Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Convert uncertain real-world choices into an auditable Bayesian evidence-to-action report with priors, evidence grading, posterior update, action thresholds, sensitivity checks, multi-turn decision logs, and Markdown plus bilingual HTML output. Do not use for Bayes theorem tutoring, homework, generic brainstorming with no report, or final licensed medical, legal, or financial advice.
Yichen's personal unified entry point for audio and video transcription, routing between StepFun Step ASR and Volcano Engine Doubao ASR based on output requirements, security boundaries, and availability. For plain-text transcription of local audio or video, timestamps, SRT subtitles, rough cuts of spoken narration, and pre-transcription health checks; when the user explicitly specifies a provider, do not switch silently. Use when a local audio or video file needs transcription and the correct ASR backend is unclear, or when the user explicitly invokes $yichen-asr.
After the user explicitly authorizes it in the current turn, read-only export their Xiaohongshu favorites, Douyin favorites, or X/Twitter bookmarks as a local link file; this Skill directly handles scrolling the favorites page, extracting links, deduplicating, verifying counts, Field Theory GraphQL-only export, and sample validation. For private data export tasks such as "export/back up/sync my favorites or bookmark links"; must not be used for public search, analysis of favorited content, media downloads, archiving of full text, recommendation discovery, or private reads not authorized in the current turn.
Search, retrieve, inspect, add, or edit Zotero literature via the `zotagent` CLI. Load this skill whenever the user wants to query their Zotero library (keyword / semantic / metadata), pull quotations or context from indexed papers, add items by DOI, web page URL, ISBN / PMID / arXiv identifier, Semantic Scholar paperId, JSON, or manual metadata, change existing items (fix a field, add or remove tags, file into a collection, attach a note, trash an item), inspect recent Zotero items, or diagnose indexed attachments. Use it even on indirect requests — any mention of references, citations, bibliography checks, PDF passages, or literature discovery. Do not guess at zotagent's flags — consult this reference first.
Use when managing Alibaba Cloud TongyiTranslate (AnyTrans) via OpenAPI/SDK, including the user needs translation service resource operations in Alibaba Cloud, including list/create/update actions, task status checks, and troubleshooting AnyTrans API workflows.
Audit a full PhD or research-application package for declared-theme fit, coherence, missing evidence, narrative consistency, program fit, recommender risk, and deadline priorities. Use this skill whenever the user asks whether their whole application is ready, how to prioritize fixes before deadlines, whether their CV/SOP/research statement/faculty fit/recommenders align, whether the SOP and letters actually answer the programme's declared theme, specialisation, or track, or what weaknesses an admissions committee may notice across materials. Every audit runs the declared-theme screen first, before any academic- or faculty-fit finding, searching the web for the live official programme page whenever the target is not already known from the conversation.
Map an applicant's research interests to programmes, tracks, faculty, labs, and departments, and check whether their profile actually matches a programme's declared theme, specialisation, or application focus before writing target-specific materials. Covers PhD, research master's, and joint/consortium programmes such as Erasmus Mundus. Use whenever the user asks which professors or programmes fit their interests, how to shortlist targets, how to compare faculty fit, "does my profile match this programme's focus", "is my background relevant to this specialisation/track/theme", "should I even apply to this one", how to turn interests into searchable research themes, how to prepare target-specific fit notes for SOPs, or "does this programme match my career goal" (a goal-fit flag against the graduate the programme intends to produce, which never drops a target).
How to use BGPT MCP to search scientific papers and retrieve structured experimental data including methods, results, sample sizes, conflicts of interest, limitations, reproducibility scores, and falsifiability criteria. Use this skill when the user asks to find scientific evidence, search the literature, evaluate research quality, check reproducibility, surface study limitations or conflicts of interest, retrieve raw experimental data, or build evidence-grounded AI workflows. Also trigger when the user references PubMed, arXiv, biorxiv, medrxiv, systematic reviews, evidence-based medicine, GRADE, or critical appraisal.
End-to-end discipline for turning any large data source (audio libraries, email takeouts, document corpora, chat exports, API dumps) into brain pages at scale. The lifecycle spine: SCHEMA → ACCESS → TRIAL → EVALUATE → IMPROVE → CODIFY → TEST → SKILLIFY → BULK → MONITOR. State is tracked in a durable JSON manifest (see MANIFEST-PATTERN.md) so any crash, session boundary, or subagent fan-out resumes from ground truth instead of memory.
Prepare accountable executive decisions, information triage, briefing, calendar choices, organizational sensing, and institutional memory without assuming authority or monitoring people. Use when a chief of staff or CoS, executive office, gatekeeping, decision memo, executive briefing, board materials, organizational sensing, team health, institutional memory, calendar triage, meeting audit, strategic time, or attention allocation is requested. Do not use this skill for unrelated requests; route to the nearest named specialist.
Use when running a systematic open-source prior art survey for a software idea — deriving a keyword map (typed search vocabulary) or executing one search angle of repository discovery across code hosts, package registries, curated catalogs, code search, alternative directories, and community channels. Produces schema-validated artifacts: a keyword-map file or a per-angle search-output file with reproducible coverage records and candidate repositories — or deep-reading one candidate into an EXTRACTION (a 10-section analysis + a machine-readable verdict/score/license/deps block). Keywords: prior art, open source search, repository discovery, keyword map, code extraction, competitor alternatives. Covers the survey's SEARCH wave (keyword-map derivation + angle execution), the EXTRACT wave, and the SYNTHESIS wave (aggregating extractions into a report + a borrow-index).
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, verified claims, or comparison of approaches. Triggers include "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". Do NOT use for simple lookups, debugging, or questions answerable with 1-2 searches.
Extracts atomic sentences from academic papers — identify every cited paper, compress each citation into a single logical claim, group them by sub-topic, and summarize each group. Use this skill whenever the user pastes academic text or uploads a PDF and wants to extract what cited papers actually claimed, map the literature, build a citation map, extract key arguments from a paper, atomize citations, or asks things like "what does each paper say?", "extract the key claims", "give me an atomic breakdown of this paper", "pull out all the references and their arguments", "summarize the citations by topic", or "elaborate on [Author Year]". Also trigger when the user is preparing a literature review, working in Obsidian/Zotero/Notion and needs structured citation blocks, or uploads a PDF with a request to extract referenced claims. This skill is essential any time someone is working with dense academic text and needs to see what all the cited sources actually argued.
Email invoice processor. Filter invoice emails from a mailbox by date range, download PDF/image attachments (including downloads via links), extract invoice fields, and generate an Excel summary with one sheet per buyer. Use this skill when the user needs to process invoices, organize invoices, or extract invoices from email.
Design and evolve enterprise architectures by connecting business capabilities, value streams, applications, information, technology, operating models, and transition choices. Use when mapping an enterprise portfolio, comparing current and target states, sequencing transition architectures, or defining federated architecture decision rights and stakeholder communication. Do not use for system or solution design, API or data-platform design, organizational or talent design, product roadmaps, technology adoption, or corporate strategy; route those to the named specialist skills.
Orchestrate a complete PhD / research-program application package end-to-end — from reading the applicant's materials through CV, program & faculty fit, SOP, recommender strategy, professor outreach, a final package audit, and interview preparation once shortlists arrive. Use whenever the user wants to drive the whole application rather than one piece: "help me with my PhD applications", "where do I start with my application", "manage my application process", "I'm applying to PhD programs, what's the plan", "get my materials ready", or hands over a folder of CV/transcripts/notes and asks for the path to submission. This is a ROUTER that sequences existing singleton skills with stage gates; it does not write the SOP, CV, or emails itself. For a single piece, invoke that skill directly (e.g. apply-sop-writer, apply-cv-builder). For driving a research paper use flow-paper-lifecycle.
Expert in Freshdesk helpdesk API for building integrations, extracting support data, managing tickets/contacts/companies, and automating support workflows. Use when working with Freshdesk, building helpdesk integrations, analyzing support ticket data, or creating customer support applications.
Drive the grok build CLI (run `grok`) for search, research, and media creation. Use for Grok/X web search with citations; large-scale parallel research via grok headless + subagents; generating images (image_gen) and videos (image_to_video) through the logged-in grok session at zero API cost; and ffmpeg post-processing like green-screen / chroma-key removal, concatenation, and watermarking. Cross-platform (macOS/Linux/Windows). Optional xAI search/media API as a paid fallback. Triggers include grok, grok build, 生图, 生成图片, 生成视频, 绿幕抠像, 批量调研, xAI search.
End-of-session ritual. Captures decisions, lessons, gotchas, and open threads. Writes a narrative session log to ~/.origin/sessions/ and stores granular memories via Origin MCP. Previews any unconfirmed captures from the current session before closing. Invoked as `/handoff`.
Diagnose Kanban flow problems and design board operating models. Load this when your team is struggling with throughput, cycle times are unpredictable, multiple stakeholders compete for the same engineers, or you're wondering if Kanban is right for you. Do not use this skill for unrelated requests; route to the nearest named specialist.
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
X-ray scans articles (blog posts, essays, opinion pieces) to extract the real question and cognitive collisions. Use when user shares a non-academic article URL or text for deep structural analysis. Do NOT use for academic papers (use ljg-xray-paper) or books (use ljg-xray-book).
Create, list, and manage macOS Reminders via AppleScript. Use when the user asks to create a reminder, add a to-do, make a task, set a reminder for something, or anything involving Apple Reminders on macOS. Triggers on requests like "remind me to buy milk", "add a to-do to call the dentist", "create a reminder for Friday", "add to my shopping list", "flag this as important". macOS only.
