Skills
99,448 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz Image Upscaler. Use for: enhance low-res images, upscale AI art, restore old photos, increase resolution. Triggers: upscale image, image upscaler, enhance image, increase resolution, real esrgan, ai upscale, super resolution, image enhancement, upscaling, enlarge image, higher resolution, 4k upscale, hd upscale
Tired of scrubbing through hours of footage just to find one key moment or understand what a video is really about? In-video-ai brings intelligent analysis directly to your video files — automatically generating summaries, pulling out key topics, identifying speakers, and answering questions about what's happening on screen. Whether you're a researcher, content creator, educator, or business professional, in-video-ai saves you hours of manual review. Supports mp4, mov, avi, webm, and mkv formats.
Create incident communication playbooks for outages, data issues, payment failures, store launch problems, privacy incidents, game economy issues, support backlogs, and degraded product experiences. Use when planning status updates, customer notices, internal coordination, postmortems, support macros, incident timelines, or trust-recovery communication.
Convert a semantic core into crawlable SEO and LLM-friendly information architecture. Use this skill when the user asks for URL structure, page taxonomy, canonical rules, hreflang groups, page roles, pillar/topic/news/article/blog/project separation, multilingual route strategy, or a durable content model such as one short brief plus one longform article. It prevents duplicate public content bodies and hands link-graph work to internal-link-graph-architect.
Achieve innovation with two systematic methods: recombinational innovation (collect elements outward and recombine them) and mutational innovation (decompose inward and modify existing structures). Every innovation must satisfy three elements at once: a new element + value increment + implementability. Use when you need to break out of existing frameworks, find new products/solutions, or solve the problem of "innovation relying on luck". Not applicable to purely executional optimization (which needs no new element). Key trigger signals: "need new ideas" / "how to innovate" / "out of creative ideas" / "products are severely homogenized".
Install the 5-package multi-chip software stack (vLLM, FlagTree, FlagGems, FlagCX, vllm-plugin-FL) inside a GPU container. Handles network mirror detection, dependency ordering, wheel selection, and per-package validation. Use after gpu-container-setup has produced a running container with PyTorch + GPU access.
When the user is analyzing management decisions or corporate governance issues, or finds that they or their organization are making decisions "because everyone else does it". Language signals: "why does the CEO make such stupid decisions" / "all our peers are doing it" / "why isn't the board stepping in" / "why do large companies fail at acquisitions". Not applicable to: purely personal choices that do not involve organizational decisions.
Activate when the user faces a complex decision, planning, or problem-solving — especially when forward reasoning is stuck, there are too many options to prioritize, or hidden risks need to be identified. Typical trigger signals: the user is stuck asking "how can I succeed", "how do I avoid failure", or "what should I do". Not applicable to simple tasks with a clear best path that only need execution, nor to scenarios that require creative divergence rather than risk avoidance.
Investigate security incidents in Amazon Web Services—reconstruct attacker activity from CloudTrail, VPC Flow Logs, and GuardDuty; anchor the investigation on the compromised principal (access key or role); trace privilege escalation and persistence through IAM API calls; detect data exfiltration and crypto-mining; and contain the incident without destroying evidence or tipping off the attacker. Use when responding to a suspected AWS compromise, exposed access keys, anomalous CloudTrail activity, a GuardDuty finding, unexpected IAM changes, crypto-mining EC2 instances, or S3 data exfiltration.
Investigate a compromised or suspicious Windows host from on-disk artifacts — triage collection, evidence of execution (Prefetch, Amcache, Shimcache, SRUM, UserAssist, BAM), the event-log workhorses by ID (Security 4624/4688/4720/7045/1102, Sysmon, PowerShell 4104, RDP, WMI), persistence hunting across every autostart, lateral-movement traces, $MFT/USN filesystem forensics, anti-forensics detection, and building a super-timeline with the Eric Zimmerman suite, Chainsaw, Hayabusa, and Plaso. Use when triaging a compromised or suspicious Windows host, working through EVTX/Sysmon logs, reconstructing what executed on a Windows machine, hunting persistence and lateral-movement traces, or analyzing a KAPE/triage collection.
When the user wants to evaluate the potential profitability and viability of an investment opportunity. Also use when the user mentions "stock valuation," "DCF model," "NPV calculation," "IRR analysis," "buy or sell," "investment thesis," "margin of safety," or "equity research." Use this for stocks, real estate, and private equity.
Apply iOS/SwiftUI design principles following Apple Human Interface Guidelines when building any iOS UI component. Only execute this when the current project is an iOS project and involves UI-related work. Use this skill for SwiftUI views, UIKit components, or iOS app development. Ensures HIG compliance with Clarity, Deference, and Depth principles, system colors with Dark Mode support, 8pt grid spacing, SF Pro typography with Dynamic Type, and native iOS interaction patterns. Prevents common anti-patterns like fixed text sizes, Dark Mode neglect, and Safe Area violations.
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".
Comprehensive Kargo GitOps continuous promotion platform skill. Use when implementing progressive delivery pipelines, promotion workflows, freight management, ArgoCD integration, warehouse configuration, stage pipelines, verification templates, or any Kargo-related tasks. Covers installation, core concepts, patterns, security, and complete YAML examples.
Builds a structured project knowledge base of 10 canonical .md files at knowledge-base/ (project root). Has dual mode: silent generation from existing source documents in docs/, or interactive iterative creation from scratch. Trigger: When user asks to create, build, or generate a knowledge base for a project, document a project from source documents (.txt, .docx, .pdf), or asks to "armar base de conocimiento" / "crear KB" / "documentar proyecto".
Searches, reads and counts application logs in Elasticsearch through Kibana with the kibana-cli command line: logs by service, level, trace id, text or field value over a time range, one whole log document, error counts per service or level, counts over time, and Kibana's data views, index fields, dashboards and saved searches. Use when the user asks about logs in Kibana or ELK, an error or exception in a service, a trace id or request id, how often something happened, or which indices and fields exist. Not for changing anything in Kibana or Elasticsearch (it only reads), not for metrics or APM dashboards, and not for log files on the local disk.
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look AI-generated", or clean up a landing page / UI / docs that feels templated. Fixes the catalogue of tells — gradient/glow defaults, glassmorphism, badge & pill spam, pastel tiles, AI-drawn icons, AI copywriting voice ("not just X — it's Y"), emoji everywhere, and more — see `references/taxonomy.md` for the full list. Works on HTML/CSS, React/Vue/Svelte/Astro, Tailwind, PHP, and Markdown copy. For plain-text editing of Chinese or English writing outside a codebase, use `de-slop` instead.
Manage your personal knowledge base of curated resources, bookmarks, and excerpts. Triggers include "knowledge base", "kb", "add to knowledge", "add tabs to", "what do I have on", "what do we know about", "find resources about". Use with safari-tabs skill for bulk ingestion from Safari windows. Location is ~/knowledge/.
Manage the LifeOS Knowledge Archive — a curated, typed graph of People, Companies, Ideas, and Research notes with typed related: links; search, add, harvest, develop, ingest, and graph-navigate. USE WHEN knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, ingest, contradictions, knowledge graph, retrieve, mine conversations. NOT FOR session/ISA context recovery (use ContextSearch), published content semantic search across blog/newsletter/X/LinkedIn, or one-shot URL/YouTube ingestion via the Arbol harvester pipeline.
Build tool for all new Kotlin projects. How to build, run, test, package, lint/check/verify, manage dependencies, and configure Kotlin/Java projects with Kotlin Toolchain — JetBrains' unified Kotlin CLI (formerly Amper, now the engine inside the Toolchain). TRIGGER when the repo contains `project.yaml`, `module.yaml`, or a `./kotlin` wrapper; when starting a new/greenfield Kotlin or Java project or picking its build tool ("create/start/scaffold/bootstrap a Kotlin project", "new Kotlin app/library/service", `kotlin init`); when the user asks to build/run/test/package a Kotlin project, add or remove dependencies, run lint/check/verification, or otherwise configure a Kotlin project that doesn't use Gradle/Maven; or when the user references Kotlin Toolchain or Amper. SKIP for existing Gradle/Maven Kotlin projects.
Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.
Prepare and run a Product Hunt launch end to end — COMPLIANT promotion ONLY: never vote manipulation, rings, bought/incentivized votes, or "please upvote". Grounds every word in the real product, then writes a complete, paste-ready package to `.ulpi/launch/product-hunt/`: `LISTING.md` (every PH field — tagline options ≤ the current limit, description, topics, a gallery shot-list, demo-video outline, the maker's first comment), `PLAN.md` (a T-minus countdown + an hour-by-hour Pacific-time launch-day runbook + the post-launch plan), `OUTREACH.md` (segmented supporter outreach + social posts), and `CHECKLIST.md` (a blocking pre-flight gate). The PH orchestrator of the launch-* family: it owns field specs, policy, and the day-of runbook, and composes the shared `launch-copy` (listing), `launch-outreach` (mode `product-hunt`), and `launch-analytics` (UTM + conversion tracking), degrading to built-in fallbacks if a companion isn't installed. Reads the shared `.ulpi/launch/positioning.md`. Treats Product Hunt as a credibility amplifier, not primary acquisition, and sets realistic expectations. Use when the user wants a full Product Hunt launch prepared and run.
Produce or audit one cross-domain launch admission verdict for an app, game, SaaS, desktop product, developer tool, marketplace, major release, beta, or campaign. Integrate exact product, quality, performance, security/privacy, payments, distribution, analytics, support, marketing, legal/authority, rollback, and post-launch evidence into go, conditional-go, hold, or no-go gates. Use when launch-day decision ownership is the artifact; use specialist skills to create missing domain evidence.
Apply IRAC (Issue, Rule, Application, Conclusion) method for structured legal analysis. Use this skill when the user needs to analyze a legal question systematically, write a legal memo, evaluate whether a law applies to a situation, or structure a legal argument — even if they say 'does this law apply', 'analyze this legal issue', or 'write a legal analysis'.
LinkedIn post writing with hook formulas, formatting rules, and engagement patterns. Covers post types, algorithm signals, character limits, and content pillars. Use for: LinkedIn posts, professional content, thought leadership, B2B content, personal branding. Triggers: linkedin post, linkedin content, linkedin writing, linkedin strategy, linkedin engagement, linkedin algorithm, linkedin hook, linkedin formatting, thought leadership, professional content, b2b content, linkedin growth
Assistant for Chinese-language literature search, screening, batch collection, and lawful full-text retrieval. Use when the user needs to find papers, download lawfully available PDF/HTML/XML full texts, generate keywords and search queries, look up DOI/PMID, screen for high-impact-factor or high-quartile journals, check open access, expand citation chains, build batch literature candidate lists, download logs, deduplication lists, or Zotero/BibTeX organization, or troubleshoot papers that are hard to download; bypassing paywalls, pirated downloads, shared accounts, and copyright circumvention are prohibited.
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.