Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Overview of Tavus, the AI research lab pioneering human computing. Use when you need context about what Tavus is, their mission, core concepts like CVI and Human Computing, the model stack (Phoenix, Raven, Sparrow), or links to docs/platform/resources.
Chinese-first technical learning skill: quickly grasp technical concepts, read GitHub repositories/codebases, systematically study a topic, clarify technical questions, or generate reviewable HTML lessons. By default it initializes a learning area and produces HTML for main-line lectures, with adjustable pacing; technical terms keep their English or common abbreviations, but their role and boundaries must be explained in Chinese.
Diagnose technical SEO issues using discovery, crawling, indexing, ranking, Google Search Console, internal links, crawl budget, canonicals, duplicate content, redirects, and migration risk. Use when traffic drops, pages are not indexed, Search Console shows errors, canonicals differ, migrations are planned, or a technical SEO audit is needed.
Ship changes via pull request in Tenzir projects. Use when the user wants to open a PR, push a branch, add or update changelog entries, create a pull request for review, or when they say "ship this", "open a PR", "send this for review", or "push and create a pull request." Also use for follow-up changes to an existing PR.
This skill should be used when the user asks to "analyze test coverage", "find untested code", "check coverage gaps", "improve test coverage", "identify missing tests", "measure code coverage", "test quality analysis", or mentions testing strategies and coverage metrics.
Set up the local dev environment, seed data, and API keys to test the staff-only managed migrations MCP tools (managed-migrations-support-list, managed-migrations-support-get) end to end. Use when testing batch import support tooling, debugging MCP tool responses or discovery (tools not appearing), or verifying the support API before deploying. Covers the discovery gate: hidden scope, is_staff, user:read, and why wildcard keys and OAuth never work.
Enable efficient communication between Thai-language users and agents by translating Thai prompts into English in two modes and by preventing Thai text corruption in files. Use when the user writes in Thai, asks for Thai-to-English interpretation, wants token-efficient prompt rewriting, or reports mojibake/replacement-character issues such as U+FFFD in saved files.
Systematic threat modeling skill for applications, APIs, and systems using STRIDE, PASTA, Attack Trees, DREAD, LINDDUN, and OCTAVE. Use when assessing security architecture, creating data flow diagrams (Mermaid), enumerating threats from OpenAPI specs or architecture docs, building attack trees, mapping threats to NIST/CIS/OWASP ASVS controls, or producing a threat model report. Triggers on requests to threat model, analyze attack surface, create a DFD, apply STRIDE, or design security mitigations.
Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
Track AI token consumption, costs, and usage trends using the orbit CLI. Use this skill whenever the user asks about token usage, AI costs, Claude Code spending, how many tokens were used, cost breakdown by model, session history, or token analytics. Trigger on phrases like 'how much have I spent', 'token usage', 'show me costs', 'what's my AI spending', 'how many tokens today', 'cost per model', 'list sessions', 'track usage', 'token report', 'weekly usage', 'monthly costs', or any token/cost tracking task — even casual references like 'am I spending too much on Claude', 'what did that session cost', 'show me the dashboard', or 'how much is opus costing us'.
Spin up an isolated git worktree in its own tmux session — coding agent in one window, a shell in another, dev stack in a third — with the agent briefed and already working. Use for spinning up a worktree, starting a feature/branch/task in isolation, handing work to a fresh agent (Claude/Codex), or setting up an isolated tmux dev session.
Use when you need concrete UI/UX inputs (palette, typography, landing patterns, UX/a11y constraints) to drive design or review. Searchable UI/UX design intelligence (styles, palettes, typography, landing patterns, charts, UX/a11y guidelines + stack best practices) backed by CSV + a Python search script. Triggers: UIUX/uiux, UI/UX, UX design, UI design, design system, design spec, color palette, typography, layout, animation, accessibility/a11y, component styling. Actions: search, recommend, review, improve UI.
Use when applying Toss Tech Design principles from a 129-article toss.tech design summary to complex product flows, research ops, internal tools, UX writing, accessibility, or brand work with high cognitive load, repeated manual work, trust issues, or inclusion gaps.
A fast, extensible progress bar for Python and CLI. Instantly makes your loops show a smart progress meter with ETA, iterations per second, and customizable statistics. Minimal overhead. Use for monitoring long-running loops, simulations, data processing, ML training, file downloads, I/O operations, command-line tools, pandas operations, parallel tasks, and nested progress bars.
Research and shortlist startup traction channels before running Bullseye tests. Use when comparing acquisition channels, studying how similar companies grew, finding underused distribution strategies, or preparing the outer ring for a Traction-style growth process.
Set traction goals and identify the Critical Path from Traction so teams focus only on milestones needed for growth. Use when a startup has too many priorities, needs growth goals, is debating product versus marketing work, or wants to decide what not to do.
Plan existing-platform, trade show, offline event, speaking, and community-building traction experiments from Traction. Use when testing platform distribution, conferences, meetups, talks, forums, local events, or community-led startup growth.
Plan paid acquisition tests from Traction across SEM, social/display ads, and offline ads. Use when designing ad experiments, keyword tests, audience tests, paid channel budgets, or deciding whether a paid channel can acquire the right customers profitably.
Design cheap, measurable traction tests from Traction for startup growth channels. Use when planning marketing experiments, middle-ring tests, A/B tests, acquisition test spreadsheets, channel validation, or growth experiment success criteria.
Plan viral marketing and engineering-as-marketing traction experiments from Traction. Use when designing referral loops, viral coefficients, engineered acquisition tools, calculators, microsites, widgets, or product-led assets that acquire customers; use make-product-viral instead for landing-page audits, shareability reviews, pricing-page polish, or social-preview optimization.
Assigns a category and subcategory to a financial transaction by matching its raw description against a configurable taxonomy and rules table, falling back to LLM inference when no rule matches. Emits a normalized merchant name, category path, recurring flag, and confidence score, and proposes new rules from confirmed classifications. Use when categorizing bank, credit-card, or brokerage transactions, building or refining a category taxonomy, or when user mentions transaction categorization, merchant normalization, expense classification, or category rules.
Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management. Includes SMART goal frameworks, evidence-based interventions with minimal text citations, regulatory compliance (HIPAA), and professional formatting. Prioritizes brevity and clinical actionability.
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. Use when issues or external PRs need categorising, verifying, and turning into agent-ready briefs. Triggers on: triage, triage the backlog, review these issues.
Apply Edward Tufte's principles to any data visualization, chart, dashboard, or infographic. Use when the user asks to produce, design, critique, or improve a chart, graph, dashboard, KPI tile, table-with-data, sparkline, small multiple, time series, distribution plot, choropleth, or any other visual that communicates quantitative or categorical information. Also triggers on words like "visualize", "viz", "data viz", "chart", "graph", "dashboard", "infographic", "Tufte". Outputs Tufte-compliant designs in either self-contained HTML/SVG or React (Recharts/D3). Defaults to Tufte rules; user can opt out per chart.
Author, revise, reorganize, or review step-by-step tutorials for beginner-to-intermediate learners. Use when writing or auditing tutorials, hands-on guides, walkthroughs, procedural lessons, course content, or multimedia learning materials. Choose representations by task, reduce avoidable cognitive overhead, align practice and feedback to goals, adapt assistance to prior knowledge, and preserve accessibility.
Use TypeScript for type-safe JavaScript: types, interfaces, generics, narrowing, tsconfig, modules, and strict mode. Use when writing or reviewing TypeScript, configuring tsconfig.json, defining types or interfaces, generics, type inference, or when the user mentions TypeScript, TS, or type checking.
UE5.6-UE5.8 Blueprint graph workflow for feature implementation, input events, node wiring, and graph validation. Use when requests involve adding Blueprint logic, keyboard input behavior, function chains, event graph edits, or pin-level connection guidance.
Raise frontend visual judgment for web interfaces with a bias toward refined product-grade composition, precise component craftsmanship, disciplined interaction states, controlled motion, and coherent depth systems. Use in any supported agent or IDE when generating, reviewing, or refactoring UI that feels generic, cluttered, flat, over-styled, theatrically animated, visually imprecise, or AI-generated, or when the user asks for a cleaner, more premium, more polished, more minimal, more refined, or more product-grade interface.
This skill should be used when the user asks to "generate a UI sound theme", "create button click sounds for my app", "design notification sounds", or "build a coordinated audio theme for my dashboard or wallet app", "make game menu sounds", "create HUD feedback sounds", "design TV navigation sounds", "audit the sounds on my existing site", "check that transaction sounds are wired", "review UI audio wiring", or "edit a generated UI sound". Generates, audits, edits, and wires cohesive UI audio themes mapped to semantic interactions via ElevenLabs and ffmpeg, with an interactive local picker for auditioning, revising, reassigning, and accepting candidates.
Use when a UI/UX task needs searchable design intelligence: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, or check web/mobile UI. Covers websites, landing pages, dashboards, admin panels, e-commerce, SaaS, portfolios, blogs, mobile apps, components, forms, tables, charts, color systems, accessibility, animation, layout, typography, spacing, interaction states, shadows, gradients, and design-system choices. Includes 67 UI styles, 161 color palettes, 57 font pairings, 161 product reasoning rules, 99 UX guidelines, 25 chart types, and 15+ stacks including React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind/HTML, shadcn/ui, Three.js, Angular, and Laravel.
Updates the bostonaholic skills plugin installs (Claude Code, Codex, the Cursor plugin clone) and the skill copies in the Antigravity, OpenCode, Cursor, and Grok Bot skill directories to the latest release tag. Use when the user explicitly asks to update the bostonaholic skills. Never infer from an outdated skill or a version mismatch. Not for installing; use INSTALL.md.
Use only when the user explicitly invokes upward-networking or asks to use this skill. Helps users design sincere, restrained, actionable upward networking and high-value relationship-building moves, supporting invitations, asking for advice, follow-ups, retrospectives, and optional Obsidian note drafts.
Audit a page / surface against the Designing Interfaces pattern language + the ux skill checklists, then land findings. Three layers — static (code), visual (screenshots), dynamic (automated user journey + perf). Use to run a repeatable, standards-based UX review of one screen.
Use this skill whenever building, editing, or reviewing user-facing software with v0 — web apps, dashboards, marketing sites, component libraries, or any code change that produces visual output. Triggers on requests to "build a UI", "design a page", "make a component", "improve the look", "polish this", "make it production-ready", or whenever scaffolding a new app/screen/feature with visible surface area. Encodes v0's opinionated defaults for Tailwind CSS patterns, shadcn/ui components, design tokens, typography, spacing, color, motion, accessibility, and the component patterns that hold up under real users.
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
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.