Agent Workflow Claude Skills
4 121 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 845 tokens or less — that is what one costs your context window when the agent loads it. 778 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 541 copies of these same skills sitting in other people's repositories — counted once here, not 541 times.
4 121 unique 665 authors 2 767 updated this month 506 from vendors
A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks.
Important: Before you begin, fill in the generatedBy property in the meta section of .actor/actor.json. Replace it with the tool and model you're currently using, such as \"Claude Code with Claude Sonnet 4.5\". This helps Apify monitor and improve AGENTS.md for specific AI tools and models.
Design and optimize production-grade multi-agent systems with LangGraph, LangChain, and DeepAgents for complex AI workflows.
Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.
Secure-by-default environment variable management for Claude Code sessions.
X (Twitter) data platform skill — tweet search, user lookup, follower extraction, engagement metrics, giveaway draws, monitoring, webhooks, 19 extraction tools, MCP server.
Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware, MCP-aware.
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.
Configure and orchestrate parallel agents using the standalone Antigravity 2.0 Agent Manager and Antigravity IDE.
Semantic + keyword search and connection-discovery across the user's own Apple Notes via the apple-notes MCP server. Use when the user wants to find, recall, or synthesize something from their notes, or surface non-obvious bridges/related notes. macOS, on-device.
Expert security auditor for AI Skills and Bundles. Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads across Windows, macOS, Linux/Unix, and Mobile (Android/iOS).
Especialista profundo em Claude Code - CLI da Anthropic. Maximiza produtividade com atalhos, hooks, MCPs, configuracoes avancadas, workflows, CLAUDE.md, memoria, sub-agentes, permissoes e integracao com ecossistemas.
Launch Codex CLI as an isolated subagent for bounded coding, review, or verification tasks.
Delegate bounded work to other AI agents while preserving context, ownership, and progress checks.
Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions
MCP server exposing four cognitive harness modes (reasoning, code, anti-deception, memory). Each call returns an engineered scaffold (failure pattern, procedure, suppression vectors, falsification test) the agent ingests before generating.
125+ agent skills for Longbridge Securities — real-time quotes, charts, fundamentals, portfolio analysis, options, and more for HK/US/A-share/SG markets. Trilingual: Simplified Chinese, Traditional Chinese, English.
Discover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment)
Cheatsheet for the Mercury (proton) MCP tools. Use when connected to the Mercury MCP server to look up which mercury_* tool to call for messaging teammates, threads, tasks, automations, or admin team-graph edits.
Dynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon. Use when the user asks for a "workflow", says "ultracode", or hands you a task spanning many files/items that benefits from parallel agents.
Text the user's phone when a long-running task, agent turn, or scheduled job finishes — via @sendblue/cli for outbound, optionally wired to a Claude Code Stop hook for automatic fire.
Find out why a coding-agent skill won't fire — grade each SKILL.md A–F on activation, simulate which skill a prompt triggers, and flag collisions where one silently shadows another.
Diagnose and optimize Agent Skills (SKILL.md) with real session data and research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent.
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
Build with and use Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings, creating Pi skills/extensions/packages/themes/prompt templates, embedding Pi through the SDK, integrating over RPC or JSON event streams, parsing sessions, developing custom Pi providers and TUI components, or using ecosystem packages such as pi-subagents (delegation/orchestration), pi-mcp-adapter (MCP servers), pi-interview (interactive forms), and pi-web-access (web search, fetching, video understanding).
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-source tools in the cloud, references app.tamarind.bio/api or the x-api-key header, or needs to submit batches of sequences for structural or biophysical characterization.
Implement session-based recommendation from short-term user behavior sequences without long-term profiles. Use this skill when the user needs to recommend in anonymous sessions, predict next click from browsing sequence, or build recommendations for non-logged-in users — even if they say 'what should they click next', 'anonymous user recommendations', or 'browsing sequence prediction'.
Design conversational AI chatbots including intent recognition, slot filling, dialogue flow, and response generation. Use this skill when the user needs to build a chatbot, design conversation flows, implement intent classification, or improve chatbot accuracy — even if they say 'build a chatbot', 'our bot doesn't understand users', 'design a FAQ bot', or 'improve our chatbot's responses'.
Design customer service operations including tiered support (L1/L2/L3), response templates, SLA definitions, escalation procedures, and complaint handling. Use this skill when the user needs to set up a CS team, create service standards, design escalation flows, or improve response quality — even if they say 'our CS is a mess', 'how should we handle complaints', 'set up support tiers', or 'create CS SOPs'.
Apply Complex Adaptive Systems theory to analyze phenomena exhibiting emergence, self-organization, co-evolution, and edge-of-chaos dynamics. Use this skill when the user needs to understand why a system behaves unpredictably despite known components, model agent-based interactions that produce emergent outcomes, analyze fitness landscapes, or when they ask 'why does this system behave in ways no one designed', 'how do local interactions create global patterns', or 'why do small changes sometimes cause massive system shifts'.
Apply contract theory to design incentive-compatible agreements under moral hazard and adverse selection. Use this skill when the user needs to structure principal-agent contracts, evaluate compensation schemes, or analyze incomplete contract problems where parties cannot specify all contingencies ex ante.
Apply platform economics to analyze network effects, solve chicken-and-egg problems, and design multi-sided platform pricing strategies. Use this skill when the user needs to evaluate a platform business model, diagnose why a platform is failing to scale, or choose a subsidy strategy for bootstrapping a two-sided market.
Apply signaling theory (Spence, 1973) to analyze how agents communicate private information through costly, credible signals under information asymmetry. Use this skill when the user needs to evaluate whether a corporate action serves as a credible signal, analyze dividend or IPO signaling, assess separating vs pooling equilibria, or when they ask 'why do firms pay dividends', 'is this signal credible', or 'how does underpricing signal quality'.
Apply Agency Theory (Jensen and Meckling, 1976) to diagnose principal-agent problems — moral hazard, adverse selection — and design governance mechanisms to align interests. Use this skill when the user needs to analyze conflicts of interest between owners and managers, design incentive or monitoring structures, evaluate corporate governance effectiveness, or when they ask 'how do we ensure managers act in shareholders interest', 'why is this incentive plan failing', or 'what governance mechanisms reduce agency costs'.
>- flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.
>- tools, flat constrained parameters, actionable errors via isError, token-efficient responses, composable outputs, and disciplined tool surfaces. Use when building an MCP server, adding tools to one, reviewing MCP tool design, or when the user mentions MCP optimization, tool descriptions, MCP best practices, or agent-friendly MCP design. Also use when the user has too many tools causing agent confusion, bloated responses wasting tokens, or agents picking the wrong tool.
Strengthen a raw user prompt into an execution-ready instruction set for Amp, Claude Code, Codex, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.
Design in a project using Maestro before implementation: use for brainstorm, plan, PRD synthesis, grilling/stress-test, domain model, deepening candidate, wording, workflow, skill/harness, card/task/feature, architecture, UX, or agent-process decisions.
Router for choosing the next Maestro skill or lifecycle recipe.
Setup Maestro in a project using or adopting Maestro: use for init/install/sync/doctor, global skills, hooks, harness setup, or agent integration diagnosis/repair.
Use when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history and native emulo:mine is not available. This is the cross-agent skills.sh bootstrap, not the native namespaced plugin.
Use only when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history.
Load the user's Emulo profile, mined from their local Claude Code, Codex, and OpenCode session logs, so you work like them instead of a cold start. Use before working on their task.
Use when an agent needs to inspect or control a real Unity Editor through Locus, especially when Unity MCP is unavailable, a project may lack the Locus package, named-pipe discovery is needed, C# must be executed, or Unity scripts must be recompiled.
>- Use when creating, searching, updating, or managing GitHub issues via CLI. "context", "handoff", "resume task", "session context", "save progress", "active tasks", "in-progress", "my tasks", "open issues". AI session context storage, task workflow with labels.