LLM skills

9,702 tagged LLM, measured the same way as everything else here.

Browse within: agent 497chatgpt 225agents 208cli 169ml 133bun 132javascript 124agent-framework 120openai 117agentic-ai 116deep-learning 107foundation-models 98open-source 93agentskills 90

writing-great-skills

337

fastagent-sh/fastagent

Skill Claude Code

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

not rated 62 +4 yesterday A 24 tokens copy · 100% MIT

video-gen

338

TGYD-helige/pi

Skill Claude CodeCodex

Video creation and local composition: join existing clips or render mixed image/video timelines with videocompose, generate one AI clip with videogenerate, or make a multi-shot AI film with videorender. Use when the deliverable is a video. Do NOT use for still images (use pi-image-gen directly).

not rated 62 +3 changed 3d ago A SkillSpector: pass 64 tokens original Apache-2.0

delphi-uses-graph

339

MaxiDonkey/DelphiAnthropic

Skill Claude CodeCodex

Analyzes a Delphi / Object Pascal codebase to extract unit-level uses dependencies. Use when the user uploads a zip / archive of a Delphi project (or a folder of .pas / .dpr / .dpk files) and asks for a dependency graph, architecture map, cycle detection, fan-in / fan-out coupling analysis, or wants to know how units…

not rated 60 4d ago A 124 tokens original MIT

find-awesome-tools

340

bh-rat/context-awesome

Skill Claude CodeCodex

Discovers curated tools, libraries, frameworks, and resources across thousands of awesome-lists. Use this skill whenever the user is shopping for options in a technology space — "what are good Rust CLI argument parsers", "recommend React state management libraries", "popular Python web frameworks", "tools for building…

not rated 59 3mo ago A 195 tokens original MIT

database

341

bug-ops/zeph

Skill Claude CodeCodex

Query and manage SQLite, PostgreSQL, and MySQL databases from the command line. Use when the user asks to run SQL queries, inspect database schemas, create or alter tables, import or export data, manage indexes, analyze query performance with EXPLAIN, back up or restore databases, or perform CRUD operations via…

not rated 59 +1 2d ago A SkillSpector: pass 76 tokens original MIT

ocm-browser

342

mathaix/OpenClawMachines

Skill Claude CodeCodex

Drive a browser from an OpenClaw machine. Companion to the browser-harness skill — explains the OCM-specific bridge proxy, the readiness check you must run first, and how pairing works. Start here before writing any browser code.

not rated 57 1mo ago A SkillSpector: pass 51 tokens original Apache-2.0

join-buyer

343

AntSeed/antseed

Skill Claude CodeCodex

Help the user set up an AntSeed buyer node to consume AI services from the peer-to-peer network. Walk them through installation, funding, and connecting their existing tools (Aider, Continue.dev, Cursor, or any OpenAI-compatible client) through the local proxy.

not rated 57 yesterday A 0 tokens GPL-3.0

MIMIFY/skill_everyone

Skill Claude Code

A perspective tool based on Princess Zelda from The Legend of Zelda: Breath of the Wild and Tears of the Kingdom. It applies her fictional values and reasoning style to real-world questions, rather than role-playing her directly.

not rated 57 +2 5mo ago A 114 tokens original MIT

agenta

345

diegosouzapw/awesome-omni-skill

Skill Claude CodeCodex

LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted solution.

not rated 57 6mo ago A 36 tokens

loop-engineering

346

invincible04/awesome-loop-engineering

Skill Codex

Design and scaffold an autonomous "loop" around a coding agent for a recurring workflow. Use when the user wants to stop hand-prompting an agent and instead build a system that discovers work, delegates it to a maker, verifies the result with a separate checker, remembers progress on disk, and re-runs until a goal is…

not rated 56 +1 2mo ago A 150 tokens original MIT

octave-literacy

347

elevanaltd/octave-mcp

Skill Claude Code

LLM-native structured communication format. Teaches OCTAVE syntax rules, canonical forms, and warning prevention for zero-error .oct.md authoring.

