Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Snapshots/restores Ghostty Claude Code/Codex tabs across reboots. Use before Mac updates (保存终端会话/重启前备份终端), after restart to reopen original session IDs (恢复之前的窗口/restore my ghostty tabs), audit survivors, or periodic change-only snapshots (定期增量快照/没变化不记录). Also for unmanaged/legacy Codex account switches (额度耗尽换号/换号后恢复全部 Codex); Minions native_runtime uses Account Manager. Not for --resume, screenshots or tmux.
Structure and format meeting notes following PM best practices. Use when asked to create meeting notes, format discussion notes, capture action items, or document decisions from any meeting type. Produces structured notes with decisions, action items (owner + deadline), open questions, and next steps.
Maintain a project's canonical terms and settled decisions that future work should reuse, and record follow-ups a session discovers but does not resolve. Use when project-specific terms are being clarified, when a choice that may constrain future work is being considered or settles, including during planning, or when a session applies a temporary workaround whose root cause stays open or observes an out-of-scope defect with evidence. Do not use for simple definitions, routine implementation details, or carrying out an already-settled decision.
Search and browse tasks on OpenAnt. Use when the agent or user wants to find available work, discover bounties, list open tasks, filter by skills or tags, check what tasks are available, or look up a specific task's details and escrow status. Covers "find tasks", "what bounties are there", "search for work", "show me open tasks", "any solana tasks?".
Prioritizes features using structured scoring across user impact, revenue potential, strategic alignment, confidence, and engineering effort. Use when deciding which feature to build next or comparing competing priorities.
Analyzes local MP4 video files using the Gemini API and generates structured Markdown summaries. Supports custom prompts to extract specific information instead of the default summary. Use when the user wants to summarize, analyze, or extract key points from video files in bulk. Triggers on requests like "summarize my videos", "create markdown summaries for the videos", "analyze videos with Gemini", "generate video summaries", or "extract X from my videos". Requires GEMINI_API_KEY environment variable set in the system.
Connect a user's own X (Twitter) dev app (BYOK) for the official X API MCP (reads) plus X v2 REST writes — post, reply, like, retweet, DM. Use when the user wants to act on X with their OWN X account or app — search, read timeline/users/news/trends/bookmarks via MCP, and post/reply/like/retweet/DM via REST. Walks through OAuth 2.0 setup in the X portal, xurl CLI registration, headless OAuth (user pastes the redirect URL back), the client-not-enrolled / Pay-per-use trap, the token-expiry auto-refresh mechanism, agent.yaml MCP wiring, and FAQ. For read-only scraping WITHOUT the user's own app, use the twitter skill.
Refine academic writing for computer science research papers targeting top-tier venues (NeurIPS, ICLR, ICML, AAAI, IJCAI, ACL, EMNLP, NAACL, CVPR, WWW, KDD, SIGIR, CIKM, and similar). Use this skill whenever a user asks to improve, polish, refine, edit, or proofread academic or research writing — including paper drafts, abstracts, introductions, related work sections, methodology descriptions, experiment write-ups, or conclusion sections. Also trigger when users paste LaTeX content and ask for writing help, mention "camera-ready", "rebuttal", "paper revision", or reference any academic venue or conference. This skill handles both full paper refinement and section-by-section editing.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to “open a website”, “fill out a form”, “click a button”, “take a screenshot”, “scrape data from a page”, “test this web app”, “login to a site”, “automate browser actions”, or any task requiring programmatic web interaction.
Verifies that every bibliography entry actually exists by cross-checking Crossref, OpenAlex, Semantic Scholar, and arXiv (no API key required) plus doi.org DOI registration, fuzzy-matching title and authors (difflib ratio >= 0.70), flagging retractions recorded by Crossref (including Retraction Watch data) or OpenAlex, and emitting per-entry JSON verdicts in the AlterLab citation-hallucination taxonomy (TF/PAC/IH/PH/SH); a companion script scores whether a cited abstract supports a claim (SH). Accepts BibTeX, DOI/arXiv lists, or pasted references, and reports unverified instead of passing anything it could not check. Use when the request mentions verify citations, check references, fabricated or hallucinated references, fake DOI, retraction check, bibliography audit, reference existence check, or whether a source supports a claim. For drafting a manuscript prefer alterlab-paper-writer; for dead hyperlinks prefer alterlab-link-health. Part of the AlterLab Academic Skills suite.
