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。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
on-chain-investigator-agent
Operates as an on-chain forensics investigator using only public chain data and OSINT-tracing flows across chains, clustering addresses, reviewing contracts for risk patterns, detecting scam vectors, and producing evidence-backed reports. Use when the user asks for blockchain investigation, forensic tracing, scam or rug analysis from public data, transaction trail documentation, or structured intelligence reports without private keys or insider access.
neodyme-solana-security-workshop
Points to Neodyme’s public Solana Security Workshop (workshop.neodyme.io) and its open-source mdBook source on GitHub (neodyme-labs/neodyme-breakpoint-workshop)-hands-on levels, PoC framework, and intentionally vulnerable programs for learning attack and defense on Solana. Use when the user names Neodyme workshop, the Breakpoint workshop repo, or wants a structured Solana program security curriculum alongside sealevel-attacks-solana-not for reusing vulnerable code in production or attacking live systems without authorization.
mots-transaction-semantics
Points to the MoTS (Know Your Transactions) open-source Python/Scrapy research codebase-EVM transaction acquisition, semantic-vector extraction, and Etherscan-backed action labels (WWW 2023). Use when the user cites the MoTS paper/repo, needs legacy spider names (blocks.eth, blocks.semantic.eth, labels.action), or wants to relate transaction semantics to blockchain-analytics-operations-not as a substitute for current BlockchainSpider docs, RPC ToS, or legal review.
mev-bot-rug-coordination-investigator-agent
Investigates hypotheses that MEV activity (bundles, searchers, same-block ordering) temporally overlaps or co-occurs with launch-phase rug signals-using public txs, bundle IDs, and clustering with explicit confidence. Use when the user asks about MEV plus rug coordination, launch sniper bundles, Jito or Flashbots overlap with dev exits, or joint profit-flow case studies-not for alleging collusion without evidence, harassing addresses, or live interference.
mev-bot-infrastructure-analysis-agent
Maps observable MEV searcher behavior and infrastructure from public bundles, blocks, and traces-EVM builder/relay patterns, Solana Jito bundles, strategy fingerprints, profit consolidation paths, and concentration metrics. Use when the user asks for MEV bot analysis, searcher clustering, bundle/builder mapping, private-order-flow research questions, or ecosystem centralization studies-not for running competitive bots, mempool manipulation, or harassing operators.
lcamtuf-afl-documentation
Points to Michał Zalewski’s (lcamtuf) canonical American Fuzzy Lop (AFL) documentation at lcamtuf.coredump.cx/afl-coverage-guided fuzzing concepts, afl-fuzz usage, and historical technical notes for C/C++ targets. Use when the user cites AFL classic, lcamtuf’s AFL page, or needs the original upstream reference-not as a substitute for current AFL++ docs or authorized fuzzing policy.
katana-web-crawling
Guides use of ProjectDiscovery Katana for web crawling and spidering in security testing and recon workflows. Covers installation, standard vs headless mode, scope and rate limits, JSONL output, and piping from httpx or URL lists. Use when the user mentions Katana, projectdiscovery/katana, web crawling, spidering, endpoint discovery, attack surface mapping, or chaining crawlers in automation pipelines.
impersonator-dapp-devtools
Points to Impersonator (EVM) and Impersonator Solana-open-source tools to connect to dApps via WalletConnect (and related flows) while presenting an arbitrary address for UI exploration without holding that address’s keys. Use when the user names impersonator.xyz, solana.impersonator.xyz, or the GitHub repos for local dev-not for phishing, identity fraud, or circumventing dApp or legal controls.
honeypot-detection-techniques
Educational techniques to assess honeypot-style token risk from verified source, bytecode clues, and observational on-chain history-EVM ERC-20 patterns (transfer gates, fees, blacklists), Solana SPL and Token-2022 hooks, and safe validation paths. Use when the user asks how to detect honeypots, sell-restricted tokens, scam token mechanics, or static review checklists-not for deploying scams, stealing funds, or advising high-risk mainnet test trades on unknown contracts.
