DevOps & Infra

patsnap Bundle

Build the patent-data layer for an applicant asset dashboard using Patsnap search and analytics APIs. Use when an IP analyst or developer needs applicant patent retrieval, patent-type subsets, filing trends, industry distribution, filing-office coverage, top inventors, or an innovation word cloud with documented collapse and counting rules.

zhaobenxiang5-coder Bundle

安全与逆向工程全套技能集合（Reverse Engineering & Security Suite）。涵盖 APK逆向、JS反混淆、Ghidra/IDA分析、二进制Diff、代码审计、云原生/K8s安全、漏洞挖掘与渗透工具链等全方位能力。

zhaobenxiang5-coder Bundle

Capture same-day Zhitai new-product data into the AI product pipeline console by using the project’s existing Chrome extension flow, Temu title jump, real Temu product-detail extraction, and default-workspace writeback. Use when the user asks to 抓蜘泰, 补今天蜘泰, 抓 TEMU 链接, 补 Temu详情, 回写项目台/中台, or work on flow-task-center-pro Zhitai/Temu capture.

littlebeaverstudio Bundle

金蝶云星空经营数据导出技能。仅当用户明确要求从金蝶云星空或 K3 Cloud 查询、导出经营数据时使用；支持配置账号、自动发现账套、连接自检、查询组织与可用单据/报表，按期间、组织及单据或报表类型导出多工作表 Excel，也支持追加官方字段、全组织导出、字段核对与结果二次筛选。

kakatur Skill

Design, implement, or review a batch data pipeline with explicit source and output contracts, deterministic transformations, lineage, quality handling, stable identifiers, idempotent materialization, backfill planning, and reproducible verification. Use for bounded or scheduled batch workloads; use a streaming-specific workflow for continuously processed event streams.

stofancy Skill

通用部署预检、SSH 通道修复、备份流式验证、可逆生产冒烟与回流合并检查。任何涉及远程服务器发版、rollback、生产数据写入验证的任务在动手前使用；项目专用命令以仓库内 deploy 技能/runbook 为准。

ruosong320 Skill

Write Python code in the abstraction-first style used by knowledge_graph_xm: define domain data models, abstract interfaces, strategy classes, default implementations, pipeline orchestration, dependency injection, async contracts, and verification hooks before adding concrete behavior. Use when creating or modifying project code that should be extensible, replaceable, and readable by future agents.

ruosong320 Bundle

Use for any Matrix chat work via the `xm chat` CLI: messaging (text/markdown/emote/notice/reply/edit), files/stickers/locations, history, real-time listening, daemon sessions, ACP-based AI virtual personas (`xm chat persona`), E2E encryption keys, appservice virtual identities, profiles/presence, room members, and event-triggered commands with context injection, batching, and agent session continuity. Covers all `xm chat` subcommands, event filter config (prefix/domain/regex matching, room/sender exclusion, @mention detection), and bot development. Trigger on: chat, messaging, Matrix, IM, bot, daemon session, chat trigger, virtual user, virtual persona, AI persona, chatbot, DM, room members, trigger pipeline, agent mode, XM_AGENT_SESSION, Monitor mode, XM_CHAT_USERNAME, XM_CHAT_PASSWORD, XM_CHAT_TOKEN, multi-device login, file send, sticker, location, emote, edit message, event filter, prefix filter, domain filter, persona debugging, router check, event tracing, or any room-based communication task.

ryanalexanderbrashear Skill

Open a pull or merge request for the current branch on GitHub, GitLab, Bitbucket, or Azure DevOps, with the title and description filled in from the branch's own commits using the standard PR template. Use when the user wants to open, create, raise, or draft a PR or MR for the work on the current branch.

gabson0x Skill

MCP server integrating Slither + Aderyn + SWC patterns into Claude Code for smart contract auditing. Use when analyzing Solidity files, running DeFi-specific detectors, or generating invariants. 10 MCP tools, 86 SWC detectors, DeFi preset pack, CI/CD workflow.

tahr-security Bundle

Audit application-owned secrets, cryptography, dependency reachability, infrastructure-as-code, containers, CI/CD, cloud permissions, and runtime security configuration with evidence and false-positive controls. Use for repository hardening, deployment review, leaked-key triage, dependency/CVE review, exposed debug or admin surface checks, or pre-release configuration audits.

iabuelruzz Skill

Use when working on the DISS binary file processing pipeline — filters, parsers, nav_utils, config files, service descriptors, or any part of the ground-to-space uplink data flow in this eLTS Galileo project.

gabson0x Skill

Complete reference for 28 web2 bug classes with root causes, detection patterns, bypass tables, exploit techniques, and real paid examples. Covers IDOR, auth bypass, XSS, SSRF (11 IP bypass techniques), SQLi, NoSQLi, business logic, race conditions, OAuth/OIDC, file upload (10 bypass techniques), GraphQL, LLM/AI (ASI01-ASI10 agentic framework), API misconfig (mass assignment, JWT attacks, prototype pollution, CORS), ATO taxonomy (9 paths), SSTI (Jinja2/Twig/Freemarker/ERB/Spring), subdomain takeover, cloud/infra misconfigs, HTTP smuggling (CL.TE/TE.CL/H2.CL), cache poisoning, MFA bypass (7 patterns), SAML attacks (XSW/comment injection/signature stripping), XXE, insecure deserialization, host header injection, custom header injection, clickjacking, open redirect (11 bypass techniques), WebSocket attacks, SSRF chaining, and business logic bypass. Use when hunting a specific vuln class or studying what makes bugs pay.

steve-t-hill Bundle

Use this skill to create, manage, bind, and inspect Dataplex Data Domains in Google Cloud Knowledge Catalog. Use when the user wants to organize data assets logically by business structure, authorize domains, or link BigQuery/GCS resources to a domain. Do not use for general Dataplex catalog search outside of domain contexts, or for managing "Data Products" (which package assets for distribution rather than logical ownership).

steve-t-hill Bundle

Use this skill to create, manage, bundle, and secure Data Products in Google Cloud Knowledge Catalog. Use when the user wants to package related data assets (BigQuery tables, views, GCS buckets) into curated bundles designed to solve specific business use cases or streamline access for consumers. Do not use for logical ownership organization (which is handled by Data Domains) or general catalog browsing.

steve-t-hill Bundle

Expert guidance and automated agent protocol for managing Google Cloud Knowledge Catalog Business Glossaries. This skill provides the ability to create, update, and manage glossaries, categories, and terms, as well as link terms to data assets and columns. It enforces a strict "Exhaustive Analysis" rule to ensure 100% conceptual coverage of BigQuery datasets in a single pass. Use this skill when: 1. Building a new business glossary from scratch for a BigQuery dataset. 2. Auditing existing glossaries for missing terms or technical mappings. 3. Establishing data stewardship and ownership metadata across a business ontology. 4. Linking related or synonymous business concepts to improve discoverability.

marco9442 Bundle

Skill to call Cloud API for Tencent Cloud (腾讯云). Used for cloud automation or resource management. 当用户需要查询、创建、管理腾讯云资源，或执行云 API 自动化操作时触发。

agentcorp-inc Bundle

Choose when the user needs **Shopify CLI** to run or fix something now: validate app or extension config on disk (`shopify.app.toml`, `shopify.app.<name>.toml`, `shopify.extension.toml`); run or troubleshoot store workflows (`shopify store auth`, `shopify store execute`); inventory or product changes by handle, SKU, or location name; or CLI setup, auth, upgrade issues. Emphasize **commands and operational steps**, not only authoring GraphQL. Skip for API-only understanding or codegen with no CLI execution. Examples: validate configuration before deploy; run an existing query via CLI; list products; missing `shopify store execute`.

agentcorp-inc Bundle

Builds or rebuilds the Carta Home live artifact — a Cowork dashboard home page that works for any Carta firm. Shows a live Schedule of Investments, Fund Performance benchmarks, P&L (from STATEMENT_OF_OPS), Balance Sheet (from MONTHLY_NAV_CALCULATIONS), LP Reporting, Portfolio Valuations (top holdings by MOIC), ManCo expense actuals by category, Form ADV regulatory AUM, and a Skill Directory with one-click copyable prompts. The artifact auto-detects the active firm from the Carta MCP context — no hardcoded firm name needed. Use this skill whenever the user asks to "build the carta home artifact", "rebuild carta home", "set up the carta home page", "deploy carta home", or "restore the carta home dashboard". For a company's cap table use carta-cap-table's carta-captable-home-build; for a CRM home of pipeline, deals and contacts use carta-crm's carta-crm-home-build.

