anthropic skills

10,762 tagged anthropic, measured the same way as everything else here.

Browse within: chatgpt 410LLM 314agents 179ai-assistant 147ai-avatar 134openai 128chatbot 124claude-plugins 123marketplace 123plugin-marketplace 123anthropic-claude 122Autonomous Agents 113agentic-coding 104web-development 104

atomic-writing

146

damusix/atomic-claude

Skill Claude CodeCodex

One voice for every file the repo ships: README, docs/guides/, docs/reference/, docs/spec/, docs/design/, docs/research/, docs/wiki/, CLAUDE.md, and the prompt artifacts under commands/, agents/, skills/, rules/, and output-styles/. Clear, direct, technical, and visual wherever the content has a shape. No marketing…

not rated 89 +5 3d ago A SkillSpector: warn 268 tokens original MIT

initiating-coverage

147

prof-little-bear/cc-equity-research

Skill Claude CodeCodex

Create institutional-quality equity research initiation reports through a 5-task workflow. Tasks must be executed individually with verified prerequisites - (1) company research, (2) financial modeling, (3) valuation analysis, (4) chart generation, (5) final report assembly. Each task produces specific deliverables…

not rated 88 4mo ago A 90 tokens copy · 100% Apache-2.0

vasilyu1983/AI-Agents-public

Skill Codex

16 behavioral-economics primitives for ethical pricing, choice design, and retention. Use when framing, defaults, habits, dark patterns, AI-agent nudging, or nudge ethics apply.

not rated 87 +3 10d ago A SkillSpector: warn 48 tokens original MIT

openacme-platform

149

sandydasari/openacme

Skill Claude CodeCodex

How OpenAcme is laid out — data dir, agents, skills, MCP servers, tasks, memory, the peer-notes convention. Read this when the user asks you to manage their workforce, set up an agent, install a skill, configure an MCP server, or explain how the platform works.

not rated 86 +1 1mo ago A SkillSpector: warn 66 tokens original MIT

api-authentication

150

stefan-jansen/claude-code-toolkit

Skill Claude CodeCodex

API authentication patterns including JWT, OAuth 2.0, API keys, and session-based auth. Covers token generation, validation, refresh strategies, security best practices, and when to use each pattern. Use when implementing API authentication, choosing auth strategy, securing endpoints, or debugging auth issues.…

not rated 86 +1 2mo ago A SkillSpector: warn 77 tokens original MIT

gpt-image-2

151

jiangmuran/claude-image

Skill Claude CodeCodex

Use when generating, editing, composing, or iterating on images — illustrations for reports/web, posters with Chinese or English typography, pitch-deck slides, UI mockups, infographics, pixel art, game sprites, character reference sheets, app icons, logo concepts, photoreal product shots, or photo edits with precise…

not rated 85 4mo ago A 198 tokens original MIT

continuum-tools-mcp

152

shyftlabs/continuum

Skill Claude Code

Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…

not rated 84 yesterday A SkillSpector: pass 94 tokens original Apache-2.0

cookbook-audit

153

timothywarner-org/claude-architect

Skill Claude Code

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

not rated 82 +2 1mo ago A 26 tokens copy · 100% MIT

ppt-report-generator

154

myunwang/ppt-report-skills

Skill Claude CodeCodex

A browser-based presentation tool that turns data and conclusions into 16:9 report slides. It can show slides full screen and export them as a PDF.

not rated 81 3mo ago A 198 tokens original MIT

add-handler

155

MuhammadUsmanGM/claude-code-best-practices

Skill Claude Code

Scaffold a new HTTP handler with service function, store method (if needed), and table-driven test, following the project's internal/{api,service,store} layout. Invoke when the user asks to add an endpoint, handler, or route.

not rated 79 +1 2mo ago A 52 tokens original MIT

ad-attacks

156

mukul975/Threatswarm

Skill Claude Code

Active Directory attack reference — BloodHound Cypher queries, Kerberos attack decision tree, ACE/ACL abuse, ADCS ESC1-8, and AD misconfig checklist.

