Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Guidance for Microsoft Purview Compliance Manager — continuous compliance posture across Microsoft and non-Microsoft assets, mapped to 360+ regulatory templates (ISO 27001/27018/27701, SOC 2, NIST 800-53/171/CSF, PCI DSS, HIPAA, GDPR, FedRAMP, IRAP, Essential Eight, DORA, EU AI Act, etc.). Covers compliance score, improvement actions (Microsoft-managed vs customer-managed), evidence collection, assessment authoring (custom templates from CSV), multi-assessment grouping, automated testing of technical controls via Microsoft 365 / Defender for Cloud / Entra, evidence repository, audit-ready reports, and continuous assessment vs point-in-time. WHEN: Compliance Manager, compliance score, regulatory assessment Purview, NIST 800-53 assessment, ISO 27001 evidence, FedRAMP assessment, custom compliance template, improvement action, technical control automation, audit evidence M365, DORA assessment, EU AI Act assessment. DO NOT USE for Defender for Cloud regulatory dashboard (use defender-for-cloud-hardening), Records Management (use purview-records-management), or M365 secure score only.
Build a component the way a library author would. Decide primitive versus hand-rolled, cover the full state matrix, design the API by composition, style through data attributes, keep it controlled or uncontrolled deliberately, and pick the right library for the job from a short trusted list instead of installing whatever is first on npm. Use when creating or refactoring a button, input, menu, dialog, drawer, toast, tooltip, table, command palette, tabs, or any reusable piece of UI.
Compound Engineering workflow for AI-assisted development. Use when planning features, executing work, reviewing code, or codifying learnings. Follows the Plan → Work → Review → Compound loop where each unit of engineering makes subsequent work easier. Triggers on: plan this feature, implement this, review this code, compound learnings, create implementation plan, systematic development.
When the user is making long-term investment, savings, or growth decisions and needs to understand the power of time and compounding, or is troubled by short-term fluctuations. Language signals: "how long should I hold", "what happens in ten years at X% annualized", "why is long-term holding better than frequent trading", "how do small gains become great wealth". Not applicable to: short-term trading decisions or analyses that do not need a time dimension.
Check and configure Skaffold for project standards. Use when checking Skaffold configuration compliance for a Kubernetes project, fixing port forwarding security issues (0.0.0.0 binding), adding dotenvx hooks for secret generation, upgrading Skaffold API version, or creating a standard skaffold.yaml from template.
When the user wants to optimize container loading, load shipping containers efficiently, or maximize container utilization. Also use when the user mentions "container packing," "FCL optimization," "LCL consolidation," "container stuffing," "cargo optimization," "shipping container loading," or "container utilization." For pallet-level optimization, see pallet-loading. For general 3D packing, see 3d-bin-packing.
Paste in raw internal team notes, Slack messages, or email threads with feedback on a creator's content draft and receive a clear, constructive, ready-to-send revision request for the creator. This skill should be used when turning internal feedback into a creator-friendly revision request, cleaning up messy team feedback before sending to a creator, writing a content change request for an influencer, converting brand manager notes into creator revision instructions, translating legal or compliance feedback into plain language for a creator, consolidating scattered feedback from multiple reviewers into one message, drafting a content revision DM or email for an influencer, or preparing approval notes to send after internal review. For building the original content brief, see creator-content-concept-generator. For checking content against brief requirements, see content-to-brief-compliance-checker. For FTC disclosure issues, see ftc-disclosure-spot-checker.
Generate a structured content calendar for any brand, product, or creator. Use when asked for a content plan, editorial calendar, social media schedule, or weekly/monthly content strategy. Produces a calendar with topics, formats, channels, and copy hooks.
Builds a month of social media post ideas for SMBs. Takes brand context, platforms, and goals and produces a structured content calendar with post topics, formats, angles, and visual direction for each slot. Output saves to context/content-calendar.md for use by /caption-writer and /social-creative-designer. Supports Instagram, LinkedIn, Facebook, TikTok, and X.
Takes activated influencers and their deliverables and generates a structured monitoring checklist specifying what to capture on each platform, when to check, and what to do if content goes missing. This skill should be used when building a content monitoring plan for a creator campaign, creating a checklist to track influencer deliverables across platforms, setting up a capture schedule for Instagram Stories before they expire, planning when to screenshot or capture creator posts, building a monitoring cadence for TikTok and YouTube deliverables, organizing content capture across multiple creators and platforms, making sure no creator content slips through the cracks, preparing a content tracking plan before a campaign goes live, or setting up a system to catch expiring Stories and time-sensitive posts. For checking whether submitted content matches the brief, see content-to-brief-compliance-checker. For tracking which creators have posted versus who is overdue, see creator-posting-compliance-tracker.
Comprehensive overview of ALL Coval platform resources, their hierarchy, relationships, API endpoints, and ID formats. Use when user asks about Coval resources, data model, how things relate, what endpoints exist, or needs context about the platform structure before making API calls.
"Scaffolds new Aptos projects using npx create-aptos-dapp. Supports fullstack (Vite or Next.js) and contract-only templates with network selection and optional API key. Triggers on: 'build app', 'create app', 'make app', 'new app', 'build dApp', 'create dApp', 'new dApp', 'build project', 'new project', 'create project', 'scaffold', 'start project', 'set up project', 'build me a', 'I want to build', 'make me a', 'help me build'."
Generate self-contained HTML reports that make analyses, comparisons, research findings, progress, and plans easy to use for decision-making. Use for requests such as “make an HTML report”, “summarize this in a report”, “visualize the comparison”, “show it in a chart”, “make a Gantt chart”, “make it look like a dashboard”, or “make this easier to read”. Choose appropriate formats from KPI, tables, bar, line, scatter, heatmap, waterfall, donut, radar, and Gantt based on the data and relationships to convey, and generate a single accessible, responsive, print-ready HTML file.
Author, review, or refactor a skill for the SAP Fiori Tools / open-ux-tools ecosystem. Use this skill whenever the user wants to create a new skill, rewrite an existing one, add references, split an oversized SKILL.md, enforce the `sap-fiori-<feature>` naming convention, validate frontmatter, add CAP/RAP samples, declare OData V2 vs V4 requirements, mark a skill as internal (developer-facing) or external (public), or produce a verification checklist — even if the user does not explicitly say "skill". Enforces host-agnostic tooling, canonical fallbacks, explicit scope boundaries, and progressive-disclosure chunking (<500 lines per file).
This skill should be used when the user asks to generate an image, create an AI image, produce a product image, generate a visual from a prompt, or check and continue an existing image generation task. Generates images through CreatOK's image generation API and can also recover interrupted generation flows from an existing task id.
Analyze a creator negotiation scenario and generate strategic response options with trade-off analysis and suggested language. This skill should be used when a creator counters with a higher rate, an influencer pushes back on deliverables, a negotiation stalls and you need to re-engage, a creator objects to exclusivity or usage rights terms, you need help responding to a creator's counter-offer, figuring out what to say when a creator asks for more money, handling a creator who wants fewer deliverables, drafting a response to a stalled creator deal, navigating a tricky influencer negotiation, or deciding whether to accept or counter a creator's rate. For estimating fair rates before negotiating, see creator-rate-estimator. For writing initial outreach messages, see creator-outreach-sequence-generator. For classifying a batch of creator replies, see reply-triage-classifier.
CTF cryptography attack techniques. For CTF crypto challenges such as RSA/AES/ECC/lattice cryptography/PRNG/ZKP/classical ciphers. Use when encrypted data needs cracking, on cryptography-related CTF problems, when weaknesses in encryption algorithms need analysis, or when ciphertext/public keys/cryptographic parameters are identified. Covers the full range of cryptographic attack and defense techniques, from classical substitution ciphers to modern public-key cryptography, elliptic curves, lattice attacks, and zero-knowledge proofs
CTF binary exploitation (Pwn) techniques. Use when a challenge provides an ELF/PE executable and opens an nc port, or when stack overflow/heap overflow/format string/UAF vulnerabilities are present. Covers ROP chain construction, heap exploitation (tcache/House of Orange/Spirit), kernel exploitation, seccomp sandbox escape, and writing pwntools automated exploit scripts
Daily news briefing aggregator that fetches and delivers content from 5 sources — Readhub (Chinese tech news), Karpathy-recommended RSS feeds (92 HN popular blogs), GitHub Trending, Hacker News top stories, and V2EX hot topics — with summaries for each item. Use when setting up a daily automated briefing, running an on-demand news digest, or configuring a morning push notification via cron. Triggers on "每日资讯", "daily briefing", "早报", "新闻推送", or requests to aggregate news from HN/GitHub/V2EX/Readhub.
DDEV local development environment guidance for Docker-based PHP/Node projects. Use when: (1) running CLI tools (composer, npm, wp, drush, artisan, console, etc.) in a DDEV project, (2) executing commands inside DDEV containers, (3) working in a subdirectory of a DDEV project (e.g., wp-content/plugins/my-plugin), (4) managing databases, snapshots, or project lifecycle with DDEV, (5) any task involving ddev exec, ddev ssh, or ddev start/stop.
This skill should be used when cleaning up codebases that have accumulated dead code, redundant implementations, and orphaned artifacts — especially codebases maintained by coding agents. Triggers on "find dead code", "clean up unused code", "remove redundant code", "prune this codebase", "dead code sweep", "code cleanup", or when a codebase has gone through multiple agent-driven refactors and likely contains overlooked remnants. Systematically identifies cruft, categorizes findings, and removes confirmed dead code with user approval.
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Management APIs for projects, API keys, members, invites, requests, usage, billing, models, and agent think-model discovery. Covers `client.manage.v1.*` plus `client.agent.v1.settings.think.models.list()`. Use `deepgram-js-voice-agent` when you want to run an agent live rather than administer projects or inspect models. Triggers include "management API", "list projects", "API keys", "members", "invites", "usage stats", "billing", "list models", and "manage.v1".
When a feature is requested, use this skill before implementation to clarify requirements, design direction, and acceptance criteria through dialogue with the user, then create a requirements definition document (Markdown). Use when the user says “I want to build…”, “add or modify a feature…”, “make it possible to…”, or “define the requirements”, as well as when implementation is requested before the specifications are settled. Do not implement. For plan reviews, see review-plan.
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.