anthropic skills

10,771 tagged anthropic, measured the same way as everything else here.

Browse within: chatgpt 388LLM 311agents 179ai-assistant 147ai-avatar 135Autonomous Agents 134openai 126agentic-coding 124claude-plugins 123marketplace 123plugin-marketplace 123anthropic-claude 122chatbot 122Multi-Agent 119

docx

25

nextlevelbuilder/goclaw

Skill Claude CodeCodex

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…

not rated 3.6k +10 yesterday A SkillSpector: warn 168 tokens

dbhub

26

bytebase/dbhub

Skill Claude CodeCodex

Guide for querying databases through DBHub MCP server. Use this skill whenever you need to explore database schemas, inspect tables, or run SQL queries via DBHub's MCP tools (searchobjects, executesql, and the opt-in explainsql and healthcheck). Activates on any database query task, schema exploration, data retrieval…

not rated 3.5k +28 2d ago A Socket: passSnyk: passSkillSpector: pass 108 tokens original MIT

claude-md-review

27

wesammustafa/Claude-Code-Everything-You-Need-to-Know

Skill Claude Code

Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.

not rated 3.0k +29 1mo ago A SkillSpector: warn 69 tokens original MIT

upstream-audit

28

maxritter/pilot-shell

Skill Claude CodeCodex

Audit and update Pilot Shell upstream dependencies in installer/upstreams.yaml. Checks npm, PyPI, brew, and curl-pipe entries for newer stable versions, known security advisories, and sha256 drift. Verifies each update installs successfully before committing. Use when: "check upstreams", "update dependencies", "audit…

not rated 2.1k changed today C 89 tokens

stealth-browser-mcp

29

vibheksoni/stealth-browser-mcp

Skill Codex

Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…

not rated 1.9k +39 2d ago A SkillSpector: warn 76 tokens original MIT

resemble-detect

30

Prat011/awesome-llm-skills

Skill Claude CodeCodex

Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI.

not rated 1.7k +7 1mo ago A 45 tokens

ha-skill-creator

31

shiwenwen/hope-agent

Skill Claude Code

Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…

not rated 1.6k +23 changed 3d ago A SkillSpector: warn 106 tokens original MIT

ritual

32

ghostwright/phantom

Skill Claude Code

Discover recurring behaviors from memory and offer to formalize them as scheduled jobs.

not rated 1.5k +2 2mo ago A SkillSpector: pass 18 tokens original Apache-2.0

shogun-bloom-config

33

yohey-w/multi-agent-shogun

Skill Claude CodeCodex

An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.

not rated 1.4k 1mo ago A SkillSpector: pass 86 tokens original MIT

h-reason

34

m0n0x41d/haft

Skill Claude Code

Source-first umbrella for FPF-aware reasoning in a Haft project. Use when the operator asks to think through an ambiguous engineering, management, architecture, specification, or project question without naming a narrower Haft capability. Recover the current object and question, query the bundled FPF source, inspect…

not rated 1.4k +2 29d ago A 112 tokens

caliber-testing

35

caliber-ai-org/ai-setup

Skill Claude CodeCodex needs its repo

Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says…

not rated 1.3k +7 1mo ago A SkillSpector: pass 113 tokens original MIT

migrate-from-ai-sdk

36

Deuz-AI/Deuz-SDK

Skill Claude CodeCodex

Use when porting an app from the Vercel AI SDK (ai, @ai-sdk/) to @deuz-sdk/core. Triggers include "migrate from the AI SDK", "replace ai with @deuz-sdk/core", "we use streamText/generateText/useChat and want to switch", removing @ai-sdk/openai or @ai-sdk/anthropic, porting a toUIMessageStreamResponse route, converting…

not rated 1.3k +41 28d ago A SkillSpector: pass 118 tokens original MIT

contacts

37

vellum-ai/vellum-assistant

Skill Claude CodeCodex

Manage contacts, communication channels, access control, and invite links.

not rated 1.2k +21 changed 5d ago A SkillSpector: warn 14 tokens original MIT

data-analysis

38

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Comprehensive data analysis skill for CSV files using Python and pandas.

not rated 1.1k +2 18d ago A SkillSpector: pass 15 tokens original MIT

eli5

39

DreambigOu/ELI5

Skill Claude CodeCodex

Explain any topic, code, concept, or error tailored to a specific audience's level of understanding. Use this skill whenever the user says 'explain like I am', 'ELI5', 'explain this to my', 'break this down for', 'dumb it down', 'simplify this for', or asks you to explain something to a specific person or audience…

not rated 992 +97 5mo ago A Socket: passSnyk: pass 162 tokens original MIT

metaschedule

40

xvirobotics/metabot

Skill Claude CodeCodex

MetaBot's persistent server-side scheduler (cron + one-shot). Optional skill — not installed by default. Use when the user wants tasks that survive Claude session restarts, are visible to other bots, or need to run in MetaBot's PM2 process rather than this Claude session.

not rated 976 +1 8d ago A SkillSpector: warn 61 tokens original MIT

image-crop-rotate

41

instavm/coderunner

Skill Claude CodeCodex

Image processing skill for cropping images to 50% from center and rotating them 90 degrees clockwise. This skill should be used when users request image cropping to center, image rotation, or both operations combined on image files.

not rated 891 28d ago A SkillSpector: pass 50 tokens original Apache-2.0

academic-pptx

42

Gabberflast/academic-pptx-skill

Skill Claude CodeCodex

Use this skill whenever the user wants to create or improve a presentation for an academic context — conference papers, seminar talks, thesis defenses, grant briefings, lab meetings, invited lectures, or any presentation where the audience will evaluate reasoning and evidence. Triggers include: 'conference talk'…

not rated 861 +19 1mo ago A 164 tokens original MIT

returns-policy

43

strands-agents/samples

Skill Claude Code

Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.

not rated 841 +2 8d ago A SkillSpector: pass 36 tokens original Apache-2.0

hue

44

dominikmartn/hue

Skill Claude CodeCodex

Meta-skill that generates new design language skills. Works on Claude Code and Codex. Use when the user says 'create a design skill', 'generate design language', 'new design system skill', 'design skill inspired by X', 'design skill from this screenshot', '/hue', or 'use hue'. Also triggers for 'remix my design skill'…

not rated 828 +8 3mo ago A 84 tokens original MIT

api-relay-audit

45

toby-bridges/api-relay-audit

Skill Claude CodeCodex

OpenClaw skill for local API Relay Audit. Use when an OpenClaw agent must audit a third-party AI API relay, LLM proxy, gateway, or resale API before trusting coding, tool, production, or wallet-sensitive traffic.

not rated 826 +3 12d ago A 54 tokens AGPL-3.0

story

46

Storybloq/storybloq

Skill Codex

Track tickets, issues, and progress for your project. Load project context, manage sessions, guide setup.

not rated 730 +19 changed 2d ago A SkillSpector: warn 23 tokens

fetch-tweets

47

aeonfun/aeon

Skill Claude CodeCodex

Search and curate X/Twitter behind one selector - keyword, topic roundup, a single or tracked-account digest, an X list, or the AI-agent buzz preset - clustered into signal-scored sub-narratives.

not rated 721 +6 today A SkillSpector: warn 47 tokens original MIT

svc-mobile-android

48

s0ld13rr/pentestcode

Skill Claude CodeCodex

Android APK static analysis — OWASP Mobile Top 10, Retrofit API audit, transport security, smali reading, component export, auth flow analysis. Use when target is an APK/Android app. Triggers - APK, Android, mobile app, decompiled, smali, jadx, apktool.

not rated 684 +70 8d ago A SkillSpector: pass 66 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: