Recently Added

omnidocbench-eval-helper

by opendatalab

Help users deploy, validate, run, and parse OmniDocBench evaluations. Use this skill whenever the user mentions OmniDocBench, document parsing/OCR benchmark scoring, MinerU or other model evaluation on OmniDocBench, CDM formula metrics, end2end/md2md configs, Docker/conda deployment, remote SSH/H-cluster execution, result JSON parsing, or troubleshooting TeX Live/ImageMagick/Ghostscript/Docker/worker/OOM issues. Prefer Docker first, generate concrete commands from the user's paths, validate inputs before running, and report final Overall/Text/Formula/Table/Reading-order scores with result file paths.

mobilerun-docs

by droidrun

Mobilerun documentation reference. Use when users ask about Mobilerun setup, configuration, SDK usage, CLI commands, device setup, agents, architecture, app cards, credentials, tracing, Docker, migration, structured output, or any Mobilerun "how do I..." questions.

ikuai-cli

by ikuaidev

CLI for managing iKuai routers via local v4.0 API. Use when the user asks to check router status, configure network/DNS/DHCP/VPN/firewall, manage users, view logs, or automate any iKuai router operation.

routstrd CLI Reference

by Routstr

~/.routstrd/logs/YYYY-MM-DD.log Daily log files

configure-ecc

by affaan-m

Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.

deep-research

by Imbad0202

"Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題."

academic-pipeline

by Imbad0202

"Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow."

setup-brain

by adelaidasofia

Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.

accessibility

by affaan-m

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA

反ai-skill

by Wholiver

企业级代码复杂度增强工具包。将干净、可读的代码转化为专业混淆的、为保住工作而优化的实现，展示深厚的工程成熟度和架构 sophistication。

snes-fit

by DimmMak

Fleet-wide QA skill that audits any other skill against structural, adversarial, scale, composition, security, threat-intel, type, and design dimensions. Plugin architecture lets you add dimensions as separate dirs — no core code changes. Ship only when decay rule hits 2 consecutive zero-finding rounds. Compatible with Anthropic skill-creator eval schemas. NOT for: creating new skills (use snes-builder). NOT for: running skills (use the skill directly). NOT for: continuous background monitoring (use scheduled-tasks).

bd-artes-impressoes-design

by eduardushenrique-create

Use this skill to generate well-branded interfaces and assets for B&D Artes & Impressões, a Brazilian 3D-printed gifts e-commerce. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

fb-group-monitor-v3.4

by Nikolaustis

用于 Facebook 游戏群组两阶段监测的严格技能。用户提到“FB 群组采集/监测/输出 CSV/Excel/多游戏批量/manual_review_queue/collision_report/先登录再采集”时使用。先执行登录阶段；在用户回复“已登录”前不要搜索、采集、分析或生成报告。登录后按两阶段流程执行，并输出 CSV、Excel、中文摘要、manual_review_queue.csv、collision_report.json、audit_stats.json。

zoho-gym-campaigns

by laura-shireelite

Create Zoho Campaigns email marketing drafts automatically for your gym's term calendar. This skill reads your key calendar dates from a Google Sheet and creates two types of campaign drafts in Zoho Campaigns: 1. Term-start campaigns: A single "Term X YYYY - All Events" campaign listing all upcoming events for the term 2. Reminder campaigns: Individual campaigns scheduled to be created 3 days before each event Templates are customized by event type (promotions, class launches, member events, etc.). The skill can be scheduled to run on a set calendar (e.g., at the start of each gym term) or triggered manually. Use this skill when you want to automate campaign creation for recurring gym events, ensure consistent messaging across your term calendar, or save time creating multiple related campaigns at once.

pr-writer

by getsentry

ALWAYS use this skill when creating or updating pull requests — never create or edit a PR directly without it. Follows Sentry conventions for PR titles, descriptions, and issue references. Trigger on any create PR, open PR, submit PR, make PR, update PR title, update PR description, edit PR, push and create PR, prepare changes for review task, or request for a PR writer.

sitelayer

by GitSteveLozano

Default engineering workflow for the Sitelayer repo. Applies to planning, debugging, implementation, review, and autonomous task work.

dataflow-builder

by DimmMak

Pipeline-build coach for the DATAFLOW framework (Define → Acquire → Tidy → Archive → File → Launch → Observe). Walks the user through writing a real end-to-end stock-data pipeline as a code-along drill: each line of code is rendered with first-letter blanks (coderecall mechanic), user types first letters, system reveals the matching keyword, code is appended to the project file. Composes existing fleet desks at the Acquire stage — price-desk (history + live), fundamentals-desk, technicals-desk, macro-desk, options-desk. Output = a real working project directory, not a tutorial transcript. Observe stage is collaborative — Claude proposes candidate angles, user picks/refines, dashboard wireframe emerges before viz code is drilled. NOT for: Socratic WHY-questions on existing pipelines without writing code (use dataflow-tutor — zero code, conceptual). NOT for: gamified DATAFLOW pipeline-stage concept quiz (use dataflow-millionaire — game format, conceptual). NOT for: drilling raw SQL/pandas keywords as muscle memory without building a project (use coderecall — single-line drills, no project output). NOT for: orchestrating existing skills into one-shot execution (use mewtwo — executor, not teacher).

survivorship-bias

by jefrnc

Use when constructing a backtest universe, computing index/sector returns, ranking strategies, or comparing performance across time. Catches the silent inflation that comes from using today's universe (or today's ticker resolution, or today's index membership) for a historical backtest. Especially severe in small caps and FPI-heavy universes where delisting rates exceed 30% over five-year windows.

crypto-futures-depth-analysis

by alkindivv

Deep Binance Futures and altcoin intraday analysis using public exchange APIs, WebSocket stream plans, Bybit cross-venue confirmation, CoinGecko market metadata, news RSS, and macro event context. Use when the user asks for Binance Futures scans, best long or short setups, deep single-coin analysis, signal validation, execution-quality checks, or when the assistant needs to proactively gather public market data without waiting for extra permission.

transaction-cost-modeling

by jefrnc

Use when designing, reviewing, or running a backtest that involves slippage, commission, borrow APR, locate failures, bid-ask spread, or transaction-cost assumptions — especially for small caps or short-side strategies. Forces realistic friction defaults and flags the "near-zero cost" assumptions that fabricate small-cap backtest profits.

paper

by Wahba475

Paper-textured, print-inspired design with minimal colors, clean serif/sans typography, and tactile surface qualities.

AI Agent Skill

by frankois944

ebook-knowledge-extractor

by HonoSumi

从电子书中提取结构化知识的完整工作流。 支持 PDF / EPUB / MOBI / TXT / MD 等多种电子书格式。 特点：(1) 分块处理避免上下文爆炸，绝不直接读取全书； (2) 每块串行通过 subagent 提取名词，结合互联网检索给出解释； (3) 最终汇总到 SQLite 数据库。 当用户需要"提取电子书知识"、"做读书笔记"、"整理书中人物/事件"、 "归档书中概念"、"结构化电子书内容"时务必使用此 skill。 也适用于用户想从书中提取具有民族特色或地方特色的文化元素时。

geo

by zubair-trabzada

GEO-first SEO analysis tool. Optimizes websites for AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Performs full GEO audits, citability scoring, AI crawler analysis, llms.txt generation, brand mention scanning, platform-specific optimization, schema markup, technical SEO, content quality (E-E-A-T), and client-ready GEO report generation. Use when user says "geo", "seo", "audit", "AI search", "AI visibility", "optimize", "citability", "llms.txt", "schema", "brand mentions", "GEO report", or any URL for analysis.