Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Teaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration — parallel fan-out, verifier separation, the stop rule, human gates). Use when asked to build a knowledge graph, extract entities/relations from text, design an ontology, dedupe/merge entities, add graph memory or GraphRAG to an agent, orchestrate multi-agent workflows as a graph, or LEARN graph engineering — in teaching mode the agent explains each stage with worked examples and generates visual diagram artifacts.
Plan, qualify, pitch, and track guest post placements that build links and expertise through audience-specific, citation-justified, editorially placeable off-site content. Use when checking guest post viability, making sales pages citable, creating guest post pitch titles, assessing publisher quality, reviewing guest post outreach, or tracking placements.
Connects to Oxylabs remote headless browsers over the Chrome DevTools Protocol (CDP) with Playwright or Puppeteer. Built-in anti-detection, residential proxies, geo-targeting, persistent sessions and profiles, session recording and live VNC inspection for debugging. Use instead of WebFetch or a local browser whenever a site renders with JavaScript, blocks bots (DataDome, Cloudflare, Akamai), needs a real browser session, screenshots or PDFs. Covers connection, retries, error recovery and safe scraping of protected targets without any human help.
Token-reduction skill for coding agents. Compresses JSON tool output, build logs, grep/ripgrep search results, source code, and conversation history the same way the Headroom proxy does — but in-context, with no binary install. Use this skill whenever an agent is about to paste a large tool result (a 1000-row JSON array, a 5000-line pytest log, a 200-result grep, a 1000-line source file) into its next message, or when the agent's conversation is approaching the context limit, or when the user complains about token cost or latency. Also use it to shape the agent's own output: skip ceremony, don't restate code already on screen, drop reasoning on routine turns. Triggers: "compress this output", "this is too long", "trim", "summarize the log", "reduce tokens", "context is full", "running out of context", "too many tokens", "make it shorter", "be terse"
Financing monitoring system for healthcare companies. Monitors business registration changes of healthcare companies in real time, identifies financing signals, and pushes alerts automatically. Supports Tianyancha/Qichacha data collection, AI-based financing assessment, and multi-channel push notifications.
Use the `hrc` command line to communicate with another Herdr user across machines: draft notes, questions, and delegation requests, build context packages, read approved inbox content, and diagnose synchronization problems. Use when the user wants to reach a remote collaborator or their agent, check an HRC inbox or channel, or set up an HRC channel. Gather what you need by asking, then run it, and send the user to a Herdr pane for the decisions only a person may make rather than to a terminal. Do not use it to read a private key, to approve another person's decision, or to reach anything on their machine: none of that is possible here.
Diagnose and fix failing GitHub Checks on PR work by default: fetch evidence, write ephemeral ci-fails report, apply fixes, verify locally. Run automatically — do not wait for user to ask. Never merge without authorize merge. Companion to /heyeddi fails.
Iterates toward a goal one measured change at a time, keeping what raises the score and reverting what does not, until a fresh run of the check proves the completion criteria met. Use when the user says "hillclimb", or when the user gives a goal and completion criteria and asks to hillclimb, iterate, or keep going until they pass.
Set up and maintain hk git hook manager in any repository. Use when adding pre-commit hooks, configuring linters, setting up code quality automation, working with hk.pkl, or maintaining existing hook configurations. Triggers on tasks involving hk, git hooks, pre-commit checks, commit-msg validation, or linting pipelines.
When the user wants to optimize hospitality purchasing, manage hotel/restaurant suppliers, or improve procurement processes. Also use when the user mentions "hotel procurement," "restaurant purchasing," "hospitality sourcing," "F&B procurement," "hotel supplier management," "group purchasing organization," "contract negotiation," or "hospitality spend management." For hotel operations, see hotel-inventory-management. For cruise operations, see cruise-supply-chain.
Generates a single self-contained static HTML dashboard for a household finance JSON store, with embedded D3.js, inlined data, and six standard panels (net worth over time, monthly cash flow, recurring & subscriptions, goals progress, asset allocation, vigilance feed). Applies cognitive-design principles for visual hierarchy and visual-storytelling-design for narrative annotations. Use when emitting a weekly or monthly finance dashboard, or when user mentions weekly dashboard, household dashboard, finance HTML report, or static dashboard.
Retro Zine — Beige paper with green accent and Bebas Neue + Caveat: a riso-printed zine in HTML form. Anything that should feel printed, lo-fi, and crafted: indie zines and publications, music / arts brands, creator portfolios, small-batch craft launches, community decks.
Manage CloudRobo robot instances — register robots, query robot lists and details, update robot metadata, delete offline robots, export robot certificates for secure access, and fetch the latest robot-side SDK package information. Robots are the physical carriers of embodied intelligence tasks and serve as execution targets for the robo-dispatcher (dispatch) and embodied services. Triggers include: robot registration, robot management, robot type, robot certificate, export certificate, robot SDK, latest SDK, robot_model, manufacturer, 机器人注册, 机器人管理, 机器人类型, 机器人证书, 导出证书, 机器人SDK, 机器人型号, 制造商.
"Deploy Dify - an open-source LLM app development platform on Huawei Cloud with ECS via Terraform. Use when the user wants to deploy Dify (or an LLM application development platform) on Huawei Cloud and directly implement it with a Terraform/SAC template. Trigger: Dify 一键部署, Dify development, Agentic workflow, build AI App"
Remove traces of AI generation from Chinese text. Designed for the distinctive problems of Chinese AI writing: era-opening preambles, overused connectives, internet jargon, translationese, overly formal written style, formulaic structure, canned endings, and intrusion of mainland Chinese terms. Makes text more natural, more human, more like something a Taiwanese person wrote. Trigger words: /humanizer, humanize, 去除 AI 痕迹, 人性化, 去機器味
Reference skill for building high-end interactive 3D websites (WebGL hero scenes, scroll-driven camera moves, product-style renders) using Three.js, React Three Fiber, drei, and GSAP ScrollTrigger — including retrofitting 3D into an existing site (restyle/redesign) without breaking its current routes, content, or accessibility. Use when the user wants to build, restyle, review, or debug a 3D/WebGL web experience — hero canvases, scroll-jacked sections, particle fields, instanced objects, hub/navigation scenes, or performance issues in a Three.js/R3F scene, on a new or existing project. Complements the frontend-design skill: frontend-design covers general UI/UX craft (layout, color, accessibility), this skill covers the 3D/WebGL implementation layer.
Implements, configures, and debugs Unity In-App Purchases, including subscriptions, receipt validation, and direct-to-customer payments via Stripe or Coda. Use when asked about real-money purchases or microtransactions, or migrating from native store billing, RevenueCat, Adapty, Essential Kit, or UniPay.
Implement a GitHub issue end-to-end using the team-executor skill. Given an issue number (or URL), opens a feature branch, dispatches a planning team specialized to the project stack to decide the implementation path (unless the issue dictates the path), confirms a TL;DR with the user (or decides autonomously when asked), posts the agreed approach as an issue comment, launches a fresh execution team to build it, and opens a pull request. Use when the user provides only a GitHub issue number, an issue URL, or asks to "implement issue #N", "work on issue N", "ship issue N", "do issue N", or "build out the issue". Bare numeric input from the user should be treated as a GitHub issue reference in the current repo.
Execute one task file from docs/specs/<slug>/ end-to-end — ground in the PRD/TechSpec, implement only the slice, and hand back evidence under the execution mode's settlement contract. Starts immediately when assigned, with no confirmation prompt. Use when the user says "run task_03", "execute the next task", "pick up a task", or when an implementation loop or daemon assigns a task file from a spec folder.
This skill should be used when the user asks about TUI input handling, raw mode, cbreak mode, terminal keyboard parsing, Esc vs Alt ambiguity, Ctrl-C, shortcuts, focus management, mouse events, scroll wheel, bracketed paste, paste safety, command palettes, forms, text editing, resize events, or keybinding design. PROACTIVELY activate for: raw mode, keyboard input, keybindings, mouse support, paste handling, focus model, terminal forms, text input, vim/emacs-style shortcuts, input conflicts, and cross-platform Windows/macOS/Linux input behavior. Provides: input architecture, shortcut rules, focus patterns, paste/mouse safety, and failure-mode triage.
Java code quality with Checkstyle, SpotBugs, PMD, and SonarJava. Covers static analysis, code style, and best practices. USE WHEN: user works with "Java", "Spring Boot", "Maven", "Gradle", asks about "Checkstyle", "SpotBugs", "PMD", "Java code smells", "Java best practices" DO NOT USE FOR: SonarQube generic - use `sonarqube` skill, testing - use Spring Boot test skills, security - use `java-security` skill
A Skill from the perspective of Jiang Nan's (Yang Zhi) writing techniques — narrative protocol edition. Give everyone's Dragon Raja an ending. Trigger words: write a Dragon Raja ending, Jiang Nan style, Dragon Raja continuation in that style, Lu Mingfei, give Dragon Raja an ending, tragic and passionate writing, youthful prose, emotional rendering, polish into Jiang Nan's style, Dragon Raja fan fiction, Dragon Raja final chapter, write in Jiang Nan's style, narrative protocol.
Draft or revise emails, Slack messages, and other prose in Justin Williams's direct, conversational, pragmatic voice. Use when asked to write on Justin's behalf, sound like Justin, or apply his writing style; not for ordinary assistant replies or verbatim quotations.
Create Amazon-compliant A+ Content for KDP books with text, module layouts, and image specs. Use for A+ Content creation, book detail page design, module selection, compliance checking, rejection avoidance, or KDP marketing materials.
Review code following Kent Beck's refactoring philosophy and simple design principles. Detects code smells, guides refactoring techniques, and promotes incremental improvement (YAGNI, KISS). Use when reviewing code quality, refactoring, or improving code readability.
Guide the ZenML Pro hosted Kitaru onboarding tour from preloaded traces through human review, one reusable evaluator, and one bounded replay. Use only inside the controlled hosted onboarding runner. Resume exact durable workspace state, handle existing agents without name collisions, and keep the tour concise.
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.