not rated 55 2mo ago A 34 tokens original Apache-2.0

byok-relay

348

avikalpg/byok-relay

Skill Claude CodeCodex

OpenAI-compatible LLM gateway for any client-side application (browser, mobile, React Native, Flutter, VS Code extensions, browser extensions, Electron, smart TV, and more). Routes requests to OpenAI, Anthropic, Gemini, Groq, Mistral, and 200+ models, handling CORS, key encryption, and streaming without a dedicated…

not rated 55 +1 yesterday A SkillSpector: warn 131 tokens original Apache-2.0

tricorder-cli

349

tweag/tricorder

Skill Claude Code

Full CLI reference for the tricorder daemon (build diagnostics, test results, source lookup, eval comments, logs). This is the fallback invoked by the tricorder skill when the tricorder-mcp MCP tools aren't available or aren't working — invoke tricorder first; it decides whether this is needed.

not rated 55 yesterday A 67 tokens

docs

350

TelivityAI/careerops

Skill Claude CodeCodex

Public-facing skill docs. Full mode prompts live in .agents/skills/careerops/.

not rated 54 +1 2d ago A SkillSpector: warn 0 tokens original Apache-2.0

cubepi-trace

351

cubeplexai/cubepi

Skill Claude CodeCodex

Use when debugging a cubepi/cubebox agent run — a missing final reply, a tool that misbehaved, a 4xx from the model, wrong token/cache numbers, or "why did the agent do that?". Reads the JSONL traces cubepi writes per run via the cubepi trace CLI (ls / view / follow / stats) to inspect the span tree, errors, tool…

not rated 54 +11 5d ago A SkillSpector: warn 129 tokens original MIT

lx

352

rasros/lx

Skill Claude CodeCodex

Codebase exploration tool that reads many files or whole directories in a single call, with per-file headers, glob include/exclude filters, function/type skeleton extraction (signatures only, no bodies), and head/tail line slicing.

not rated 53 11d ago A SkillSpector: pass 48 tokens original MIT

code-review

353

Miosa-osa/OSA

Skill Claude CodeCodex

Analyze pull requests and diffs for bugs, security vulnerabilities, performance issues, style violations, and test coverage gaps — producing structured, actionable feedback.

not rated 53 +2 yesterday A 31 tokens

claim-audit

354

Mexregkan/claude-for-researchers

Skill Claude Code

Audit what a passing script actually established, before writing any prose about it — build the computed-object ledger, rewrite every check's label as the weakest statement that makes its body pass, and separate the verdict on someone else's work from your own new claim. Run after the script passes and BEFORE the…

not rated 52 7d ago A SkillSpector: pass 75 tokens original MIT

skill-creator

355

CherryHQ/stella

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 50 yesterday A 64 tokens AGPL-3.0

vault-for-llm

356

zycaskevin/Vault-Agent-Memory

Skill Claude CodeCodex

Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.

not rated 50 +1 14d ago A SkillSpector: pass 46 tokens original Apache-2.0

web-components

357

AdamBien/airails

Skill Claude Code needs its repo

Architecture and coding rules for single-page applications using web components, BCE layering, lit-html templating, unidirectional Redux-style state management (reduction.js, standards-based), and standards-based client-side routing (Navigation API + URLPattern). Web standards and web platform first, minimal external…

not rated 50 +2 changed 3d ago A SkillSpector: warn 160 tokens original MIT

js-gof

358

metarhia/metaskills

Skill Claude CodeCodex

Apply Gang of Four and related design patterns in JavaScript and TypeScript. Use when implementing creational, structural, or behavioral patterns, or when the user mentions factories, builder, prototype, flyweight, singleton, object pool, adapter, wrapper, decorator, proxy, bridge, composite, facade, chain of…

not rated 49 +1 1mo ago A SkillSpector: pass 107 tokens original MIT

omniseek-investigate

360

Battam1111/omniseek

Skill Claude CodeCodex

Deep-investigation methodology for OmniSeek. Sweep in parallel with omniseekgather, judge the signals, zoom through walled sources, structure the evidence, and close with an explicit gap ledger.

not rated 49 +1 yesterday A SkillSpector: pass 46 tokens original Apache-2.0

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: