LLM skills

9,717 tagged LLM, measured the same way as everything else here.

Browse within: agent 494chatgpt 237agents 208cli 167bun 133ml 133javascript 124agent-framework 122openai 115agentic-ai 114deep-learning 107openclaw 99foundation-models 98open-source 93

kayba-ace

73

kayba-ai/agentic-context-engine

Skill Claude CodeCodex

This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.

not rated 2.6k +3 10d ago A SkillSpector: warn 0 tokens original Apache-2.0

agentfield-use

74

Agent-Field/agentfield

Skill Claude CodeCodex

Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …

not rated 2.6k +6 yesterday A SkillSpector: warn 259 tokens original Apache-2.0

add-icon-mapping

75

lobehub/lobe-icons

Skill Claude CodeCodex needs its repo

Add or modify icon keyword mappings for providers, models, or agents in lobe-icons. Use this whenever a task involves mapping a provider/model id to an icon, adding a new entry to ModelProvider enum or providerMappings/modelMappings/agentMappings, or fixing a provider/model that renders the fallback (default) icon in…

not rated 2.5k +19 3d ago A SkillSpector: warn 111 tokens original MIT

UnicomAI/wanwu

Skill Claude CodeCodex

Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.

not rated 2.5k +8 4d ago A SkillSpector: warn 65 tokens original Apache-2.0

data-designer

77

NVIDIA-NeMo/DataDesigner

Skill Claude Code

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

not rated 2.2k +2 yesterday A 25 tokens copy · 100% Apache-2.0

karpathy-llm-wiki

78

Astro-Han/karpathy-llm-wiki

Skill Claude CodeCodex

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

5 · 1 2.2k +49 1mo ago A 67 tokens original MIT

claude-real-video

79

HUANGCHIHHUNGLeo/claude-real-video

Skill Claude Code

Watch a video for the user. Use when the user shares a video URL (YouTube etc.) or local video file and wants it summarized, analyzed, or discussed — Claude can't ingest video directly, so this skill extracts scene-aware keyframes + transcript first, then reads those.

not rated 2.1k +21 8d ago A Socket: passSnyk: warnSkillSpector: pass 61 tokens original MIT

neuron-core/neuron-ai

Skill Claude CodeCodex

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

not rated 2.1k +10 yesterday A SkillSpector: pass 77 tokens original MIT

Web2Skill

81

zhimaAi/chatwiki

Skill Codex

Convert one public website URL or an explicit batch of public URLs into a reusable skill zip backed by rendered HTML snapshots and a bounded JSONL retrieval index. Use to discover a documentation directory from one URL, crawl a supplied URL set sequentially, generate a source profile, or package indexed web content as…

not rated 2.1k +2 4d ago A SkillSpector: pass 67 tokens

benchmark-design

82

Prism-Shadow/penguin-harness

Skill Claude CodeCodex

Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.

not rated 2.0k +126 changed 3d ago A SkillSpector: warn 22 tokens original Apache-2.0

dynamic-workflow

83

pchalasani/claude-code-tools

Skill Codex

Create, review, run, inspect, pause, resume, and cancel durable JavaScript workflows that coordinate multiple headless Codex agents. Use for dynamic fan-out and fan-in, per-item analysis, multi-stage agent pipelines, loops or branches driven by worker results, long background runs, and ports of Claude Code dynamic…

not rated 2.0k +5 yesterday A SkillSpector: pass 86 tokens original MIT

BidingCC/BuildingAI

Skill Claude CodeCodex

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.

not rated 1.9k +6 18d ago A SkillSpector: warn 31 tokens original Apache-2.0

background-task

86

vstorm-co/full-stack-ai-agent-template

Skill Claude Code

Add or modify work that runs outside the request/response cycle — emails, document ingestion, webhooks, cleanups, scheduled jobs. Use when something is slow or fire-and-forget, or when adding a periodic/cron task. This project's queue is {{ cookiecutter.backgroundtasks }}.

not rated 1.9k +17 4d ago A SkillSpector: pass 62 tokens original MIT

stripe/ai

Skill Claude CodeCodex ✓ vendor

Use this skill when the user asks what information a Stripe Connect connected account must provide for verification, onboarding, KYC, or account requirements; when they need to compare requirements between connected-account setups; or when they ask which verification fields, documents, or business details are required…

not rated 1.8k +10 4d ago A Socket: passSnyk: warnSkillSpector: warn 80 tokens original MIT

quality-loop

89

trpc-group/trpc-agent-go

Skill Claude CodeCodex

Use this workflow recipe when a draft, plan, proposal, or other deliverable should be independently reviewed and revised until it satisfies explicit quality criteria.

not rated 1.8k +7 today A SkillSpector: pass 32 tokens original Apache-2.0

dcf-model

90

ginlix-ai/LangAlpha

Skill Claude CodeCodex needs its repo

DCF valuation: free cash flow projections, WACC, terminal value, sensitivity analysis.

not rated 1.7k +8 today A SkillSpector: warn 20 tokens original Apache-2.0

docs-manage

91

arabold/docs-mcp-server

Skill Claude CodeCodex

Manage the Grounded Docs MCP Server documentation index. Covers scraping and indexing documentation from URLs or local files, refreshing existing indexes with changed content, and removing libraries from the index. Use when you need to add, update, or delete indexed documentation.

not rated 1.7k +16 10d ago A SkillSpector: warn 53 tokens original MIT

smart-docs

92

sopaco/deepwiki-rs

Skill Claude Code needs its repo

AI-powered comprehensive codebase documentation generator. Analyzes project structure, identifies architecture patterns, creates C4 model diagrams, and generates professional technical documentation. Use when users need to document codebases, understand software architecture, create technical specs, or generate…

not rated 1.7k +5 25d ago A SkillSpector: pass 80 tokens original MIT

meeting-prep

93

ShenSeanChen/waku-agent

Skill Claude CodeCodex

Prep me for a meeting or call — who I'm meeting, background, talking points. Use for "prep me for", "get me ready for", "what should I know before", "who am I meeting", "brief me on my call with".

not rated 1.7k +49 10d ago A SkillSpector: pass 55 tokens original MIT

dws

94

Pinvou/pinvou-agent

Skill Claude CodeCodex

A command-line guide for DingTalk, a workplace platform with chat, documents, calendars, approvals, tasks, and other business tools.

not rated 1.7k +106 changed today A SkillSpector: pass 187 tokens original MIT

spec-init

95

legeling/PromptHub

Skill Codex

A documentation-first workflow for starting or improving a software project’s specifications and development records.

not rated 1.6k +12 3d ago A SkillSpector: pass 73 tokens AGPL-3.0

newsletter

96

masamasa59/ai-agent-papers

Skill Claude Code

Write a monthly trend newsletter for this ai-agent-papers repo. Use when asked to create/update a monthly trend report, summarize a category's recent papers, or "make a newsletter". Encodes the house procedure: cover every coherent category with enough papers that month (no fixed number of issues; overlap between…

not rated 1.6k +6 9d ago A SkillSpector: pass 120 tokens

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: