AGENT SKILLS · 任务装备
值得安装的 Agent Skills
汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。
- 目录范围
- 已验证
- Skills
- 22,719
- 仓库
- 3485
- 最近同步
- 2026年10月31日
youdotcom-ossyou-finance
Answer finance and market-data questions with the You.com you-finance MCP tool: stock prices, tickers, earnings, company financials, and market trends, with payment-aware fallbacks for keyless hosts.
- 1小时安装量
- 1
- GitHub Stars
- 87
- 最近更新
- 10月10日
agents365-aimermaid-skill
Generate Mermaid diagrams (.mmd) and export to PNG/SVG/PDF using mmdc CLI or Kroki API. USE THIS SKILL when user mentions diagram, flowchart, sequence diagram, class diagram, ER diagram, state machine, architecture, visualize, git graph, 画图, 架构图, 流程图, 时序图, 类图, ER图, 甘特图, 状态机. PROACTIVELY USE when explaining ANY system with 3+ components, API flows, authentication sequences, class hierarchies, database schemas, or state machines. Supports 17+ diagram types with fully automatic layout.
- 1小时安装量
- 1
- GitHub Stars
- 84
- 最近更新
- 10月3日
unitoneaialert-triage
Guides structured triage of security alerts using a four-phase methodology (collect, correlate, classify, escalate) mapped to MITRE ATT&CK v16 and aligned with NIST SP 800-61 Rev 2 incident handling guidelines. Auto-invoked when the user discusses alert investigation, asks "is this a true positive?", or shares alert data requiring disposition. Produces a triage decision with priority assignment, disposition category, and escalation recommendation.
- 1小时安装量
- 1
- GitHub Stars
- 82
- 最近更新
- 6月18日
unitoneaicve-triage
Triages and prioritizes CVEs using CVSS 4.0, SSVC 2.1 decision trees, EPSS scores, and CISA KEV catalog cross-referencing. Auto-invoked when a CVE ID is mentioned, vulnerability scan results are shared, or the user asks "should we patch this?" Produces a prioritized remediation recommendation with SLA assignment and business risk context.
- 1小时安装量
- 1
- GitHub Stars
- 82
- 最近更新
- 6月18日
unitoneaiiam-review
Reviews identity and access management configurations against NIST SP 800-63B, NIST SP 800-207 zero trust principles, and CIS Controls v8. Auto-invoked when reviewing IAM policies, role definitions, user provisioning workflows, or when asked to assess identity security posture. Produces findings on least privilege violations, MFA gaps, stale accounts, and service account hygiene with prioritized remediation.
- 1小时安装量
- 1
- GitHub Stars
- 82
- 最近更新
- 6月18日
unitoneaiiso27001-gap
Performs an ISO 27001:2022 gap analysis against the full ISMS requirements (Clauses 4-10) and all 93 Annex A controls reorganized into four themes. Auto-invoked when discussing ISO 27001 certification readiness, ISMS implementation, or Statement of Applicability development. Identifies control gaps, scores implementation maturity, and produces a remediation roadmap aligned to the 2022 revision structure.
- 1小时安装量
- 1
- GitHub Stars
- 82
- 最近更新
- 6月18日
unitoneailog-analysis
Guides structured security log analysis across authentication, network, endpoint, and cloud audit log sources. Auto-invoked when the user shares log data, asks about suspicious events, needs help interpreting Windows Event IDs or Linux auth logs, or is establishing baselines for anomaly detection. Produces log source taxonomy, anomaly identification, baseline recommendations, and correlation findings mapped to MITRE ATT&CK v16 techniques.
- 1小时安装量
- 1
- GitHub Stars
- 82
- 最近更新
- 6月18日
unitoneaisoc2-gap
Performs a SOC 2 Type II readiness gap analysis against AICPA Trust Services Criteria. Auto-invoked when discussing SOC 2 compliance, audit preparation, or security program maturity. Walks through all Common Criteria (CC1-CC9) plus selected additional criteria, identifies gaps, and produces a remediation roadmap with evidence requirements and 90-day action plan.
- 1小时安装量
- 1
- GitHub Stars
- 82
- 最近更新
- 6月18日
unitoneaithreat-modeling
Runs a structured STRIDE threat model on any system design, API specification, or codebase. Auto-invoked when the user discusses architecture, shares a system diagram or design document, or asks "what could go wrong?" Produces threat actor profiles, component-threat matrix, a threat register with STRIDE classification, data-flow diagram template, trust boundary identification, and prioritized mitigations mapped to MITRE ATT&CK techniques.
- 1小时安装量
- 1
- GitHub Stars
- 82
- 最近更新
- 6月18日
unitoneaizero-trust-assessment
Performs a Zero Trust Architecture maturity assessment against NIST SP 800-207 and the CISA Zero Trust Maturity Model v2. Evaluates all five CISA ZT pillars (Identity, Devices, Networks, Applications & Workloads, Data) across maturity stages. Covers microsegmentation readiness, continuous verification, and produces a pillar-by-pillar maturity scorecard with remediation roadmap.