Formulates structured, testable hypotheses from experimental observations using a scientific-method framework — derives predictions, proposes mechanisms, and designs experiments to test them, then renders a LaTeX report. Use when turning observations or data into falsifiable, mechanistic hypotheses, competing-explanation sets, testable predictions, or experimental designs. For a standalone systematic literature review or evidence synthesis (not a means to hypotheses) use alterlab-literature-review; for open-ended brainstorming before any specific observation use alterlab-scientific-brainstorm; to evaluate an existing manuscript use alterlab-peer-review. Part of the AlterLab Academic Skills suite.
Integrates the LabArchives electronic lab notebook (ELN) via its REST API — access notebooks, manage entries and attachments, back up notebooks, and bridge to Protocols.io, Jupyter, and REDCap. Use when automating LabArchives ELN workflows, programmatically reading/writing notebook entries or attachments, backing up a LabArchives notebook, or syncing it with Protocols.io, Jupyter, or REDCap. Part of the AlterLab Academic Skills suite.
Runs and scripts Open Notebook, a self-hosted open-source alternative to Google NotebookLM with a full REST API, for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 18+ AI providers including OpenAI, Anthropic, Google, Ollama, LM Studio, Groq, and Mistral, with data kept on your own infrastructure through self-hosting. For a one-shot file-to-Markdown conversion (no notebook, chat, or search), use alterlab-markitdown instead. Part of the AlterLab Academic Skills suite.
Search the web, run deep research, and extract content from known URLs via Parallel Web Systems — the Chat API (Beta, OpenAI-compatible `base`/`core` research models) for synthesized answers with inline citations and the Extract API v1 for URL content — with notes on the raw Search, Task, and Responses APIs. Use when running general web searches, current-events/market/technical lookups, broad information gathering, comprehensive research reports, or verifying a specific URL's content (requires PARALLEL_API_KEY). For scholarly paper retrieval or dual-backend academic lookup that auto-routes to Perplexity prefer alterlab-research-lookup instead. Part of the AlterLab Academic Skills suite.
Run AI web searches with real-time, citation-grounded answers using Perplexity Sonar models (sonar, sonar-pro, sonar-pro-search agentic search, sonar-reasoning-pro) via LiteLLM and a single OpenRouter API key. Use when searching for current information or recent scientific literature, getting answers grounded in cited web sources, verifying a claim against current evidence, or reaching information beyond the model's training cutoff. Requires an OpenRouter API key. This is the direct single-backend Perplexity tool: for automatic routing between Perplexity and other backends use alterlab-research-lookup, and for structured per-paper experimental-data extraction (sample sizes, effect sizes, quality scores) use alterlab-bgpt-search. Part of the AlterLab Academic Skills suite.
Works with protocols.io through its REST API (v3 and v4 endpoints) and official MCP server — search and retrieve protocols by keyword, URI, or DOI; create private protocols, edit their metadata and steps, and publish them with a DOI; manage protocol and step discussions, workspaces, file-manager items, file uploads, experiment records, and organization exports. Use when discovering, drafting, publishing, or citing protocols.io protocols, recording protocol runs, or wiring protocols.io into lab documentation. Not for general ELN notebooks (use alterlab-benchling or alterlab-labarchive) or for driving liquid-handling robots. Part of the AlterLab Academic Skills suite.
Interact with Zotero reference management libraries using the pyzotero Python client — retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3. Use when working with Zotero libraries programmatically, managing bibliographic references, exporting citations, searching library contents, uploading PDF attachments, or building research automation workflows that integrate with Zotero. Part of the AlterLab Academic Skills suite.
Use this skill whenever the user asks about Apple apps — Reminders, Calendar, Contacts, Notes, Mail, Messages (iMessage/SMS), or tmux sessions. This includes creating/completing reminders, checking/adding calendar events, looking up contacts, reading/writing notes, sending/reading email, reading/sending iMessages and texts, and capturing tmux session content. Also use this skill when the user mentions tasks, todos, scheduling, birthdays, free time slots, or end-of-day summaries. The bridges are CLI tools installed at ~/.claude/ that give Claude Code native access to these Apple apps on macOS.
Build, revise, and restructure academic CVs for PhD applications, research master's programs, fellowships, research internships, RA roles, and lab applications. Use this skill whenever the user asks to turn a resume into an academic CV, improve research-experience bullets, organize publications/projects/teaching/awards, identify missing evidence for research readiness, or make a CV fit research admissions expectations.
Drive your own Claude Code session from Basecamp. Starts the local connector (basecamp connect), which listens to the account's event feed as a Basecamp agent and prints one line per trusted request: a mention, an assignment, a ping from its operator, a comment on a thread the agent follows, a boost on something it wrote. The connector boosts each one that asks for something the moment it arrives; this session puts that boost in its own words, picks the repo for the project, and hands the request to a background subagent that reads the context, does the work with your settings and tools, and replies as the agent. The session stays free to take the next request, and you can keep using it. Also connects an agent to this computer and manages its setup: the agent's credential (basecamp auth agent connect), who may give it work, and which projects it serves (basecamp connect setup), plus status and doctor. Use when asked to connect an agent, drive agents from Basecamp, watch Basecamp for an agent's mentions, start or stop the connector, or change who can give the agent work or which projects it serves.
Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial scenario modeling, board governance frameworks, and investor relations playbooks. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Critique and improve academic writing at the paragraph level, or produce new academic paragraphs from scratch. Use this skill whenever the user pastes academic text and wants feedback, revision suggestions, or a rewrite; when they ask to "improve this paragraph", "critique my writing", "make this more academic", "help me write a paragraph about X", or asks for academic prose with a specific argument. Also trigger when the user provides a topic, claim, or rough notes and wants them shaped into a polished academic paragraph. Always use for academic writing tasks — even if the request is phrased casually.
Systematic claim-by-claim verification for any content before it ships. Modeled on professional fact-checking desks (The New Yorker, ProPublica, IFCN standards): extract every verifiable claim, check each against live citable sources (never training data), assign a 6-level confidence status, apply corrections, and produce a scored pass/fail report. Includes a data-derived-claims gate for outputs produced FROM the brain or a database: PRODUCER ≠ VERIFIER (re-derive each claim via a different query path) and AFFILIATION ≠ AUTHORSHIP (person→thing claims resolve through typed edges), with delivery hard-blocked on unsupported claims.
Use when the user wants Google Search results through Frevana, including organic results, related searches, related questions, knowledge graph, answer boxes, localized country/language results, pagination offsets, safe search, result count, or device-specific Google results.
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user needs to find papers on a topic, get details for specific DOIs, or draft sections of a literature review with proper citations.
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local web viewer. Use when (1) scaffolding a new knowledge base for any research topic, (2) ingesting articles/papers/PDFs/web pages into raw/, (3) compiling or restructuring wiki articles from existing raw material, (4) answering questions against the wiki and filing durable answers back, (5) running lint passes for dead links / orphan pages / coverage gaps / audit shape, (6) processing human feedback from the audit/ directory and applying corrections. Not for general note-taking, daily journals, or non-wiki Obsidian use.
Search 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and return results with reproducible provenance. Covers PubMed, PMC, Europe PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall, OpenCitations, PubTator3, Zenodo, Figshare, ROR, BioStudies, and DOAJ. Use when searching for papers, citations, DOI/PMID/arXiv lookups, abstracts, full text, open-access PDFs, preprints, citation graphs, author publications, biomedical entity annotations, deposited records (Zenodo, Figshare, BioStudies), institution ROR IDs, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X", "look up this DOI", "who cites this paper", or "get me the PDF"
Create, customize, or polish application-ready resumes from scratch for university students, new graduates, and internship seekers: supports a Grill Me-style question-and-answer interview to collect experience from zero and generate a PDF; reads job JDs and old resumes to build a requirement–evidence mapping and rewrite accordingly; optimizes the content structure of an existing resume or only polishes the layout without changing facts; and generates six different styles of ATS-friendly PDF resumes at once when the user explicitly requests it. Applies to requests such as "interview me to make a resume", "no resume, Q&A from scratch", "customize a resume based on a JD", "optimize/rearrange/polish an existing resume", and "generate multiple resume styles at once"; supports Chinese/English and computer science, software, AI, data, and other campus recruitment positions. Uses the A-C-R-E structure to review experience and adapts content density as sparse / balanced / dense. Fabricating experience or numbers is prohibited; by default it generates one most suitable single-column resume, and only generates in bulk when the user explicitly asks for a comparison. Do not use for academic application CVs, senior executive resumes, portfolio websites, submitting applications on someone's behalf, or pure mock interviews.
Create, inspect, or adapt an Obsidian knowledge base structure for content production (sources, knowledge, topics, writing, publishing, feedback loops). Use for “set up an Obsidian knowledge base”, “connect the vault to the content pipeline”, “inspect the knowledge base structure”, or when ray-writer cannot find the knowledge base. Only add missing structure; do not modify existing notes.
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.