Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Add Arcjet security protection to HTTP routes, AI agent tool calls, MCP servers, background jobs, and queue workers. Covers rate limiting, bot detection, email validation, prompt injection, sensitive information blocking (including Rampart NER), content moderation, capture/flush, remote Guard policies, typed inputs, and abuse prevention. Works in JavaScript/TypeScript, Python, and Go. HTTP frameworks share this skill. JS Guard adapters that ship on npm are per-adapter reference files loaded from Step 3 — do not keep the whole JS Guard reference in context. Official Python adapters (including Google ADK) have dedicated integrate-arcjet-guard skills, as do JS Cloudflare Think and Microsoft Agent Framework for Go. Use when the user wants security, rate limiting, bot protection, or abuse prevention – "protect my API," "rate limit tool calls," "block bots," "secure my endpoint," or "prevent abuse" – even without naming Arcjet.
Three-part workflow to improve overall codebase health with jscpd — find and fix duplicated code, find and remove or refactor dead code, then find and simplify the largest/most complex files. Starts from --dashboard/--health to prioritize and ends by re-measuring the score.
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
Expert blueprint for UI themes using Theme resources, StyleBoxes, custom fonts, and theme overrides for consistent visual styling. Covers StyleBoxFlat/Texture, theme inheritance, dynamic theme switching, and font variations. Use when implementing consistent UI styling OR supporting multiple themes. Keywords Theme, StyleBox, StyleBoxFlat, add_theme_override, font, theme inheritance, dark mode.
When the user wants to improve their ability to address prospect concerns, overcome resistance, or respond to pushback without being defensive. Also use when the user mentions "handling objections," "overcoming resistance," "common objections," "prospect pushback," "they said no," or "dealing with concerns."
Code refactoring best practices based on Martin Fowler's catalog and Clean Code principles (formerly refactoring). This skill should be used when refactoring existing code, improving code structure, reducing complexity, eliminating code smells, or reviewing code for maintainability. Triggers on tasks involving extract method, rename, decompose conditional, reduce coupling, or improve readability.
Enterprise integration solutions using SAP Integration Suite on BTP. Covers Cloud Integration (iFlows), API Management, Event Mesh, Edge Integration Cell, Integration Advisor, Trading Partner Management, and Migration Assessment. Use for building integration flows, managing API proxies, event-driven architectures, B2B/EDI integrations, hybrid deployments, adapter configuration, Groovy/JavaScript message processing, and troubleshooting.
Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.
Apply substantive quality and reliability grading to Ane's MEL/SRHR system (Ann/Vi/Li/Researcher team + wiki + harness + three-repo architecture): letter grades on 9 components and 10 dimensions plus OECD-DAC adapted criteria, three concrete risks, what an external evaluator would still want, and recommendations for moving the grade, with a mandatory self-grading bias note. Use when Ane types /grade-system, /grade, /quality-grade, /rate-system, or asks how good the system is. Honest grading, not flattery. Different from /system-audit (finds specific issues to fix; this grades overall quality posture).
Create portfolio- or client-ready case studies from project notes, resume bullets, or outcome data—with a credible narrative arc, process evidence, quantified impact, and visual storytelling intent. Use when the user asks for a case study, portfolio piece, project writeup, work sample, or client success story. Create case studies with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets them focus on semantic content and design intent while automatically handling layout, typography, and formatting complexity.
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legal_hold fields in _log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
Aggregate news from popular cryptocurrency RSS feeds, analyze sentiment of articles, and calculate an overall market sentiment score with detailed explanation. Use when assessing crypto market sentiment for trading decisions, research, or monitoring trends from RSS sources.
Publish and deploy C# MCP servers. Covers NuGet packaging for stdio servers, Docker containerization for HTTP servers, Azure Container Apps and App Service deployment, and publishing to the official MCP Registry. Use for: packaging stdio MCP servers as NuGet tools, creating Dockerfiles for HTTP MCP servers, deploying to Azure Container Apps or App Service, publishing to the MCP Registry at registry.modelcontextprotocol.io, configuring server.json for MCP package metadata, setting up CI/CD for MCP server publishing. Do not use for: publishing general NuGet libraries (not MCP-specific), general Docker guidance unrelated to MCP, creating new servers (use mcp-csharp-create), writing tests (use mcp-csharp-test).
IRAC-scaffolded case analysis memo with research gaps flagged — the scaffold, not the analysis. Rule blocks are RESEARCH NEEDED, Application is STUDENT ANALYSIS prompts, Conclusion is blank. Use when a student needs to scaffold a case analysis memo, write up their analysis, or build an IRAC memo for a case.
You MUST use this when the user asks to take a GitHub issue through the agentflow workflow, with manual stage approvals or a single --auto invocation. Owns intake, clarification, planning, implementation, review, handoff and resumable orchestration. Delivery consumes the installed owner's G3 helpers through explicit current project callbacks and proofs; unknown delivery contracts block their actions. Not for writing a standalone spec, executing an existing plan without issue orchestration, or bypassing project permissions.
Diagnoses why ROCm, the HIP SDK, PyTorch, or llama.cpp is broken on an AMD GPU on Linux, Windows, or WSL2, then applies a low-risk fix with consent or hands back the exact next step. Also routes Lemonade, LM Studio, and Ollama problems to the right upstream channel. Use when the user reports that ROCm or HIP "isn't working", torch.cuda.is_available() is False, rocminfo / hipInfo can't see the GPU, or hits hipErrorNoBinaryForGpu, HSA_STATUS_ERROR_INVALID_ISA, "invalid device function", "no kernel image is available", cannot open /dev/kfd, permission denied on /dev/kfd, "ROCk module is NOT loaded", a missing libamdhip64.so / amdhip64_6.dll / hipblas.dll / vcruntime140_1.dll, an HSA_OVERRIDE_GFX_VERSION page fault, an iGPU+dGPU crash, a container that can't see the GPU, or a repo-native package-manager install (formerly `amdgpu-install`) / DKMS failure. Backed by the `rocm` CLI (`rocm examine` / `rocm diagnose` / `rocm fix`); this skill is a thin driver over those commands, not a re-implementation.
Build flexible card layouts for displaying content in React. The Card component is a lightweight container that supports headers, images, action buttons, horizontal layouts, and integration with other Syncfusion components. Use this skill whenever the user needs to create cards, build card-based UIs, display content cards, add action buttons to cards, customize card layouts, or embed components within cards.
Believable agent cost report for any period, defaulting to the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED); measured provider spend when a sanctioned source exists; note-taker cost separate; Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Extracts Feishu/Lark Docs, Wiki, Sheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API — no LLM paraphrasing, browser-DOM fallback when lark-cli can't reach content. Use whenever the source is a Feishu/Lark URL and fidelity matters — 导出飞书文档/合集/妙记转写, 把飞书 wiki 转 markdown, or archiving a collection — even if the user just says "save this". Also covers owner-exported .docx → Markdown.
Search and download images via Google Custom Search API with LLM-powered selection. This skill should be used when finding images for articles, presentations, research documents, or enriching Obsidian notes with relevant visuals. Supports simple queries, batch processing from JSON config, automatic config generation from terms, and full note enrichment with automatic image insertion below headings.
Writes high-converting, psychologically-driven hooks for paid ads, TikTok, Instagram Reels, and organic content. Use this whenever a user wants to write hooks, opening lines, scroll-stoppers, or attention-grabbing openers for ads or social content. Trigger for any request involving "write me hooks," "give me hooks for," "I need hooks for my ad," "TikTok hooks," "hook ideas," or any variation of wanting compelling opening lines for advertising or social content. Also use when a user provides a product, persona, messaging angle, or awareness stage and wants tactical hook execution — especially when used downstream from the Creative Strategy Engine.
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers include title slide image, thumbnail with text, on-image text, legible text in image, brand color palette image, bounding-box layout, Ideogram.
Use when the user mentions "analyze the project", "analyze the repository", "analyze GitHub", "project analysis", "source code analysis", "architecture analysis", "code analysis", "study this project", "research this framework", "see how this library is implemented", "compare two projects", "project review", or "framework review"
Create engaging, authentic LinkedIn posts like a Top Voice. Use this skill when asked to write LinkedIn content, social media posts for LinkedIn, professional thought leadership content, or help with LinkedIn engagement strategy. Triggers include requests for LinkedIn posts, professional social content, thought leadership pieces, or viral/engaging LinkedIn content.
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to HTML-string audits.
Drafts board or committee meeting minutes in your house format. Auto-detects upcoming board and committee meetings from your calendar, asks for the agenda and any slides or pre-read materials, and produces a complete draft in the format learned from your seed minutes. Also handles written consents in lieu of meetings. Trigger: \"board minutes\", \"draft minutes\", \"upcoming board meeting\", \"committee minutes\", \"written consent\", or calendar detection of an upcoming board or committee event.
Dynamic linking skill for Linux/ELF shared libraries. Use when debugging library loading failures, configuring RPATH vs RUNPATH, understanding soname versioning, using dlopen/dlsym for plugin systems, LD_PRELOAD interposition, or controlling symbol visibility. Activates on queries about shared libraries, dlopen, LD_LIBRARY_PATH, RPATH, soname, LD_PRELOAD, symbol visibility, or "cannot open shared object file" errors.
Feishu Bitable (Bitable/Base) operations. Built on the base/v3 API, supporting full view configuration writes, record upsert, batch record retrieval, record attachment upload and download, record revision history, role CRUD plus collaborator add/remove, Bitable rename and advanced permission toggles, data aggregation queries, dashboard and dashboard block CRUD, form and form question CRUD, and workflow CRUD. Use when the user asks to "create a Bitable", "work with data tables", "add records", "query records", "manage fields", "Bitable", "base", "bitable", "data table", "view sorting", "view filters", "view grouping", "role", "advanced permissions", "advperm", "data aggregation", "data query", "dashboard", "form", "workflow", "record attachments", or "duplicate a Bitable". Supports --as bot|user|auto identity switching: auto is the default (User first, Tenant as fallback); --as bot operates Bitable with an App Token, needs no auth login, and never expires, making it suitable for cron, unattended use, and scripts that automatically fetch Bitable content. Also use this skill for anything involving "reading or writing bitable with an App Token", "fetching a Bitable without logging in", "scheduled Bitable sync with cron", or "bitable reporting that a User Token is required / no permission with 91403".
Intake a new matter — uniform questions covering identification, conflicts, source, risk triage, materiality, outside counsel, owners, legal hold, and key dates; writes matter.md and history.md and appends a structured row to _log.yaml. Use when the user says "new matter", "intake this matter", or wants to bring a new matter into the portfolio.
Use this skill whenever the user wants to archive a URL, bypass a paywall, look up an existing archive, view a cached version of a webpage, pull article text from archive.today or the Wayback Machine, or batch-archive a list of URLs. archive.today + Wayback Machine CLI with lookup-before-submit, automatic fallback when one backend is down, and agent-friendly output. No API key required. Triggers on phrasings like 'archive this article', 'bypass the paywall on this link', 'grab the cached text', 'save this url to archive.today', 'check if this was already archived', 'bulk archive these 20 URLs'.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.