- 1小时安装量
- 1
- GitHub Stars
- 82
- 最近更新
- 6月18日
quark-clouddrivequarkclouddrive
夸克网盘官方(Quark Drive)Skill，用于文件上传/下载（支持断点续传）、文件分享与转存、转存分享更新查询、网盘文件搜索、批量重命名与整批撤销、文件归类移动与撤回、相册整理、AI助手（文件总结与知识问答，支持万级文件）、获取会员开通链接。当用户要求将当前搜索结果批量重命名、一句话说明范围与命名规则后重命名、整批撤销刚才的重命名、开通或续费夸克网盘会员，或需要其他夸克网盘操作与身份验证时使用。
- 1小时安装量
- 1
- GitHub Stars
- 59
- 最近更新
- 10月10日
duneanalyticsdune
Dune CLI for querying blockchain and on-chain data via DuneSQL, searching decoded contract tables, managing saved queries, managing visualizations, managing dashboards, and monitoring credit usage on Dune. Use when user asks about blockchain data, on-chain analytics, token transfers, DEX trades, smart contract events, wallet balances, Ethereum/EVM chain queries, DuneSQL, visualizations, charts, dashboards, or says \"query Dune\", \"search Dune datasets\", \"run a Dune query\", \"create a dashboa
- 1小时安装量
- 1
- GitHub Stars
- 53
- 最近更新
- 9月14日
joneqianwechat-miniprogram
WeChat Mini Program development framework. Use for building WeChat mini apps, WXML templates, WXSS styles, WXS scripting, component development, and WeChat API integration.
- 1小时安装量
- 1
- GitHub Stars
- 32
- 最近更新
- 2月10日
magnus919skillopt
Run controlled skill optimization cycles on any skill document. Uses kanban-based pipelines with validation gates — the methodology from Microsoft Research's SkillOpt (arXiv 2605.23904).
- 1小时安装量
- 1
- GitHub Stars
- 29
- 最近更新
- 8月7日
agentmail-toagentmail
Build with the AgentMail TypeScript or Python SDK for inbox, message, thread, draft, attachment, domain, allow/block list, pod, webhook, and WebSocket workflows, including programmatic agent sign-up, domain/DNS administration, and deliverability triage (bounces, spam, blocked mail). Use when implementing or reviewing AgentMail API code; do not use for direct mailbox operations, CLI usage, MCP setup, or framework-toolkit integration.
- 1小时安装量
- 1
- GitHub Stars
- 23
- 最近更新
- 10月6日
agentmail-toagentmail-check-email
Read, search, summarize, and triage AgentMail inboxes through the connected MCP server. Use for ANY request to look at, search, or process mail — even a simple 'search my inbox for X' or 'any new mail?'; the read workflow applies regardless of task size. Also use to summarize conversations, inspect attachments, manage read/unread labels, or find messages needing a reply; do not use for sending or drafting (agentmail-send-email), inbox administration (agentmail-manage-inboxes), or MCP connection
- 1小时安装量
- 1
- GitHub Stars
- 23
- 最近更新
- 10月6日
julianobarbosaargocd-advanced
Advanced ArgoCD operations beyond the core CLI/API — multi-cluster ApplicationSet generators, automated image updates, new-cluster bootstrapping, and workload onboarding via templated ApplicationSets. USE WHEN working with ApplicationSet CRDs (list, cluster, git, matrix, merge, SCM, pull request, plugin generators), configuring ArgoCD Image Updater (semver/digest/newest-build update strategies + git write-back), bootstrapping a new Kubernetes cluster into a multi-repo GitOps setup, registering c
- 1小时安装量
- 1
- GitHub Stars
- 13
- 最近更新
- 10月7日
blu1606vlearn-lab-authoring
Author VLearn Markdown Labs from a confirmed brief. Use whenever a user asks to create, rewrite, review, import, or publish a Lab, Codelab, assignment, starter repo exercise, or hint-python lesson.
- 1小时安装量
- 1
- GitHub Stars
- 6
- 最近更新
- 9月7日
creedantscorrect
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
- 1小时安装量
- 1
- GitHub Stars
- 5
- 最近更新
- 10月11日
creedantslanding
Let many agents write to one repository at once without collisions: a per-repository landing contract, path leases claimed before work starts, one queue that is the only writer to trunk, and a machine-wide slot governor for builds and tests. Use for 'landing', 'land this', 'merge queue', 'many agents on one repo', 'where does this work land', or before any coordinator (brigade, Orchestrate, Autopilot, swarm) delegates writing work in parallel.
- 1小时安装量
- 1
- GitHub Stars
- 5
- 最近更新
- 10月11日
creedantsprinciple-exhaust-the-design-space
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
- 1小时安装量
- 1
- GitHub Stars
- 5
- 最近更新
- 10月11日
creedantsprinciple-foundational-thinking
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
- 1小时安装量
- 1
- GitHub Stars
- 5
- 最近更新
- 10月11日
creedantsprinciple-minimize-reader-load
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
- 1小时安装量
- 1
- GitHub Stars
- 5
- 最近更新
- 10月11日
creedantsprinciple-model-the-domain
Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
- 1小时安装量
- 1
- GitHub Stars
- 5
- 最近更新
- 10月11日