not rated 78 +1 4mo ago A 39 tokens original MIT

test-writer

157

kivo360/OmoiOS

Skill Claude CodeCodex

Generate comprehensive tests including unit, integration, and property-based tests.

not rated 77 +1 2mo ago A 12 tokens original Apache-2.0

upload-assets

158

TOKTOKHAN-DEV/agent-company

Skill Claude CodeCodex

An asset-upload workflow that sends files to a console’s content-delivery network and prepares a review-request payload for a person to submit.

not rated 77 +2 16d ago A SkillSpector: warn 2 tokens original MIT

release

159

gtapps/claude-code-hermit

Skill Claude Code

Bump a plugin's version, write a detailed changelog entry for the upgrade skill to consume, and commit+push. Takes a plugin slug argument identifying which plugin under plugins/ to release. Use this skill whenever the user says "release", "version bump", "cut a release", "changelog and push", or finishes a set of…

not rated 74 changed 6d ago A SkillSpector: warn 104 tokens original MIT

generate-report

160

xvirobotics/metaskill

Skill Claude Code

Generate a comprehensive summary report of the latest experiment including metrics, plots, and comparison with baseline. Use this after training and evaluation to create a shareable experiment summary.

not rated 67 6mo ago A 36 tokens original MIT

watch-video

161

Newuxtreme/watch-video-skill

Skill Claude CodeCodex

SLASH-COMMAND-ONLY. Invoke ONLY when the user explicitly types the literal /watch-video slash command. Never auto-trigger on phrases like "watch this video," "summarize this video," "take notes on this video," or on a bare YouTube URL. For ad-hoc YouTube questions, fetch the transcript directly (YouTube page or…

not rated 66 +1 4mo ago C 91 tokens original MIT

future-tokens

162

jordanrubin/FUTURE_TOKENS

Skill Claude CodeCodex

Every AI output has structural blind spots determined by the generation process itself. Future Tokens operations are named, composable instruments that target specific blind spots. They surface new information on every pass because expanding the output changes the blind spot geometry.

not rated 65 +1 6mo ago A 50 tokens

mckinsey-consultant

163

Mann1988/awesome-claude-skills

Skill Claude CodeCodex

A consulting style method for breaking business questions into structured analyses and producing research reports or presentations.

not rated 65 yesterday A SkillSpector: pass 82 tokens original MIT

avoid-ai-design

164

funboy322/avoid-ai-design

Skill Claude CodeCodex

Audit and rewrite frontend UI to remove generic AI design patterns ("AI slop"). Use this skill when asked to "de-slop a UI", "make a design look less AI-generated", "audit a component or page for AI design tells", or "fix Claude/Codex-generated frontend that looks generic". Covers HTML/CSS and React/Tailwind/shadcn.…

not rated 65 +4 2mo ago A 90 tokens original MIT

composing-1c-queries

165

Desko77/claude-code-skills-1c

Skill Claude CodeCodex

A guide for writing queries in the 1C:Enterprise query language. It covers how to select, filter, join, group, and summarize data from 1C catalogs, documents, and registers.

not rated 62 +7 yesterday A 174 tokens original MIT

api-interface-design

166

MohitGoyal09/AgentForge

Skill Claude CodeCodex

Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.

not rated 61 2mo ago A 23 tokens original MIT

wanshuiyin/ARIS-Movie-Director

Skill Claude Code needs its repo

Phase-1 (S5) UPSTREAM ref-asset gate — the bounded cross-model adversarial loop that LOCKS one reusable identity-locked asset (character sheet / location plate / prop cutout / text-panel / logo-free symbol) BEFORE it can be composited into any panel. This is NOT the panelgate (composed-output) or the assemblygate…

not rated 61 +4 3d ago A SkillSpector: pass 275 tokens original MIT

naveedharri/benai-skills

Skill Claude CodeCodex

Interactive step-by-step installer for the Google Workspace CLI (gws) on macOS, Linux, WSL, OR native Windows (Git Bash / MINGW64). From a clean machine: detects platform, installs the package manager + Google Cloud SDK + gws CLI, helps accept GCP Terms of Service, creates a GCP project, enables the Workspace APIs the…

not rated 61 +1 yesterday C 0 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: