Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Expert growth product management guidance for SaaS applications. Use when designing growth loops, optimizing activation and onboarding, building retention systems, creating referral mechanics, running growth experiments, defining north star metrics, or implementing PLG strategies. Covers the full growth lifecycle from acquisition to monetization.
Create modern, responsive websites with professional design systems. Generates complete HTML/CSS/JS websites with Tailwind CSS, modern animations, and mobile-first responsive design. Perfect for landing pages, portfolios, business sites, and SaaS applications.
Refactor MoonBit code to be idiomatic: shrink public APIs, convert functions to methods, use pattern matching with views, add loop invariants, and ensure test coverage without regressions. Use when updating MoonBit packages or refactoring MoonBit APIs, modules, or tests.
Fetch and inspect recent local server logs in repos that use openlogs or the `ol` CLI. Use when a user asks what happened in the server, wants recent dev-server output, needs startup errors or stack traces, or asks you to check backend logs from `openlogs tail`, command-specific logs, or `.openlogs/latest.txt`
Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.
A specialized security auditing tool for the CodeIgniter framework. Performs white-box static audits of CodeIgniter mechanisms such as CSRF, XSS output filtering, database query construction, route and validator configuration, and session Cookie security, mapping findings to common vulnerability categories (CSRF/AUTH/XSS/SQL/CFG/SESS, etc.).
Ruby on Rails design system guidelines for building consistent, maintainable UI with minimal abstraction. This skill should be used when creating or refactoring Rails views, partials, components, form builders, helpers, Stimulus controllers, Turbo Frames, Turbo Streams, or design tokens. Triggers on tasks involving ERB partials, Turbo navigation, Turbo Streams, ViewComponent, Phlex, Tailwind design tokens, custom form builders, view helpers, Stimulus behaviors, Import Maps, Lookbook previews, or design system consistency audits.
Implements reliability patterns including circuit breakers, retries, fallbacks, bulkheads, and SLO definitions. Provides failure mode analysis and incident response plans. Use for "SRE", "reliability", "resilience", or "failure handling".
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked “what transports are open in the system,” “show all open transports,” “transport backlog,” “what is everyone working on,” “basis transport overview,” “which requests are ready to release,” or “find import-order conflicts.”
Transform learning content (like YouTube transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework. Use when user wants to turn advice, lessons, or educational content into concrete action steps, reps, or a learning quest.
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
Re-run or deepen the agent's identity interview. Drives the SHARED bootstrap answer bank (state/interview.json) via `gbrain bootstrap interview --set/--show/--confirm`, then re-renders the identity files with `gbrain bootstrap render --only <FILE> --force`. One answer store, two surfaces: first-boot bootstrap and this re-run skill write the same bank, so an updated answer flows into SOUL.md, USER.md, ACCESS_POLICY.md, and HEARTBEAT.md without hand-editing rendered files. Every answer is the user's own words — never invented.
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on stakeholder update, status report, executive summary, exec review, manage up, communicate bad news, project comms, status meeting, weekly update. Also triggers when a project is going off track and the team needs to communicate it.
Implement interactive 3D charts in Angular applications using Syncfusion. Guide covers setup, chart types (bar, column, stacked variants), customization, data binding, axis configuration, legends, tooltips, selection, data labels, appearance styling, dimensions, print/export, and accessibility. Use this skill whenever a user needs to create, configure, or customize 3D chart visualizations.
Implement Syncfusion Angular Bullet Chart component for performance comparison visualizations. Use this when displaying actual vs target values, defining quality ranges, customizing axes and labels, or creating accessible performance indicators. Covers getting started, data binding, axes configuration, visual elements, and customization.
Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.
Operate Ryvn infrastructure: manage organizations, provision environments, deploy services and installations, configure blueprints, manage release channels and promotion pipelines, set up connections and variable groups, view logs, approve tasks, handle preview deployments, and write network policies. Use this skill whenever the user mentions Ryvn, environments, services, installations, blueprints, deployments, infrastructure, provisioning, Kubernetes, cloud, GCP, service installations, release channels, promotion pipelines, network policy, egress rules, isolating a workload, or allowing a domain or IP, even if they don't say "Ryvn" explicitly.
Comprehensive toolkit for writing high-quality computer science research papers (conference, journal, thesis). Provides narrative construction guidance, sentence-level clarity principles (Gopen & Swan), academic phrasebank, CS-specific conventions, and section-by-section quality checklists. Use when assisting with academic paper writing, revision, or structure planning across all stages from drafting to submission.
Generate reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos from reference video/image material, preserving character style, or documenting reference-to-video request/response flows.
Drive a native Mac app (AppKit, SwiftUI, react-native-macos) through argent. Use when a list-devices entry has platform "macos", or the user names a Mac app, a macOS app or a native desktop app. Never for an iOS simulator, an iPhone, or an Electron or Chromium app (platform "chromium").
Optimizes CI/CD pipeline speed by implementing effective caching for dependencies, Docker layers, build outputs, and test results. Provides before/after performance metrics and best practices. Use for "CI caching", "pipeline optimization", "build speed", or "cache strategy".
Check a Canva design against a brand kit and report where it diverges — off-palette colors, non-brand fonts, logo misuse, and off-tone copy. Read-only; makes no changes. Use when the user asks "is this on brand", "check this against our brand kit", "do a brand review", "does this match our brand guidelines", or "brand-check my design".
Helps developers integrate the Channel3 API for product search (text, image, semantic, and agentic), “more like this” recommendations, multi-merchant offer comparison, URL-to-product lookup, conversational shopping agents, live price and availability webhooks (product subscriptions), price history, click/transaction reporting, and affiliate commissions. Channel3 is a universal product catalog with TypeScript and Python SDKs plus a React component library (shadcn registry). Use when writing integration code, building shopping features or AI shopping agents, migrating to Channel3 SDK 4.0, or when the user mentions alternatives like Shopify Storefront API, Algolia, Amazon PA-API, or web scraping for product data.
Generates clean React/Vue component skeletons with TypeScript types, prop variants, styling hooks, test files, Storybook stories, and usage documentation. Use when users request "create a component", "scaffold component", "new React component", or "generate component boilerplate".
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review. Also triggers when finance flags rising costs or when a contract renewal is up.
Measure a project's code coverage and report the coverage number. Use whenever coverage needs to be measured — a user asking to run the coverage report or check the current level, and also when the task itself calls for it: recording the starting coverage before development, confirming coverage didn't drop below the committed baseline after a change. Measures the whole project (unit + integration merged) or just one test group — a package/class glob or a subproject.
Generates Cucumber BDD tests with Gherkin feature files and step definitions in Java, JavaScript, or Ruby. Use when user mentions "Cucumber", "Gherkin", "Feature/Scenario", "Given/When/Then", "BDD". Triggers on: "Cucumber", "Gherkin", "BDD", "Feature file", "Given/When/Then", "step definitions"
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like Statsig and Optimizely. Triggers on warehouse-native experimentation, run experiments in BigQuery, run experiments in Snowflake, dbt experiments, SQL t-test, CUPED variance reduction, exposure log, sample ratio mismatch, sequential testing, mSPRT, doubly robust estimation, build vs buy experimentation. Also triggers when the team is choosing between platform and warehouse, building warehouse-native experiment infrastructure, auditing one, or running an experiment with a custom metric the platform cannot handle.
Use when building, modifying, deploying, or debugging Keboola Apps (Streamlit or Python/JS). Covers the full lifecycle — choosing app type, the Python/JS prod-app-and-drafts model (never create a second app), configuring keboola-config/, storage access (RO workspace, RW Query Service, input mapping), authentication, DuckDB caching for performance, default Keboola styling, dashboard patterns, optional Kai chat integration, the three client paths (MCP-only, Claude Code with filesystem, kbagent CLI), and deploying from a private GitHub repo through the organization's GitHub connection instead of a PAT or SSH key.
Verifies identity documents and digital ID wallets through Didit's standalone APIs. Use when an agent needs to verify a passport, ID card, driver's license, or residence permit from an image or PDF; run OCR and MRZ or barcode extraction; detect screen captures, printed copies, portrait manipulation, or covered fields; read document warnings; or start a digital ID wallet sign-in (MitID, BankID Sweden, iDIN, Finnish Trust Network, Smart-ID, Mobile-ID) without a workflow. Covers 14,000+ document types from 220+ countries and territories
Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets. Use for DiffDock, molecular docking, ligand docking, blind docking, SMILES or SDF ligands, ranked poses, confidence scores, hosted NVIDIA API, or local Docker deployment.
Deploy Django on Google App Engine Standard with Cloud SQL PostgreSQL. Covers Unix socket connections, Cloud SQL Auth Proxy for local dev, Gunicorn configuration, and production-ready settings. Use when deploying Django to App Engine, configuring Cloud SQL PostgreSQL, setting up Unix socket connections, or troubleshooting "No such file or directory", "connection refused", or "FATAL: password authentication failed".
Plan, manage, and optimize a domain portfolio. Use this skill for DNS architecture decisions, redirect strategies, registrar choice, parking unused domains, multi-site setups, and domain consolidation or split planning. Triggers on DNS, domain, registrar, redirect, parking, subdomain, apex, www vs non-www, multi-site, portfolio, hreflang setup, domain migration. Also triggers when planning a new site that needs domain decisions made before launch.
How to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, sequential testing, CUPED, heterogeneous treatment effects, ratio metrics, network effects, dashboard reconciliation, and the interpretation failures that produce confidently wrong shipping decisions. Use this skill whenever the user is reading a finished experiment result panel and about to make a ship, kill, or iterate decision, or when an experiment number does not match the dashboard number. Triggers on read experiment results, result panel, ship or kill decision, p-value, confidence interval, statistical significance, multiple testing, peeking, sequential testing, CUPED, variance reduction, heterogeneous treatment effects, ratio metric, network effects, inconclusive test, experiment versus dashboard mismatch. Use `experiment-design` instead when the test has not run yet and the question is hypothesis, sample size, duration, or what to test.
Original prompt for an expert panel. Use when a user's question requires several complementary areas of expertise and a single perspective cannot provide a good solution. Trigger phrases include expert panel, look at this from multiple perspectives, find a few experts, multidisciplinary analysis, assemble an expert team, and have them challenge one another. Present the points of disagreement across three complementary perspectives and a synthesized plan, including applicability conditions, the greatest risk, and exit criteria.
**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically.
Original prompt for first-principles thinking. Use when a plan is being patched repeatedly, stuck in path dependence, or needs to be re-derived from the essence of the problem. Trigger phrases include first principles, get back to basics, reason it through from scratch, stop patching it, start over, and what is the fundamental reason for doing this? Identify which parts of the original plan only address surface symptoms, then provide a new path derived from first principles and the first validation step. For personal reflection, without an Agent running the process. For critique and challenge, use carl-idea-king.
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.