flash-loan-exploit-investigator-agent
Investigates completed flash-loan and atomic DeFi incidents across EVM and Solana from public txs-borrow-execute-repay fingerprints, oracle/pool/governance vectors, full trace reconstruction, impact quantification, and mitigations. Use when the user asks for flash loan exploit analysis, atomic attack post-mortems, large-borrow suspicious tx triage, or evidence-structured case studies from explorer data and read-only simulation-not for designing new attacks on live protocols.
fatf-glossary-reference
Points to the official FATF Glossary on fatf-gafi.org for standardized AML/CFT and related terms used across FATF Recommendations and guidance. Use when the user needs authoritative definitions (e.g. CDD, ML/TF, STR, PEP, risk-based approach) in compliance or investigation writing-not as legal advice or a substitute for jurisdiction-specific law and supervisory rules.
evm-solidity-defi-triage-agent
Guides EVM Solidity DeFi triage from public verified source or bytecode-access control, proxies, oracle usage, reentrancy and CEI patterns, DEX/router integrations, and common vulnerability classes. Use when the user asks for Ethereum or L2 smart contract security review, Solidity audit triage, OpenZeppelin proxy risks, or EVM-specific DeFi patterns-not for live exploits or private keys.
ethereum-ecosystem
Comprehensive map of Ethereum trust primitives Bastion orchestrates. Covers wallets (Safe, EOA, AA), identity (ERC-8004, ENS, A2A), payments (x402, Pact), attestations (EAS, Sign, zkTLS), shared trust (EigenLayer), oracles (Chainlink, Pyth), bridges (Across, LayerZero), indexing (The Graph, Blockscout MCP), agent platforms (Olas, Virtuals), and developer tooling (ethskills, Base MCP, Foundry, Scaffold-ETH 2). Use when building on Ethereum trust standards.
dune-sim-onchain-analytics
Standalone skill for on-chain analytics and product work with Dune-choose Sim realtime APIs (EVM and SVM including Solana) vs Dune Analytics SQL, design CU-aware flows, subscriptions and dashboards, and safe key handling. Use when building or analyzing with Dune Sim, wallet or token intelligence, multichain balances and activity, or SQL over Dune datasets-not for legal sanctions conclusions or exposing API keys in browsers.
defi-security-audit-agent
Guides DeFi protocol security review and rug-risk assessment from public chain data, verified source, and historical patterns-covering EVM and Solana-style deployments, liquidity and tokenomics, governance centralization, bridges, exploit pattern matching, and evidence-structured audit reports. Use when the user asks for a DeFi security audit, rug risk analysis, contract vulnerability triage, LP lock verification, governance or upgrade risk, or cross-chain bridge review from observable data only.
defi-admin-takeover-mitigation-lessons
Mitigation patterns for privileged-access and governance-adjacent DeFi failures, anchored on the public Drift Protocol incident analysis in Chainalysis’s blog-social engineering, Solana durable nonces, oracle and collateral abuse, multisig governance, and operational monitoring. Use when hardening signer processes, reviewing admin surfaces, or teaching post-incident lessons-not for designing exploits or attributing actors without evidence.
crypto-market-structures
Summarizes descriptive concepts for max pain options theory, covered-call style crypto ETFs, crypto arbitrage families and risks, and bull/bear flag chart patterns-always as non-prescriptive education. Use when the user asks about max pain, premium income ETFs, arbitrage, funding rates, flash loans, or bull/bear flags in crypto trading context.
crypto-investigation-compliance
Maps high-level crypto crime categories, safe and ethical OSINT plus on-chain investigation workflow, and victim reporting posture. Use when the user asks about scam types, pig butchering, rug pulls, tracing stolen funds ethically, compliance-adjacent investigation, or how to document cases for authorities.