discover, compare, and optionally install published Skills from QianWen. TRIGGER when: user asks to find or rec…

qianwen-ai/qianwen-ai

bump-deps paulrberg/-skills/bump-deps Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.

paulrberg/-skills

code-simplify paulrberg/-skills/code-simplify Use for simplifying recently changed code: clean up, refactor for clarity, reduce complexity, improve readability, or…

paulrberg/-skills

workflow-skill-creator google-deepmind/science-skills/workflow-skill-creator Distills a completed user workflow or interaction into a reusable skill. Use when the user asks to turn their w…

google-deepmind/science-skills

frontend-design jwynia/-skills/frontend-design Create distinctive, production-grade frontend interfaces with high design quality. Provides analysis tools for auditi…

novel-writer-cn yangsonhung/awesome--skills/novel-writer-cn 当用户需要创作、续写、修改小说，或设计角色和世界观时使用。

yangsonhung/awesome--skills

okx-a2a-payment okx/onchainos-skills/okx-a2a-payment DEPRECATED legacy alias — a2a-pay support has been merged into `okx--payments-protocol` (see `references/a2a_cha…

okx/onchainos-skills

boost goldsky-io/goldsky-/boost Configure and troubleshoot Goldsky Boost, the free RPC caching CDN in front of a provider the user already pays for. …

goldsky-io/goldsky-

merge-ready every-app/open-seo/merge-ready merge-ready — an installable skill for AI s.

every-app/open-seo

ast-grep-outline ast-grep/-skill/ast-grep-outline Use when exploring or modifying a codebase and you need a cheap structural map of files, directories, imports, export…

ast-grep/-skill

cargo-project getcargohq/cargo-skills/cargo-project Manage a whole Cargo workspace as code — declare connectors, models, plays, tools, s, MCP servers, segments, con…

getcargohq/cargo-skills

bangumi-frames s365-ai/365-skills/bangumi-frames Extract and organize frames from a Bilibili video (bangumi episode, UP upload, or a local file) into scenery shots an…

s365-ai/365-skills

correct backnotprop/pstack/correct Find the mistakes s keep repeating in this repo and make each one impossible. Try architecture first, then types…

backnotprop/pstack

requirements-analysis jwynia/-skills/requirements-analysis Diagnose requirements problems and guide discovery of real needs and constraints

ce--native-architecture everyinc/compound-engineering-plugin/ce--native-architecture Build applications where s are first-class citizens. Use this skill when designing autonomous s, creating M…

everyinc/compound-engineering-plugin

impl-validator ar9av/obsidian-wiki/impl-validator Validate whether an implementation matches its stated goal. Use this skill when a skill or wants a second opini…

ar9av/obsidian-wiki