Agent Workflow Claude Skills
4 122 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 844 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 589 copies of these same skills sitting in other people's repositories — counted once here, not 589 times.
4 122 unique 665 authors 4 updated this month 506 from vendors
Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract, normalize, and standardize financial data into investment committee-ready Excel workbooks with consistent structure, proper formatting, and documented assumptions. Use for M&A due diligence, private equity analysis, investment committee materials, and standardizing financial reporting across portfolio companies. Do not use for simple financial calculations or working with already-completed data packs.
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.
Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live preview, and copy out a prompt. Use when the user asks to make a playground, explorer, or interactive tool for a topic.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker", "dashboard" or "confirmation dialog" inline in the conversation, or mentions "apps SDK" in the context of MCP. Use AFTER the build-mcp-server skill has settled the deployment model, or when the user already knows they want UI widgets.
Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.
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.
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer activity, chromatin state, sequence-to-expression (log TPM), and de-novo gene annotation, plus a composite find-genes-then-predict-expression workflow. Use when the user has a gene symbol, a genomic region, or a DNA/FASTA sequence and wants any of these predictions, mentions Genomic Intelligence, genomicintelligence.ai, api.genomicintelligence.ai, or mcp.genomicintelligence.ai.
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.
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and release gates—not for clinical decision-making.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Agent Context Isolation
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
Find and resume interrupted Copilot CLI sessions using session_store queries
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs (HTTP 402/x402), wallet custody or trust concerns, spending mandates, delegated permissions (ERC-7710/7715), escrow, agent identity or reputation (ERC-8004), negotiation between agents (A2A), agent jobs (ERC-8183), machine payments (MPP, AP2), supervision of agent behavior, revocation, verification, or dispute resolution (GenLayer) — even if they never say "Internet Court". Routes to the vendored protocol skills and connector skills in this package.
Use this skill when the user wants to launch a new AltClaw, OpenClaw, PicoClaw, or Ottie deployment through Cloud Claw. Covers the same user-facing fields and constraints exposed in the Cloud Claw UI, using the local altllm cloud-claw-* commands. Do NOT use for post-launch lifecycle tasks like start/stop/delete/logs; use cloud-claw-manage-vm.
Use this umbrella skill when the request spans multiple Cloud Claw user-facing domains, especially launching a new AltClaw or OpenClaw VM and then managing lifecycle, logs, renewal, or dashboard access through the local altllm cloud-claw-* commands in this repository.
BNB Chain MCP server connection and tool usage. Covers npx @bnb-chain/mcp@latest, PRIVATE_KEY and RPC, and every MCP tool — blocks, transactions, contracts, ERC20/NFT transfers, wallet, ERC-8004 agent registration, Greenfield. Use when connecting to bnbchain-mcp, querying or transacting on BNB Chain/opBNB/EVM, registering as ERC-8004 agent, or using Greenfield.
Give the AI agent its own EVM wallet with admin-controlled policies the agent CANNOT bypass even under prompt injection. Encrypted keystore (AES-256-GCM, scrypt KDF), policy file the agent has no tool to write, deterministic policy gate on every signing operation, optional local HTTP dashboard. Triggers: agent wallet, give the agent a wallet, agent address, fund the agent, agent autonomy, policy gate, kill switch, agent permissions, bounded autonomy, ERC-4337 alternative, session-key alternative.
Upload files to IPFS through the Kleros x402 payment gateway in exchange for $0.01 USDC on Base mainnet. Use this skill **specifically** when the user is uploading content destined for the Kleros ecosystem — dispute evidence, meta-evidence JSON, court / dispute / arbitrator policies, Curate item metadata, juror justifications, or any artifact a Kleros smart contract or subgraph will reference by IPFS CID. Trigger when the request mentions Kleros, a court / arbitrator / dispute / juror / curate / proof-of-humanity context, or any of the conventional Kleros operation tags (evidence, meta-evidence, justification). Do NOT trigger for generic 'upload to IPFS' / 'get me a CID' requests with no Kleros context — point those users at Pinata, web3.storage, or any general-purpose pinning service instead. Exception: if the user explicitly names this gateway (kleros-ipfs-gateway.fly.dev / kleros-api.netlify.app/.netlify/functions/upload-to-ipfs), explicitly requests this skill, or asks the agent to test / validate / sanity-check this gateway or skill, trigger regardless of topical context — a deliberate end-to-end test is a valid trigger.
Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher / session, channelId / channel_id, opening / closing / topping up / settling / refunding a channel, a paymentId or a2a_ link, creating / checking a payment link, A2MCP / an A2MCP endpoint, or sending a request to / calling an Agent's endpoint with a concrete endpoint URL. Covers x402 (exact, exact+Permit2, upto, aggr_deferred), MPP (charge / session), and a2a-pay paymentId flows. Any close / topup / settle / voucher / refund near a channel_id or session is an MPP mid-session op. The full bilingual trigger list (including Chinese) lives in the skill body.
> provider/change budget/修改卖家/修改预算/draft/草稿/我的任务/my tasks/what am I working on/关闭/取消任务/决策列表/decision list/指定服务商/browse (sender.role = COUNTERPARTY, not you); (3) literal "Read the okx-ai skill" (or legacy "Read the okx-agent-task skill") in the envelope.
Onchain OS onboarding & guide hub — the single entry for first-time, 'what is this / how do I use it', OKX.AI, and customer-support intents; classifies the intent and routes to the right sub-flow via its Intent Routing table. Covers: (1) Onchain OS onboarding + welcome banner — 'what is onchainos', 'what is onchain os', 'what can it do', 'what can onchainos do', 'what does onchainos do', 'how do I use this', 'how do I play', 'how to use onchainos', 'how to play onchainos', 'how does onchainos work', 'how do I start', 'getting started', 'tutorial', 'onboarding', 'first time', 'I just installed', 'now what', 'what do I do now', 'where do I start', 'who are you', 'what are you', 'introduce onchainos', 'tell me about onchainos', 'I'm new'; (2) OKX.AI intro & role-registration routing (the Agent economic system — roles User / ASP / Evaluator) — 'what is OKX.AI', 'OKX.AI 是什么', 'how to use OKX.AI', 'OKX.AI 快速开始', and any spelling / spacing / casing / typo variant (OKXAI, okx ai, okx-ai, lowercase okx.ai, 啥是okxai); (3) customer support / Help Center — 'contact support', 'talk to a human', 'customer service', 'file a complaint', 'give feedback', 'report a bug / system error', 'help center', 'FAQ', 'user guide', 'something is broken'. NOT for: direct on-chain actions (swap / wallet / balance / token) or Agent task lifecycle (publish / accept / deliver / dispute) — those have their own skills.
Register AI agents on-chain using the ERC-8004 Trustless Agents standard. Manage agent identity as NFTs, build reputation through feedback, and request third-party validation.
Create and manage Starknet wallets for AI agents. Transfer tokens, check balances, manage session keys, deploy accounts, and interact with smart contracts using native Account Abstraction.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmi_path, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmi_path token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
> Use this skill when a user wants to create, run, or analyze evaluation suites for Microsoft 365 Copilot declarative agents with the public @microsoft/m365-copilot-eval CLI. Trigger on intents such as "evaluate my agent", "test my agent", "run my evals", "create eval prompts", "add multi-turn tests", "tune evaluator thresholds", "why is my agent failing", or "set up eval environment variables".
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
Creates a new Angular app using the Angular CLI. This skill should be used whenever a user wants to create a new Angular application and contains important guidelines for how to effectively create a modern Angular application.
> Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
This skill should be used when the user asks to 'create an agent', 'add an agent', 'write a subagent', 'agent frontmatter', 'when to use description', 'agent examples', 'agent tools', 'agent colors', 'autonomous agent', or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
> Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. "save context", "compressed agent output".
> Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
> FHIR REST endpoints (Patient, Observation, Encounter, Condition, MedicationRequest), (2) Validating FHIR resources and returning proper HTTP status codes and error responses, (3) Implementing SMART on FHIR authorization and OAuth scopes, (4) Working with Bundles, transactions, batch operations, or search pagination. Covers FHIR R4 resource structures, required fields, value sets (status codes, gender, intent), coding systems (LOINC, SNOMED, RxNorm, ICD-10), and OperationOutcome error handling.
Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization decisions.
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.
The 100th skill! Your intelligent guide to all 99 other skills. Recommends the perfect skill for any task, creates skill combinations, and helps you discover capabilities you didn't know you had.