Agents
AI agents and automation
abel-causal-benchmark-v2
by zeyuyuyu
Run Abel Causal Benchmark V2 with 35 forward-looking prediction questions. Features 10 intervention scenarios, CAP (Causal Agent Protocol) mapping, and Enhanced CEVS scoring. Tests "causal emotional value" through explainable predictions, what-if analysis, and multi-hop causal chains that surpass generic LLM capabilities.
hook-runner
by grobomo
"Modular hook runner for Claude Code. Workflows group modules into enforceable pipelines."
implement-agents
by ianphil
This skill should be used when the user asks to "implement in parallel", "run phases concurrently", "parallel implement", "implement-agents phase X phase Y", or wants to orchestrate multiple agents running /implement simultaneously.
codebase
by Vistablox-EU
A brief description of what this skill does
pr-screenshots
by nullswan
Capture before/after screenshots for pull requests to document visual changes. Supports both agent-browser CLI and Playwright Python approaches. Use when creating PRs with UI changes, comparing visual states between branches, documenting frontend changes for code review, or generating visual diff reports.
super-assistant-framework
by LiubaiCheng
超级助理Agent的完整系统脚手架。包含7层架构目录结构、WIKI知识库管理规则、工程纪律方法论、自动化日程模板、setup引导流程和使用指南。当用户想要搭建一个拥有知识库管理、晨读信息摄入、信号追踪、周期巡检等自动化能力的超级助理Agent时使用此技能；当用户提到"搭助理框架""初始化超级助理""搭建知识库Agent""复制助理系统"等意图时触发。
seo-analyzer
by loo-y
基于 Google 官方文档的 SEO 自动检测工具。自动分析网址的技术 SEO、内容元数据、性能体验和链接结构，输出符合 Google 最佳实践的检测报告。使用场景：(1) 分析网站 SEO 状况，(2) 诊断搜索引擎排名问题，(3) 验证页面是否符合 Google Search Essentials 标准，(4) 生成可执行的 SEO 优化建议。
financial-analysis
by coopergwrenn
Real-time stock, crypto, forex, and options data with 50+ technical indicators via Alpha Vantage. Use when the user asks about stock prices, technical analysis, RSI, MACD, options chains, crypto prices, market briefings, or earnings reports.
maiat
by JhiNResH
Trust infrastructure for AI agents. Register your agent, get an on-chain identity, check trust scores, and protect transactions. Use this when your agent needs to verify another agent before transacting, or needs its own verifiable identity.
mine
by awp-worknet
Autonomous data mining and validation on the ocDATA / aMine platform. Use this skill whenever the user mentions: mining, miner, validator, validating, aMine, ocDATA, data mining rewards, crawling for rewards, earning tokens by crawling, mining status, mining start/stop/pause/resume, dataset selection, repeat crawl, evaluation tasks, mining diagnostics, doctor, mining errors, 401/auth errors related to mining, submission scores, epoch rewards, credit tier, or anything about running autonomous data collection workers. Also trigger when the user asks to "go online", "start earning", "check my submissions", or troubleshoot platform connectivity issues. ALL platform interaction goes through python scripts/run_tool.py — never make direct HTTP calls (they require EIP-712 signatures and will always fail). Not for AWP wallet transfers, RootNet staking, smart contract deployment, or general server monitoring.
tw-portfolio
by kzokv
A brief description of what this skill does
sae-policy-guard
by SatoshiRenZ
Pre-trade risk assessment and policy enforcement for crypto trading using the Survivability-Aware Execution (SAE) framework. Use this skill before executing any crypto trade, when evaluating trader behavioral state (revenge trading, tilt, overconfidence, late-night impulsivity), when assessing market narrative risk, when computing position/leverage/frequency limits, when enforcing cool-down periods or staged execution, when auditing trading plugins or extensions for supply-chain risk, or when the user mentions risk management, survivability, blow-up prevention, liquidation avoidance, or trading discipline.
pydantic-ai-agent
by randomStar
Build production-grade Pydantic AI agents with layered architecture. Use when creating AI agents with tool systems, dependency injection, streaming responses, multi-provider support, or conversation state management. Includes scaffolding scripts for rapid project setup and comprehensive architectural patterns for FastAPI web services and CLI applications.
claw-relay
by AndreaGriffiths11
Control a remote browser through Claw Relay. Use when you need to navigate authenticated websites, click buttons, fill forms, take screenshots, or read page content on a user's real browser — especially when the agent runs on a different machine (cloud, container, server) than the browser. Triggers on remote browser control, authenticated browsing, real browser, cookie-based access, browser relay.
hoosat-dev
by codecustard
"Comprehensive Hoosat blockchain development toolkit for building transactions, integrating wallets, creating dApps, and interacting with the Hoosat network (a Kaspa fork using Blake3 and Hoohash). Use when working with Hoosat blockchain development including: (1) Building and broadcasting HTN transactions, (2) Generating addresses with hoosat: prefix, (3) Creating dApps using hoosat-sdk or hoosat-sdk-web, (4) Integrating Hoosat wallets, (5) Using Hoosat SDKs (Node.js hoosat-sdk, Browser hoosat-sdk-web, Motoko hoosat-mo for IC), (6) Using the Hoosat REST API at proxy.hoosat.net, (7) Working with HRC20 tokens. Supports JavaScript/TypeScript (Node.js and Browser), Go, and Motoko (Internet Computer) development."
git-workflow
by kprsnt2
Git best practices and workflows including conventional commits, branching strategies, and collaboration patterns.
ground
by ddaanet
Ground claims with external research before asserting methodology. Triggers on "ground", "create a scoring system", "design a methodology", "build a framework", or "synthesize best practices". Parallel diverge-converge research preventing confabulated structures.
multi-agent-thinker
by CodingHeader
This skill is the "Heavy Lifting Engine" for complex problem solving.
agent-creator
by slurpyb
Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks requiring consistent high-quality performance with deeply embedded domain knowledge.
swe-implementer
by diegocanepa
"Development persona for writing clean, tested code and executing subtasks within the SWE workflow."
Social Content Creator
by kolegadev
GITHUB_TOKEN — Auto-provided for Actions
skill-ai-escape-mrc
by oxydavid-maxx
Use when reviewing AI harness, agent, CI, or browser/API automation flows that reported success but may have missed verification, renamed entrypoints, plugin links, generated docs, tests, runtime artifacts, delivery artifacts, or other escape paths. Triggers on AI automation escape review, harness escape, automation-flow escape, missed verification, false completion, non-detection, recurrence prevention, corrective action, proof of action, and managerial root cause. LangGraph FSM-driven with research, IS/IS-NOT scoping, four-quadrant TRC/MRC analysis, corrective/prevention matrices, proof-of-action verification, report/plan generation, and email delivery.
vscode_integration
by Zazzles2908
Enables Mini-Agent to integrate directly with VS Code Chat API for seamless AI assistance
claude-code-dev
by maxoreric
Claude Code Plugin 开发专家。当用户要创建 Plugin、Skill、Subagent、Slash command、Hook 时触发。也用于解答 Claude Code 开发相关问题。触发词：创建 plugin、写 skill、写 agent、创建 hook、写 command、插件开发。