agentcorp-inc Bundle

Operate the Clerk CLI (`clerk` binary) for authentication, user/org/session management, deploy verification, instance config, env keys, and any Clerk Backend or Platform API call. Use when the user mentions Clerk management tasks, "list clerk users", "create a clerk user", "update organization", "pull clerk config", "clerk env pull", "clerk doctor", "clerk deploy", "clerk deploy status", "clerk api", or any ad-hoc Clerk API request. Prefer the CLI over raw HTTP: it handles auth, key resolution, app/instance targeting, and formatting automatically.

agentcorp-inc Bundle

Focused Signals scout for PostHog projects capturing Core Web Vitals (`$web_vitals`). Watches each page's p75 LCP / INP / CLS / FCP against the absolute Google thresholds (good / needs-improvement / poor) and against its own history: pages standing in the poor band, pages crossing a band boundary after a deploy, and sharp in-band regressions. Reads the historical trajectory — not just the moment a value changes — so a page that is steadily slow surfaces even when nothing moved today. Every finding carries a metric-specific cause hypothesis and a concrete remediation. Emits only above the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet.

sumanjeet0012 Skill

Explain any technical topic, system, protocol, or data structure in crystal-clear, structured terms tailored for software engineers, DevOps, and IT professionals. Blends plain-English intuition, architecture diagrams, concrete code or CLI examples, real-world trade-offs, and common pitfalls. Use when the user asks "what is X", "how does X work", "explain Kubernetes / Kafka / OAuth / Raft", or asks for a clear technical breakdown of any concept without academic fluff.

sumanjeet0012 Skill

Set up Let's Encrypt HTTPS on an AWS EC2 Ubuntu instance for a new domain. Checks/installs certbot, inspects existing nginx vhosts without replacing them, adds a new port-80 vhost, validates DNS points to the public IP, and issues a cert with certbot --nginx. Use when the user says "link this domain to EC2", "set up let's encrypt", "enable https on this domain", "add one more domain with letsencrypt", or provides a domain plus an EC2 host.

agentcorp-inc Bundle

Turns a learning intent or an intent to practice a skill into a personalized experience: asks 3 questions (topic, familiarity, modality), searches the catalog, delivers the right learning experience (course, project, video, or roleplay), then acts as a path finder connecting users to the right Coursera learning path. Trigger when a user manifests a learning intent. Some examples of users manifesting a learning intent or a skill practice intent are: "teach me", "I want to learn X", "I need to get better at X", "upskill in", "prepare for an interview", "I keep searching this but I don't get it", "I get by but don't understand it", "I use AI for this but want a real foundation", "my team uses X and I'm lost", "I need to practice how to X", "help me prepare for X conversation". Covers technical topics (SQL, Python, data, cloud), professional interpersonal skills (negotiation, communication, leadership), certification prep, interview prep, professional tools, and new skills.

agentcorp-inc Skill

Signals scout for Content Security Policy violation reports. Watches `$csp_violation` events for blocked-URL clusters, per-directive bursts, post-deploy regressions, and suspicious third-party domains, and files each validated cluster as a report in the inbox.

agentcorp-inc Skill

Signals scout for PostHog data pipelines — CDP destinations and transformations, batch exports, and hog flows. Watches for delivery failures, degraded functions, and stalled exports against each pipeline's baseline, and files each validated delivery contradiction as a report in the inbox.

agentcorp-inc Bundle

Use this skill when authoring PolicyRuleDefinition and PolicyRuleDefinitionSet metadata XML for the Salesforce Enforce-O-Matic MDAPI (Data Cloud governance policies), or when editing *.policyRuleDefinition / *.policyRuleDefinitionSet files. Covers the category decision tree, full schema for all policy variants (ACCESS, GOVERNANCE, RECORD, TRANSFORM), UI-compatibility rules for the Data Governance Policy Builder, and validation guardrails. Do NOT use this skill for UserAccessPolicy, AccessPolicy, SharingRules, PermissionSet, or any non-Enforce-O-Matic access-control metadata — those have their own types and live outside the PolicyRuleDefinition schema.

agentcorp-inc Bundle

Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from a field, or scoping/limiting picklist values for a specific record type. Also use when users encounter field deployment errors, especially around Roll-up Summary format, Master-Detail constraints, formula issues, or a record type that won't deploy without a business process. Use this skill for custom field metadata work, field generation, and field troubleshooting. DO NOT TRIGGER for creating or customizing the value set itself — defining a new GlobalValueSet, or modifying a StandardValueSet catalog like Industry or Lead Source — use platform-value-set-generate instead; this skill covers the field that references a value set, not the value set definition.

agentcorp-inc Bundle

Develop and deploy Data Cloud Code Extensions using SF CLI plugin. Use this skill when creating custom Python transformations for Data Cloud, deploying code extensions, or testing data transformations. Supports init, run, scan, and deploy operations.

agentcorp-inc Skill

Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools — pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI is getting faster or slower, which GitHub Actions workflow is the slow or flaky long-pole, how long PRs take from open to merge, how an author's merge time compares to the cohort, which open PRs have failing or pending CI, or where a specific pull request is stuck. Triggers on "engineering analytics", "is CI getting slower", "slow workflow", "flaky CI", "time to merge", "cycle time", "PR throughput", "failing checks", "where is PR <n> stuck", "CI long pole", "what's holding up this PR".

silviobeer Bundle

Set up, run, troubleshoot, and triage SonarQube Cloud/Server analysis from Codex. Use when working with SonarScanner CLI (`sonar-scanner`), SonarQube CLI (`sonar`), SonarCloud project setup, quality gate creation/assignment/status, `sonar-project.properties`, `SONAR_TOKEN`, coverage import/LCOV merging, issue/security hotspot queries, scanner authentication failures, or confusion about which Sonar CLI to use.

dangtran1003 Bundle

Đọc Grafana fmon BSS ($GRAFANA_URL) — dashboard, panel query, PromQL, LogQL (Loki), alert rule đang firing. Dùng khi user hỏi về metric hạ tầng/K8s/MySQL/Kong, "grafana có gì", "alert nào đang kêu", "CPU/RAM/pod của service X", hoặc muốn biết một dashboard đang đo cái gì. Trigger - /grafana, "xem grafana", "check metric", "alert đang firing".

dangtran1003 Skill

Luồng chuẩn từ dấu hiệu lỗi đến MR đã có tài liệu cho BSS portal — observability → định vị code → verify → fix → MR → wiki/BDR/KB → xác minh sau deploy. Dùng khi user đưa một trace SigNoz, một issue Sentry, một ticket ISD, một alert, hoặc chỉ mô tả triệu chứng ("VM không có SG", "API trả 500", "khách báo mất firewall rule") và muốn đi tới tận cùng chứ không chỉ đọc log. Cũng dùng khi user nói "điều tra vụ này", "trace cái này xem sao", "fix rồi tạo MR luôn", "làm nốt tài liệu". Trigger - /bss-flow, "điều tra", "trace rồi fix".

dangtran1003 Bundle

Build documentation from filled markdown intake forms. AI fetches knowledge from Notion/GitHub/GDrive/URL/files, drafts content, captures screenshots via browser walkthrough, translates to multiple locales, and deploys to Docusaurus. Layered intake (project + module). Re-run safe; source change detection via lock file. Commands: init, module, fetch, run, continue, audience, plan, voice, draft, edit, walkthrough, record, translate, verify, update, categorize, deploy, publish, intake-help, help.

franky47 Bundle

Audit GitHub Actions workflows for supply-chain and CI/CD security vulnerabilities — script injection, expression injection, token exfiltration, unpinned actions, cache poisoning, and Shai-Hulud-class self-replicating worms. Use when the user asks to audit, review, or check the security of GitHub Actions, workflows, CI/CD pipelines, or asks about supply-chain risk, npm publish security, or Shai-Hulud.

dangtran1003 Skill

Use when the user asks to create/update a reviewer-facing Confluence page on $WIKI_URL — an MR/PR review doc, OR a bug/security/analysis report wiki page ("tài liệu review", "trang wiki cho MR", "tạo report wiki", "page wiki báo cáo lỗi/bảo mật", "giải thích cho team"). Produces an objective, outsider-readable page: context → how-it-works flow → why-it's-a-problem → how-fixed/impact → prioritized fixes; MR variant ends with REAL git diffs. Also covers the FCI Confluence house style + storage-format gotchas + PNG-diagram-via-REST pipeline. Examples: "tạo tài liệu review cho MR này", "update thêm vào trang wiki", "tạo page wiki report vấn đề này", "viết report bảo mật lên wiki".