Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

自审

21553

xiamenhewei/zishen

Skill Claude CodeCodex

A self-review checklist for software plans and code changes, with fourteen review areas and a final acceptance check.

not rated 2 changed 1mo ago A 123 tokens original MIT

mempalace-zettelkasten

21554

sefodo26/mempalace-server

Skill Claude CodeCodex

Capture an idea as an atomic, self-contained note in your own words, link it to related notes, and store it in MemPalace so it resurfaces fast later. Use when the user wants to add a thought/idea/insight as a Zettelkasten note, reformulate notes atomically, or build a linked knowledge base.

not rated 2 23d ago A 79 tokens original MIT

daf-git

21555

itdove/devaiflow

Skill Claude Code

GitHub/GitLab issue operations (update, link) with Markdown syntax reference and gh/glab CLI guide.

not rated 2 changed 26d ago A 26 tokens original Apache-2.0

vscode-bridge

21556

mengqiuzhen/claude-code-skills

Skill Claude CodeCodex

Bridge between CLI Claude Code and VSCode Claude Code on the same Windows machine. Use when the user needs to: read what VSCode Claude last said, send commands to VSCode Claude, check if VSCode Claude is busy/idle, or coordinate between the two Claude instances. Triggers: "what did vscode claude say", "send to vscode…

not rated 2 4mo ago A 102 tokens

youtube-metadata-updater

21557

nikhilbhansali/youtube-data-skills

Skill Claude CodeCodex

Update video titles and descriptions on your OWN YouTube channel to improve search and browse visibility, using the YouTube Data API v3 with a write scope. Every change is previewed, approved by you, backed up, and reversible. Use when users want to (1) Rewrite titles on videos that get good retention but weak views…

not rated 2 1mo ago A 176 tokens original MIT

claude-dual-supervisor

21558

ling-ling-luo/claude-code-skills

Skill Claude Code

Run dual Claude Code sessions with Worker (executes tasks) and Supervisor (makes decisions, reviews). Use when user wants "two Claude sessions", "supervisor-worker pattern", "decision maker and executor", "code review workflow", or "collaborative AI agents".

not rated 2 8mo ago A 61 tokens

meeting-minutes-docx

21559

system-xmu/skills

Skill Codex

Generate structured meeting minutes and export Word (.docx) from meeting transcript text, a local transcript file, or Playwright MCP extraction from Tencent Meeting transcript result pages, plus PPT Markdown. Use when Codex needs transcript cleanup, Tencent Meeting transcript-page reading, speaker-and-time anchored…

not rated 2 changed 1mo ago A 86 tokens

AntonioMellies/claude-code-skills

Skill Claude CodeCodex

Atua como Principal Product Designer e Enterprise UX Architect especializado em Material Design 3 adaptado para SaaS B2B, CRM, ERP, Backoffice e plataformas corporativas complexas. Prioriza produtividade, densidade de informação, eficiência operacional, Design Tokens e acessibilidade.

not rated 2 3mo ago A 66 tokens

api-scaffold

21561

xmqywx/claude-code-skills

Skill Claude CodeCodex

Scaffold a production-ready REST API endpoint with CRUD operations, input validation, error handling, rate limiting, and test skeletons. Supports Express and Fastify.

not rated 2 6mo ago A 36 tokens

agent-browser

21562

JayAI623/claude-code-config

Skill Claude Code

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…

not rated 2 6mo ago A 108 tokens

autoresearch-network

21563

gensyn-ai/collaborative-autoresearch-demo

Skill Claude Code

Share autoresearch experiment findings over the Yggdrasil P2P network. Use at the START of each autoresearch round to receive peer findings and decide whether to adopt a better baseline, and at the END of each round to broadcast your result to all peers.

not rated 2 5mo ago A 57 tokens

davidbeglenboyle/davids-claude-code-setup

Skill Claude CodeCodex

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation.

