Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use the CreatiBI CLI (cbi) to manage material libraries, projects, and project sets, including files, folders, tags, associated products, video understanding signals, AI video analysis results, highlight clips, project lists and creation, project script/material lists, project set lists and project lists under project sets; use when the user mentions uploading to a material library, querying files or projects, viewing signals or storyboards, maintaining material metadata, viewing project sets, or initializing cbi or logging in before operating.
Guidance for cell-free protein synthesis (CFPS) optimization. Use when: (1) Planning CFPS experiments, (2) Troubleshooting low yield or aggregation, (3) Optimizing DNA template design for CFPS, (4) Expressing difficult proteins (disulfide-rich, toxic, membrane).
Review documents, proposals, and plans through the lens of a CEO. Simulates feedback from a founder-CEO who is technical, data-driven, and focused on long-term vision while navigating market volatility. Use when you want high-level strategic review: does this idea make sense as a company bet? Is the team right-sized? Will this survive a downturn? Is it community-first?
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Master compliant China multi-platform growth operations across Douyin, Xiaohongshu, Kuaishou, WeChat, and major ecommerce marketplaces. Use for product selection, offer positioning, content strategy, listing copy, social captions, chat reply flows, lead capture funnels, browser-ready field preparation, publish checklists, and daily growth review. Do not use for spam, fake engagement, mass unsolicited messaging, or platform rule circumvention.
Use Chrome DevTools MCP to retrieve and analyze web page data. Use this skill when users need to scrape web content, analyze page structure, extract data, take screenshots, monitor network requests, or perform web automation tasks.
PRODUCES a citation-budget plan/report (`output/CITATION_BUDGET_REPORT.md`); does NOT edit the draft. Allocates an in-scope per-H3 budget (NO NEW FACTS) so drafts stop failing the global unique-citation gate; citation-injector applies it.
Use when a manuscript's claims need to be checked against the sources cited for them, when literature search results must be verified before they enter a draft, or when an agent or collaborator has proposed references that have not yet been adversarially reviewed. This is claim-to-evidence verification, not bibliography hygiene; for duplicate keys, DOI syntax, and metadata cleanup use citation-verifier instead.
Check what's playing on WRHV 88.7 FM (Classical WMHT), fetch recent tracks, build playlist reports, search for pieces, and create or manage Spotify playlists from radio tracks. Triggers on 'Classical 887', 'WRHV', 'what's playing', 'classical radio', 'Hudson Valley radio', 'Spotify playlist from radio'.
Analyzes professions/jobs for Claude Code automation opportunities. Triggers: 'how can Claude help me', 'what can Claude do for', 'I'm a [profession]', 'help me as a [job]', 'I work as', describing their work + asking about Claude. Use whenever user mentions their profession/role and wants to discover what Claude can automate.
Configure CLAUDE.md project memory files for persistent context, coding standards, architecture decisions, and team conventions. Reference for the 4-tier memory hierarchy, cross-platform AGENTS.md compatibility, and quick-add commands.
Generate TypeScript/JavaScript code that reads/decodes AND writes/encodes ClickHouse RowBinary streams for the ClickHouse HTTP server. Use this skill whenever a user wants to parse or produce `RowBinary`, `RowBinaryWithNames`, or `RowBinaryWithNamesAndTypes`. Node.js only, doesn't cover browsers.
Scores every active client account green / yellow / red on 6 health criteria and outputs a health table + action plan for the reds. Built for B2B service companies (agencies, outsourcing, consulting) where losing one account hurts. Use when the user says: "оцінка здоров'я клієнтів", "client health check", "health scoring", "хто з клієнтів у зоні ризику", "churn risk review", "проскор акаунти", or pastes a list of active clients and asks which ones are at risk. NOT for scoring new leads (use lead scoring) and NOT for upsell mapping (use upsell-mapper).
Use when a val needs to ship JavaScript that runs in the browser — React apps, vanilla DOM scripts, canvas/games, htmx/Alpine, or any client-side module beyond a single inline snippet. Explains how Val Town serves transpiled .ts/.tsx/.jsx modules with no build step, how the browser resolves their imports, and how to load third-party deps.
Use CloudBase document database Web SDK only for confirmed NoSQL collection work. Query, create, update, and delete document data; if the task mentions PostgreSQL / CloudBase PG / app.rdb(), route to postgresql-development instead.
Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.
Reference for Cloudflare Browser Rendering, headless Chrome on Workers via @cloudflare/puppeteer and @cloudflare/playwright. Covers the browser binding, puppeteer.launch, puppeteer.connect and puppeteer.sessions, page.goto, page.screenshot, page.pdf, page.evaluate, browser.close and disconnect, session reuse with keep_alive, incognito contexts, batch scraping and crawling, and pricing and concurrency limits. Use when taking screenshots, generating PDFs from URLs or HTML, scraping or crawling sites, automating or testing web apps from a Worker, extracting page content for AI, or troubleshooting browser timeouts, concurrency limits, memory exceeded errors, XPath selectors not supported, or Cannot read properties of undefined (reading fetch).
Guide to the Cloudflare Sandbox SDK (@cloudflare/sandbox), which runs code inside isolated Ubuntu Linux containers at the edge, routed by Durable Objects. Covers wrangler container and Durable Object bindings, getSandbox(), exec(), runCode(), gitCheckout(), session management, container lifecycle and cold starts, file handling, and state persistence. Use when executing untrusted or AI-generated code, running Python or Node.js scripts safely, building code interpreters and chat-based coding agents, issuing shell commands in isolation, working with git repositories programmatically, creating ephemeral build or CI/CD environments, processing files with system tools such as ffmpeg or imagemagick, or debugging sandbox container lifecycle, routing, and session persistence problems.
Audit an entire project for bugs, security vulnerabilities, code quality problems, performance issues, missing tests, documentation gaps, and concrete improvement or feature ideas—then produce a prioritized, actionable report with file:line references. Read-only by default; only edits or commits when the user explicitly asks for a fix afterwards. Use when someone says “review my project”, “audit the codebase”, “find bugs”, “check for security issues”, “what could be improved”, “suggest improvements”, “are there any vulnerabilities”, “do a code quality review”, or the Hungarian equivalents “nézd át a projektet”, “auditáld a kódot”, “találj hibákat”, “milyen biztonsági problémák vannak”, “javasolj fejlesztéseket”, “mit lehetne javítani”. Trigger whenever the user wants a holistic assessment of a project rather than a fix to one specific thing—even without the word “audit”. Not for reviewing a single diff or PR, debugging one known error, or carrying out a refactor.
Writing, refactoring, or reviewing code for maintainability or design — keeping what you change readable, cohesive, and cheap to change next time. Triggers on "readable", "too long", "refactor", "abstraction", "cohesion", "magic number", "dead code", "what should this be called", or "should this live elsewhere". While authoring, each concern is a practice to uphold; while reviewing, a finding to raise against the diff. Covers cohesion as the test of what belongs in one unit, naming and file organization, abstraction boundaries, complexity limits, dead code, and SOLID/DRY/KISS/YAGNI judgment.
End-to-end code quality workflow for evidence-backed code review, full repository reviews, architecture reviews of software and character-card systems, refactor decisions, authorized minimal changes, and verification. Use for 全量审查、架构审查、全量架构审查, code or diff audits, cleanup triage, or a scoped quality fix. Preserve coverage gaps and keep audit-only requests read-only. Soul/persona voice does not change review ownership.
Before pushing a non-trivial change, spawn read-only subagents on two different model families to adversarially review the same diff in parallel, then merge the findings yourself. Use for "multi-model review", "adversarial review", "challenge this", or a pre-push review of a large or risky diff — not for small or low-risk changes, which don't justify the cost of a panel. Once a PR exists, cloud bot feedback is handled by `pr-review-loop`, not this skill
Review one implementation change against its Phat task, feature spec, acceptance criteria, repository engineering standards, and any accepted prototype evidence. In standalone or final mode record supported task evidence/status; in delegated mode return a read-only report to the parent. Use after implement-task or when reviewing a working tree, staged change, commit, or branch.
Implementation subagent dispatch patterns. Use when a task's design is settled and the file just needs to be made, or when independent implementation work can run in parallel. Covers eligibility, dispatch, shared-tree patch snapshots, one combined review per completed batch, and serial integration.
Inspect an existing repository and refresh only the generated section of CONTEXT.md with attributable Observed, Inferred, and Unknown evidence. Use for onboarding, material repository-context gaps, or explicit refresh; not as a mandatory stage during ongoing implementation.
Tools, patterns, and utilities for creating music with code. Output as a .mp3 file with realistic instrument sounds. Write custom compositions to bring creativity to life through music. This skill should be used whenever the user asks for music to be created. Never use this skill for replicating songs, beats, riffs, or other sensitive works. The skill is not suitable for vocal/lyrical music, audio mixing/mastering (reverb, EQ, compression), real-time MIDI playback, or professional studio recording quality.
Navigate, search, and understand the Resume Matcher codebase using ripgrep, ack, or grep. Find functions, classes, components, API endpoints, trace data flows, and understand architecture. Use FIRST when exploring code, finding files, or understanding project structure.
Audit Codex installation health and workspace context quality by combining the built-in `codex doctor` report with read-only checks for AGENTS.md scope, instruction bloat or duplication, Skills, MCP, hooks, config, thread-provider history scope, Git state, and repository-root hygiene. Use whenever the user asks for `/doctor`, `/checkup`, Codex health checks, context cleanup, AGENTS.md cleanup, unused or broken Skills/MCP/hooks, missing history after provider changes, slow or polluted context, or asks why Codex is ignoring rules. Default to diagnosis only; never edit, disable, delete, trust, install, update, authenticate, move, or clean anything without a separately approved finding-level diff.
Roll an oversized or slow Codex task into a fresh user-visible task with compact continuity. Use only for an explicit handoff or context rollover; not for ordinary continuation, delegation, full-history forks, Git migration, or handoff files.
An intelligent multi-store memory system with human-like encoding, consolidation, decay, and recall. Use when setting up agent memory, configuring remember/forget triggers, enabling sleep-time reflection, building knowledge graphs, or adding audit trails. Replaces basic flat-file memory with a cognitive architecture featuring episodic, semantic, procedural, and core memory stores. Supports multi-agent systems with shared-read, gated-write access. Includes philosophical meta-reflection that deepens understanding over time. Covers MEMORY.md, episode logging, entity graphs, decay scoring, reflection cycles, evolution tracking, and system-wide audits.
Receive and verify Coinbase Commerce webhooks. Use when setting up Coinbase Commerce webhook handlers, debugging X-CC-Webhook-Signature verification, or handling cryptocurrency payment events like charge:created, charge:confirmed, charge:failed, charge:pending, charge:delayed, and charge:resolved.
Calculate, review, and generate web color systems using RGB, HSL, LAB, OKLCH, contrast ratios, luminance, opacity, blend modes, and light/dark mode transformations. Use when auditing accessible colors, converting color models, deriving palettes, checking WCAG contrast, building theme tokens, or debugging opacity and CSS blend math.
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.