Agents
AI agents and automation
PRD
by fullykubed
Comprehensive PRD (Product Requirements Document) management skill for creating, planning, and implementing PRDs. USE WHEN the user mentions PRDs, wants to plan a feature, or needs to implement planned tasks.
masumi
by masumi-network
"Build AI agents with decentralized payments, identity, and marketplace integration on Masumi Network (Cardano blockchain). Make no mistake - use this skill when working with: (1) Monetizing AI agents with automated payments, (2) Enabling Agent-to-Agent (A2A) autonomous payments, (3) Registering agents in decentralized registry, (4) Listing agents on Sokosumi marketplace, (5) Implementing blockchain-based decision logging, (6) Adding verifiable credentials and DIDs to agents, (7) Setting up Masumi Payment Service nodes, (8) Integrating MIP-003 Agentic Service API, (9) Working with CrewAI, AutoGen, PhiData, LangGraph or custom frameworks, (10) Troubleshooting payment detection or registry issues, (11) Cardano smart contract integration for AI services. Framework-agnostic, self-hosted, and MiCA compliant."
completion-evaluator
by masanao-ohba
Evaluates task completion against acceptance criteria and determines pass/fail verdicts
workflow-patterns
by masanao-ohba
Common workflow patterns and coordination strategies for multi-agent orchestration
erc8004-avalanche
by den-labs
Register and manage AI agent identities on Avalanche C-Chain using ERC-8004 (Trustless Agents). Use this skill when the user wants to register an AI agent on-chain, give or read reputation feedback, request validation, or interact with ERC-8004 identity/reputation/validation registries on Avalanche mainnet or Fuji testnet.
gh-aw-helper
by swannysec
GitHub Agentic Workflows (gh-aw) — write AI-powered automation workflows in natural-language markdown that compile to secure GitHub Actions. Supports Copilot, Claude, and Codex engines with safe-output guardrails, MCP tool integration, and sandboxed execution. Use this skill when users need to: (1) Install or set up gh-aw in a repository (2) Create, edit, or compile agentic workflow markdown files (3) Configure triggers, schedules, safe outputs, tools, or MCP servers (4) Switch AI engines (Copilot, Claude, Codex) or configure engine options (5) Troubleshoot workflow failures, compilation errors, or permission issues (6) Understand gh-aw patterns (ChatOps, DailyOps, IssueOps, etc.) (7) Configure security: permissions, network rules, sandbox, threat detection (8) Use advanced features: memory, imports, orchestration, cross-repo ops
create-agent
by jclfocused
Create a new Claude Code custom agent (subagent). Use when the user asks to "create an agent", "make an agent", "new agent", "build an agent", "create a subagent", "/create-agent", or says something like "create an agent for that" referencing something in the conversation.
Skill
by fullykubed
Create and manage Claude Code skills, including workflows, reference docs, and CLI scripts. USE WHEN the user wants to create a new skill, add workflows to an existing skill, or update skill definitions.
ai-dev-research
by swannysec
World-expert deep technical research agent for AI-enabled software development. Use PROACTIVELY when users need: (1) Deep research on AI/ML development topics (RAG, agents, LLMs, embeddings, vector DBs, prompt engineering, fine-tuning) (2) Technical consultation on AI architectures, tool selection, or implementation approaches (3) Implementation guidance with production-ready patterns and best practices (4) Comparative analysis of AI frameworks, models, or services (5) Current state-of-the-art analysis with authoritative citations Triggers: "research AI", "compare LLMs", "RAG architecture", "agentic workflow", "AI coding tools", "which model should I use", "how does X work in AI", "best practices for AI development", "production AI systems", "AI implementation guidance"
production-audit
by costa-marcello
"Audits a codebase for production readiness across six dimensions: API completeness, frontend-backend sync, security, scalability, infrastructure, and dead code/architecture. Use when asked for a launch assessment, production readiness check, pre-deployment audit, or multi-agent patchwork cleanup."
article-outliner
by daqi
生成写作提纲与文章结构策划。基于素材规划叙事逻辑、情绪曲线及差异化写作方案。
article-writer
by daqi
大齐风格文章撰写与初稿生成。模拟通俗有趣、去AI味的专家口吻，输出高质量内容。
Agent Arena
by Neeeophytee
Discover, register, and hire ERC-8004 autonomous agents across 16 blockchains. Search by capability, check on-chain reputation scores, and get complete machine-readable hiring instructions.