not rated 2 5mo ago A 35 tokens

extend-vision-solution

21565

suharvest/sensecraft-solutions

Skill Claude Code

A workflow for extending an AI camera or vision application from one edge device to several platforms, such as Jetson, RK, reCamera, and Hailo. Edge platforms are small computers that process camera data locally.

not rated 2 6d ago C 119 tokens original Apache-2.0

zenmoney

21566

miilv/zenmoney-go

Skill Claude Code

Query personal finances via ZenMoney API. Use when the user asks about money, finances, accounts, balances, transactions, spending, income, expenses, budget, net worth, savings, or cash flow.

not rated 2 6mo ago A 44 tokens

tree-of-thoughts

21567

NikkeTryHard/tree-of-thoughts-mcp

Skill Claude CodeCodex

Multi-path investigation with parallel agents. Use when researching complex questions requiring breadth-first exploration with verification.

not rated 2 4mo ago A 25 tokens

audit-agent-docs

21568

oroddlokken/slop

Skill Claude CodeCodex

Audit agent-facing documentation (CLAUDE.md, AGENTS.md, copilot-instructions.md) for redundancies, contradictions, gaps, and misplaced content. Supports Claude Code, OpenAI Codex, and GitHub Copilot. For a general agent's system prompt, persona, or tool descriptions (not repo docs), use audit-agent-prompt. Use when…

not rated 2 yesterday A 89 tokens

claude-code-seo-blog

21569

liyakhar/claude-code-seo-guide

Skill Claude CodeCodex

Generates a production-ready, SEO-optimized, voice-matched blog post from keywords.csv using the Claude Code SEO blueprint. Picks unused keywords, researches top-3 SERP, fetches Pexels images, applies on-page SEO, and marks keywords used. Use when the user types /blog, asks for a new SEO blog post, or wants…

not rated 2 3mo ago A 85 tokens

memory-init

21570

spudy-vibing/Claude-Code-Prompts

Skill Claude Code

Initialize Claude's persistent memory system with self-designed format and auto-loading SessionStart hooks. Use when starting a new project or when user says "set up memory", "init memory", "remember this project", or "create memory system".

not rated 2 8mo ago A 50 tokens original MIT

django

21571

Mariatta/claude-skills

Skill Claude CodeCodex

House conventions for writing code in a Django codebase: formatter and linter compliance (black, isort, djlint, flake8), imports at module top with real refactors for circular imports, docstrings over comment blocks, maintained libraries over hand-rolled code, full test coverage as a merge gate, one squashed migration…

not rated 2 changed 9d ago A 0 tokens original MIT

caravo

21572

Caravo-AI/Agent-Skills

Skill Claude CodeCodex

Caravo is the first service marketplace built for autonomous AI agents — featuring 200+ ready-to-use services across categories: AI Models, Search, Data & Analytics, Finance, Social Media, Communication, eCommerce, Cloud & Infrastructure, Digital Assets, Utilities, and more. Caravo provides access to premium and…

not rated 2 7mo ago A 516 tokens original MIT

develop

21573

BostonOrange/claude-code-framework

Skill Claude CodeCodex

Full development cycle - fetches ticket from work item tracker, analyzes, implements, validates, fixes build errors, and creates PR. Use when developing a ticket end-to-end.

not rated 2 2mo ago A 37 tokens original MIT

ai-code-review-tutor

21574

johnefemer/skillfish

Skill Claude CodeCodex

Teach AI to review like your team: custom review checklists, tone calibration, org-specific patterns, and AI-assisted code review workflows.

not rated 2 5mo ago A 0 tokens

core-web-vitals-audit

21576

JakeLabate/Claude-SEO-Skills

Skill Claude CodeCodex

Audit a website's Core Web Vitals and page-experience signals (LCP, CLS, INP, TTFB). Optionally pulls real field data from Google PageSpeed Insights (CrUX) and always collects browserless lab proxies — render-blocking CSS/JS, page weight, image dimension and lazy-loading hygiene, TTFB, text compression, DOM size…

not rated 2 3mo ago A 133 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: