GITHUB AGENT SKILLS / 技能收录

给你的 AI 助手
装上专业技能

我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

zkos-labs
zkos-labs/bastion

cross-chain-clustering-techniques-agent

Guides multi-chain wallet and entity clustering using public bridge traces, wrapped-asset flows, temporal and behavioral heuristics, unified graphs with chain-prefixed addresses, and confidence scoring. Use when the user asks for cross-chain clustering, bridge hop analysis, multichain scam or phishing infrastructure mapping, laundering-pattern education from observable flows, or Arkham/Nansen-style entity graphs-without claiming ground-truth identity from heuristics alone.

★ 3
zkos-labs
zkos-labs/bastion

cmichel-smart-contract-auditor-guide

Points to Christoph Michel’s (cmichel.io) long-form guide on becoming a smart contract security auditor-EVM-centric learning path, CTFs, canonical DeFi contracts, finance basics, and an FAQ (tools, scoping, compensation). Use when the user asks how to start in Solidity/EVM auditing or cites this article-not as current salary data, job placement advice, or a substitute for hands-on practice and primary documentation.

★ 3
zkos-labs
zkos-labs/bastion

chainalysis-sanctions-screening

Routes to Chainalysis public Sanctions Screening surfaces-the free Sanctions REST API (address checks against OFAC SDN crypto listings) and the EVM on-chain oracle-plus how they differ from paid Chainalysis customer data. Use when the user references Chainalysis sanctions tooling, public.chainalysis.com, or repo notes in Chainalysis.md-not for legal conclusions, full vendor ToU reproduction, or substituting official government sanctions lists.

★ 3
zkos-labs
zkos-labs/bastion

blockchain-spider-toolkit

Points to the BlockchainSpider open-source Python/Scrapy toolkit for collecting on-chain data-transfer subgraphs around an address or tx, EVM and Solana block/transaction ingestion, receipts/logs, and optional label plugins. Use when the user wants to build datasets, offline traces, or research pipelines alongside blockchain-analytics-operations and solana-tracing-specialist-not as a substitute for RPC provider ToS, rate limits, or legal review of sensitive crawls.

★ 3
zkos-labs
zkos-labs/bastion

blockchain-intelligence-playbook

Index skill for the blockint-skills bundle-includes a “choosing a skill” routing map and routes to focused skills on blockchain intelligence fundamentals, address clustering, analytics, tokenomics, investigation ethics, Phalcon Compliance documentation pointer, Chainalysis public Sanctions API/oracle router, FATF official AML/CFT glossary, Arkham Intel research article on leading crypto analysis tools for traders, Christoph Michel cmichel.io guide on becoming an EVM smart contract auditor, risk exposure, behavioral risk, address and transaction screening workflow concepts, Range AI investigation playbook (MCP), standalone Dune Sim and Dune Analytics on-chain analytics skill (dune-sim-onchain-analytics), crypto market mechanics, OSINT (Bellingcat toolkit), Solana external stacks (Helius, Range MCP, Tavily, PayAI, React Flow, Solana Policy Institute), DeFi/MEV/rug skills, privileged-access mitigation lessons (Chainalysis Drift case study), coral-xyz sealevel-attacks Solana security examples, Neodyme Solana Security Workshop (workshop.neodyme.io), Osec (osec.io) Solana auditor introduction blog post, canonical X post citation for @armaniferrante status 1411589629384355840, BlockchainSpider open-source data collection, MoTS (Know Your Transactions / transaction semantics research repo), Impersonator dApp devtools (EVM + Solana read-only address presentation), Katana web crawling, lcamtuf American Fuzzy Lop (AFL) classic documentation (lcamtuf.coredump.cx/afl), and the official Agent Skills open-format specification (agentskills/agentskills, agentskills.io/llms.txt doc index). Use when the task spans multiple topics or the user needs help picking which named skill to load.

★ 3
zkos-labs
zkos-labs/bastion

blockchain-intelligence-fundamentals

Explains what blockchain intelligence is, standard tool categories (explorers, dashboards, tracers, visualizers), and traditional vs crypto payment rails context. Use when the user asks what blockchain intelligence means, how to read on-chain data at a high level, SWIFT vs settlement, stablecoin rails, or which classes of tools exist for chain analysis.

★ 3
zkos-labs
zkos-labs/bastion

blockchain-analytics-operations

Describes how blockchain analytics platforms work in practice, typical use cases (markets, compliance, law enforcement, tax, market integrity), tool layers like visualizers and tracers, and limitations of heuristic attribution. Use when the user asks about blockchain analytics for AML, transaction monitoring, forensic tracing, institutional ops, or taint-style analysis at a high level.

★ 3
zkos-labs
zkos-labs/bastion

bellingcat-investigation-toolkit

Routes investigators to Bellingcat's Online Open Source Investigation Toolkit (tool catalog, GitBook, GitHub repo) for discovering and citing OSINT tools and workflows beyond chain-only work. Use when the user asks for Bellingcat toolkit, general OSINT tool discovery, open-source investigation resources, or methodology pointers to complement blockchain tracing-not for bypassing laws, harassment, or non-consensual deanonymization.

★ 3
zkos-labs
zkos-labs/bastion

behavioral-risk-screening-concepts

Educational map of behavioral risk screening-volume, velocity, and transit-style heuristics at address and transaction level. Use when the user asks about suspicious pattern detection, structuring-like activity, rapid fund movement, or AML-style behavior rules-not for tuning systems to evade monitoring or for legal conclusions.

★ 3
zkos-labs
zkos-labs/bastion

bastion-trust-runtime

Integrate Bastion programmable policy enforcement with trustless-ai agents. Compose ERC-8004 identity + ERC-8263 anchor proofs + ERC-8281 OCP commitments with Bastion's policy engine and human-in-the-loop gate. Use when building agents that need enforceable trust rules, multi-chain execution, or recompute-able audit trails.

★ 3
zkos-labs
zkos-labs/bastion

bastion-how-to-use

Guides agent developers on integrating Bastion (Programmable Trust Runtime). Covers SDK usage (BastionClient), REST API endpoints (/simulate, /policy, /override, /logs), interpreting audit logs and simulation results, configuring policy rules (allowlists, SOL caps, rate limits, blockint security checks), on-chain program interaction (audit trail, agent registry, circuit breaker), and deployment. Use when the user asks about integrating an AI agent with Bastion, sending transactions through the trust runtime, configuring security policies, reading audit trails, or deploying Bastion alongside autonomous agents.

★ 3
zkos-labs
zkos-labs/bastion

armaniferrante-x-status-solana-reference

Canonical pointer to Armani Ferrante’s X (Twitter) post at status id 1411589629384355840 for primary-source citation in Solana/Anchor/Coral-adjacent discussions. Use when the user cites this exact URL or needs a stable bookmark alongside sealevel-attacks-solana-not as a substitute for opening the post for verbatim text, thread context, or current Anchor documentation.

★ 3
zkos-labs
zkos-labs/bastion

arkham-leading-crypto-analysis-tools

Points to Arkham Intelligence’s public research article that surveys leading crypto analysis tools for traders and investors, organized around fundamental, technical, and on-chain analysis. Use when the user asks for a tool landscape for trading or research, cites Arkham “leading tools” content, or wants a high-level map next to blockchain-intelligence-fundamentals-not investment advice, not an endorsement of listed products, and not a substitute for reading each tool’s terms and primary data sources.

★ 3
zkos-labs
zkos-labs/bastion

agentskills-specification

Points to the official Agent Skills open-format-agentskills/agentskills on GitHub, agentskills.io docs (including llms.txt index: Overview, What are skills?, Specification, Integrate skills into your agent). Use when the user asks how Agent Skills work, SKILL.md structure, integration, contributing, or aligning blockint skills with the upstream format-not as a substitute for reading the live specification and LICENSE terms in the upstream repo.

★ 3
zkos-labs
zkos-labs/bastion

address-screening-workflow-concepts

Educational map of address-centric compliance screening-tags vs markers, single and bulk import, address list and detail views, audit trails, blacklist and whitelist policy effects, and delete behavior. Use when the user asks how commercial screening UIs organize wallets/contracts, KYA-style exports, or rescreen policies-not for legal advice or bypassing controls.

★ 3
zkos-labs
zkos-labs/bastion

address-clustering-attribution

Explains blockchain address clustering heuristics (UTXO common-input ownership, account-based deposit sweeps), entity and label layers, attribution confidence, peel chains and taint-style tracing concepts, and operational caveats. Use when the user asks about wallet clustering, linking addresses to the same owner, exchange deposit patterns, attribution, deanonymization limits, or how analytics firms group addresses.

★ 3
UnB-COMNET
UnB-COMNET/REIN

video-qoe

Maps video quality, QoE and streaming complaints about a client to the cdn-qoe service.

图像与多媒体
★ 3
UnB-COMNET
UnB-COMNET/REIN

topology-context

Clients, CDN servers, PoPs and installed intents, generated from the live inventory.

★ 3