tigris-snapshots-forking
by tigrisdata
Use when needing point-in-time recovery, version control for object storage, or creating isolated bucket copies for testing/experimentation
anti-laziness-guard
by swannysec
Three-layer Stop hook that detects and blocks work-skipping rationalizations by Claude Code agents. Prevents agents from unilaterally deciding to skip assigned work, bypass mandatory processes, or cite unverified context constraints as justification for shortcuts. Layer 1: Deterministic regex detection of known laziness phrases (Tiers 1-2) Layer 2: Haiku-evaluated intent detection for premature victory and silent omission (Tier 4) Layer 3: Optional agent-based deep verification against task lists and plan files This is a passive hook — it activates automatically when the plugin is enabled. No slash command needed. The hook fires on every Stop event and only blocks when laziness patterns are detected.
kcap
by swannysec
Capture and distill knowledge from URLs into structured markdown notes. Supports web articles, YouTube videos, and Twitter/X posts. Extracts content using the best available tool, synthesizes key insights via a sandboxed sub-agent, generates YAML frontmatter with auto-suggested tags, and saves to a configured directory. Optionally integrates with Obsidian for direct vault linking. Use this skill when users want to: (1) Save/capture/distill a URL to a structured note (2) Create knowledge base entries from web content (3) Capture YouTube video transcripts as notes (4) Save Twitter threads as structured summaries (5) Build an Obsidian vault or markdown knowledge base from web sources For saving/distilling a specific URL to a note, use kcap. For browsing, discovering, or searching AI tweets, use ai-twitter-radar instead.
refactor-pass
by montagao
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal and expects build/tests to verify behavior.
agent-factory
by Art-of-Technology
"Spawn a full autonomous software development team from a single prompt. Creates 12 specialized AI agents (PO, PM, Architect, Senior Dev, UI, DB, QA, Security, API, CI/CD, Code Review, Infrastructure) that collaborate via GitHub Issues/Projects board with label-based workflow automation. Use when: (1) setting up a new project with full agent team, (2) adding agent ecosystem to existing repo, (3) creating autonomous development pipeline. NOT for: simple one-off coding tasks, single-agent work, or non-GitHub workflows."
The Synthesis - Hackathon API for AI Agents
by ohmniscientbot
The Synthesis. The first hackathon you can enter without a body. May the best intelligence win.
erc8004-celo
by den-labs
Register and manage AI agent identities on Celo using ERC-8004 (Trustless Agents). Use this skill when the user wants to register an AI agent on-chain, give or read reputation feedback, request validation, or interact with ERC-8004 identity/reputation/validation registries on Celo mainnet or Celo Sepolia testnet.
taiwan-stock-radar
by rabbit68116-ux
Use when the task is to analyze one Taiwan stock through a multi-agent research council. Prioritize Taiwan-specific evidence such as market regime, sector peers, monthly revenue, institutional flow, liquidity, catalyst timing, and invalidation risk. Separate observation from forecast, preserve dissent between specialist agents, and end with explicit buy, stop, take-profit, and thesis-break conditions.
shibaswap-trading
by Testingtester2
Trade tokens on ShibaSwap DEX across Ethereum and Shibarium networks. Supports V1 (AMM) and V2 (concentrated liquidity) protocols with multi-hop routing.
gha-hardening
by swannysec
GitHub Actions security hardening, configuration best practices, and vulnerability detection. Covers workflow syntax, trigger security, permission management, secrets handling, OIDC federation, supply chain protection, self-hosted runner hardening, attack pattern recognition, and security scanning tool rules. 60% security/hardening content, 40% implementation/configuration guidance. Use this skill when users need to: (1) Harden GitHub Actions workflows against injection, supply chain, or privilege escalation attacks (2) Configure workflow permissions, secrets, OIDC, or environment protection rules securely (3) Understand dangerous workflow patterns (pull_request_target + checkout, workflow_run artifact poisoning, script injection via ${{ }}) (4) Choose or configure security scanning tools (zizmor, scorecard, actionlint, poutine, harden-runner, Raven) (5) Respond to supply chain incidents (tj-actions, reviewdog, compromised action tags) (6) Audit workflows for OWASP CI/CD risks, CIS benchmark compliance, or OpenSSF Scorecard checks (7) Write or review workflow YAML (triggers, matrix, reusable workflows, composite actions, caching, artifacts, environments) (8) Secure self-hosted runners (ephemeral patterns, network egress, persistence detection, runner groups)
reactor-sub-agent
by knowlet
專責處理 RIF (Required Behavior Frame) 類型的需求。讀取規格目錄結構，生成/審查 Event Handler 設計與實作。支援冪等性、重試、死信佇列。