LLM skills

9,876 tagged LLM, measured the same way as everything else here.

Browse within: agent 502chatgpt 227agents 211cli 169ml 133bun 129javascript 124agentic-ai 122openai 118agent-framework 116deep-learning 107foundation-models 98agentskills 90cortex 90

log-analyze

481

fossuav/aap

Skill Claude Code

Analyze ArduPilot DataFlash .bin log files or MAVLink .tlog telemetry logs. Use when the user provides a .bin or .tlog log file path or asks to analyze flight log data.

not rated 19 changed yesterday A 46 tokens GPL-3.0

tolato

482

momaek/tolato

Skill Claude CodeCodex

Inspect and operate servers managed by a Tolato instance using the tolato CLI. Use when the user asks about their VPS fleet, wants to check a server's status or metrics, or wants to run a shell command on a remote node they manage through Tolato.

not rated 19 +1 2d ago C 58 tokens original Apache-2.0

deslop

483

fayerman-source/deslop

Skill Claude CodeCodex

Audits and rewrites legal writing, professional documentation, and general text to follow plain English principles. Translates archaic legalese and eliminates verbose "AI slop" by enforcing active voice, subject-verb proximity, and concise phrasing (inspired by Bryan Garner, the SEC Plain English Handbook, Federal…

not rated 19 +1 11d ago A 85 tokens original MIT

crisp

484

shubhamV123/crisp

Skill Claude CodeCodex

Use this skill when the user wants shorter, more direct responses. Activate on: "crisp mode", "go crisp", "/crisp", "be brief", "less tokens", "cut the fluff", "shorter answers", "stop being verbose", "drop the filler", "skip the pleasantries", "no fluff", "just the answer". Do NOT activate for: "explain in detail"…

not rated 18 3mo ago A 109 tokens original MIT

engram-memory

485

staticroostermedia-arch/engram

Skill Claude CodeCodex

Engram geometric memory for AI agents — slash commands map decision moments to MCP rituals. You are the primary user. Lean highway + power escalation.

not rated 18 1mo ago A 33 tokens AGPL-3.0

anything-to-md

486

1596941391qq/anything-to-md

Skill Claude CodeCodex

Universal document to Markdown converter. Convert any file (PDF, Word, Excel, PPT, images, audio, video, YouTube URLs) to clean LLM-ready Markdown. Use when: User wants to convert documents to Markdown User needs to process entire directories of files User has YouTube videos or audio files to transcribe User wants to…

not rated 18 4mo ago A 265 tokens copy · 100% MIT

android-use

487

iurysza/android-use

Skill Claude Code

Control Android devices via ADB. Use when user asks to tap, swipe, type, launch apps, take screenshots, or automate Android device interactions.

not rated 18 7mo ago C 33 tokens original MIT

stream-flutter

488

GetStream/agent-skills

Skill Claude Code

Build and integrate Stream Chat, Video, and Feeds in Flutter apps. Use for Flutter/Dart project work with Stream package setup, auth wiring, and widget blueprints. Supports streamchatflutter (pre-built Chat UI), streamchatfluttercore (custom Chat UI), streamvideoflutter (Video calling and livestreaming), and…

not rated 18 11d ago A SkillSpector: warn 112 tokens original Apache-2.0

skill-adaptor

489

zjunlp/SkillAdaptor

Skill Codex

Run SkillAdaptor to evolve agent skills from task failures. Use when improving SKILL.md files from trajectories or after benchmark runs.

not rated 18 1mo ago A 29 tokens original MIT

faf-expert

490

Wolfe-Jam/grok-faf-mcp

Skill Claude CodeCodex

Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.

not rated 18 4d ago A SkillSpector: warn 69 tokens original MIT

clumsies

491

lilhammerfun/clumsies

Skill Claude CodeCodex

Use Clumsies in a bound project to retrieve relevant Memory, including project-maintained skills and procedures. Use for substantive project tasks when the Clumsies memory MCP tool is available; skills stored in Memory remain ordinary project guidance.