Reply to a message, comment, thread, review, or email as the user, so the result reads like they typed it themselves and nobody suspects an AI wrote it. Use when asked to reply as me, respond to this, answer this comment, draft a reply, be me, sound like me, or /mimic. Pulls the user's voice from examples in context and applies the dispel register. With setup or refresh, or when asked to build or update my voice profile, spawns Ghost to fill in a voice profile from the user's own writing.
Multi-perspective deep analysis. Several sub-agents each act as advisers with different thinking frameworks, analyse the same material independently, then their consensus and disagreements are cross-summarised into a structured diagnostic report. Triggered when the user says "help me analyse from multiple perspectives", "multi-dimensional analysis", "look at it from several angles", or "help me diagnose this".
Expert n8n workflow automation consultant for B2B sales and GTM teams. Use when the user asks about n8n workflows, n8n nodes, n8n triggers, n8n webhooks, n8n credentials, n8n self-hosting, n8n Docker setup, n8n queue mode, n8n error handling, n8n sub-workflows, n8n CRM automation, n8n pricing, n8n vs Zapier vs Make, or building automations with n8n. Also triggers on "n8n workflow", "n8n automation", "n8n webhook", "n8n node", "n8n self-host", "n8n Docker", "n8n queue", "n8n HubSpot", "n8n Salesforce", "n8n vs Zapier", "n8n pricing", "workflow automation". Do NOT use for general automation strategy without n8n.
Expert guide for the NotebookLM CLI (`nlm`) - a command-line interface for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of \"nlm\", \"notebooklm\", \"notebook lm\", \"podcast generation\", \"audio overview\", or any NotebookLM-related automation task.
Operate Notion from a terminal or agent: retrieve pages, query databases, search pages and databases, and update page properties — with a bundled notion-cli script that is read-only by default and gates every create or update behind a --dry-run/--yes confirmation. Use when an agent needs to read Notion content, answer questions from a team wiki or database, or make a confirmed edit. Do not use for building Notion integrations or block-level page composition beyond property updates (that is Notion API application development), or for other knowledge bases (that is their own tooling).
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
Route obsidian-mind work into the right mode: install/bootstrap the vault (ShardMind vs git clone), the daily standup/dump/wrap-up session loop, capture routes for decisions, incidents, 1:1s, and wins, the performance-graph review flow (/om-review-brief, /om-self-review, /om-peer-scan), vault maintenance and /om-vault-upgrade migration, multi-agent wiring across Claude Code, Codex CLI, and Gemini CLI, and optional QMD semantic search. obsidian-mind is a specific ready-made Obsidian vault template giving coding agents persistent, session-spanning memory through five lifecycle hooks, /om-* commands, subagents, and a competency graph — not a generic vault-building or wiki-authoring workflow. Triggers on: obsidian-mind, om-standup, om-dump, om-wrap-up, om-review-brief, om-self-review, om-peer-scan, om-vault-upgrade, brag doc, North Star.md, performance graph, competency notes, session lifecycle hooks, shardmind install obsidian-mind.
OpenBio API for biological data access and computational biology tools. Use when: (1) Querying biological databases (PDB, UniProt, ChEMBL, etc.), (2) Searching scientific literature (PubMed, bioRxiv, arXiv), (3) Running structure prediction (Boltz, Chai, ProteinMPNN), (4) Performing pathway/enrichment analysis, (5) Designing molecular biology experiments (primers, cloning), (6) Analyzing variants and clinical data, (7) Analyzing and editing plasmid files (GenBank, SnapGene).
Open-source intelligence on people, companies, domains, and B2B accounts. Use when the user wants to investigate, vet, research, or build a dossier on a target — phrases like "OSINT", "due diligence", "background check", "research this person", "look into [company/domain]", "vet this prospect/vendor", "what does X do", "is this account worth pursuing", "find me a contact at", "who's the buyer for", or any open-source investigation task. Disambiguates identities before reporting and grades every claim by independent source count.
Interpret the meaning of a paper's figures and output a highly readable Markdown report that "teaches humans how to read the figures"; supports input of one or more absolute paths to figure files plus human interpretations, automatically attempts to retrieve the source code that generated each figure from near the figure, and interprets each figure with process-level isolation via `codex exec`/`claude -p` in a parallel-vibe-like manner (default concurrency limit 3, adjustable in config.yaml). Not applicable: the user merely wants to resize/crop/convert a figure, or asks to directly modify images or source code (this skill is read-only for images and source code throughout, and modification is strictly prohibited).
Conduct reviewer-style, evidence-safe reviews of academic manuscripts across disciplines using progressive method, domain, review-round, and optional reviewer overlays. Use when the user asks for a critique, scientific review, priority comments, top-to-bottom review, revision-round assessment, prior-comment regression check, or review memo rather than ordinary drafting. Infer the smallest applicable module set from the conversation and manuscript; ask only when unresolved domain or review-profile ambiguity would materially change the review. Includes optional psychometrics and SEM, computational and LLM, water and CNHS, flood and hydrodynamics, and explicit Ethan-style modules.
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.