not rated 18 +1 yesterday A 50 tokens original MIT

channel-telegram

492

moshthepitt/lionclaw

Skill Claude CodeCodex

Run and operate a Telegram channel worker for LionClaw using the kernel channel bridge APIs.

not rated 16 11d ago A SkillSpector: pass 22 tokens original MIT

tasks

493

hypercycle-development/mosaic-companion

Skill Claude Code

Manage your task list — add, complete, list, and prioritize tasks stored in TASKS.md.

not rated 16 10d ago A SkillSpector: pass 21 tokens original Apache-2.0

template-skill

494

Code-MonkeyZhang/mini-agent-ts

Skill Claude CodeCodex

A template skill for creating new skills. Use this skill as a starting point when you want to create your own specialized skill.

not rated 16 6mo ago A 29 tokens original MIT

personal-assistant

495

bigduu/Bamboo-agent

Skill Claude Code

Use this skill whenever the user acts like Bamboo is their personal assistant. Triggers include stating commitments, deadlines, appointments, or recurring routines ("remind me to...", "I need to... by Friday", "every Monday I..."), asking to be reminded of something, agenda questions ("what's on my plate", "what's due…

not rated 16 yesterday A 137 tokens original MIT

crawl4ai-skill

497

lancelin111/crawl4ai-skill

Skill Claude CodeCodex

A web crawler and scraper that searches with DuckDuckGo, fetches individual pages or whole sites, and returns clean Markdown intended for language models. It can also scrape pages that need JavaScript to display their content.

not rated 16 6mo ago A 63 tokens original MIT

docingest-docs

498

Amal-David/docingest

Skill Claude CodeCodex

Find, search, and read approved documentation snapshots through DocIngest.

not rated 16 +1 today A 20 tokens original MIT

akf

499

HMAKT99/AKF

Skill Claude CodeCodex

Trust metadata for files, memories, and skills — check before you trust, stamp what you verify. A stamp costs 15 tokens; re-verifying costs 15,000.

not rated 16 +1 1mo ago A 39 tokens original MIT

mobile-perf-doctor

500

ezesubu/VERA

Skill Claude CodeCodex

VERA ships a mobile and performance doctor: a small set of read-only tools that audit the project for things that hurt — or outright break — a mobile build. Use it proactively whenever the user is about to package for mobile, complains about device crashes, or worries about GPU/shader cost.

not rated 16 1mo ago A 0 tokens original MIT

artifact_editor

501

sandeshnaroju/ai-skill-engine

Skill Claude CodeCodex

Skill for generating, searching, reading, surgically editing, and rolling back digital artifacts (code scripts, 1000-page documents, spreadsheets, presentations, SVG diagrams, 2D/3D CAD drawings, geospatial maps, and industrial automation/schedules).

not rated 16 +4 changed today A 56 tokens

svg-chart

502

NUGURI-7/CoCoWork

Skill Claude CodeCodex

Render data into a standalone SVG chart file — bar, line, or pie. Use when the user provides numbers (inline, JSON, or CSV) and asks for a chart, graph, plot, trend, comparison, breakdown, or any visual summary of the data. Produces a self-contained .svg viewable in any browser; no external libraries required.

not rated 15 11d ago A SkillSpector: pass 75 tokens original MIT

fablize

503

teixeirazeus/fablize-for-hermes

Skill Claude CodeCodex

A harness that makes any model see a task through to the end — with evidence and verification — as procedure, not as luck. Enforces verification grounding (run & observe artifacts before declaring done), multi-story decomposition with an evidence gate, a systematic investigation protocol, and early-stop prevention.…

not rated 15 2mo ago A 79 tokens original MIT

oz

504

hiringbae/tryoz

Skill Claude CodeCodex

Use Oz for version-aware external library, SDK, framework, API, and package documentation before Context7 or web search. Trigger for questions about external packages, APIs, libraries, SDKs, frameworks, versions, config keys, CLI flags, or code examples.

not rated 15 2mo ago A 54 tokens original MIT

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: