Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Meta-orchestration guide for choosing optimal reasoning patterns. Analyzes problem characteristics and recommends which cognitive methodology to use - tree-of-thoughts (find best), breadth-of-thought (explore all), self-reflecting-chain (sequential logic), or direct analysis. Use when facing complex problems and unsure which reasoning approach fits best.
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
Finds, evaluates, fills, submits, and tracks a candidate's own job applications using a verified resume, evidence-based targeting, secure local profile storage, and browser automation. Use for onboarding or migrating a job-search profile, searching active roles, assessing a posting, applying to an authorized URL or batch, recording outcomes, or reviewing application effectiveness.
Ingest a source into the knowledge bundle. Use when the user wants to capture, ingest, file, process, or "add this" — a note, transcript, email, PDF, image, web page, or any raw source — into a knowledge/ bundle, or drops content for processing. Reads the source once, extracts its signal, and integrates it across the bundle under the trust model so knowledge compounds instead of being re-derived per query.
Portable OKF knowledge bundle for coding-agent memory and LLM wikis. Use when the user wants to start a wiki, ingest a source, document a repository, query project knowledge with citations, lint for drift, or visualize connections; whenever a repo has a knowledge/ bundle that should inform the task; and when another kb-* skill needs the shared spec, glossary, templates, or trust model.
Deeply analyze links, documents or code and generate "all-round mentor-level" teaching notes (from zero basics to mastery). Features "truth anchoring" verification that automatically identifies hallucinations and outdated information. Supports traditional Chinese studies style rendering and automatically cleans ads and useless content.
**Business Korean-English/English-Korean translator**: a business-specialized translation skill supporting industry-specific terminology, politeness levels, and translation styles by document type. It provides translations suited to document types such as emails, contracts, proposals, and reports. - MANDATORY TRIGGERS: 번역, 영어 번역, 한영 번역, 영한 번역, translate, 비즈니스 번역, 이메일 번역, 계약서 번역, 통역
Compresses domain mastery using Ultralearning and Metacognition principles — moving from passive consumption to active production through directness, retrieval practice, and feedback loops. Use when learning a new domain rapidly, building a study plan, or preparing for a high-stakes professional skill.
Lightweight research workflow step 8: paper writing. Organizes the work around “how to convince reviewers that the work merits publication,” iterating from a draft through the reviewer’s perspective. Every claim must have evidence, wording strength must match evidence strength, and overclaiming is never allowed. Use after experiments and analysis are complete and a paper needs to be written; to write or revise an abstract, introduction, contribution statement, or conclusion; when concerned about unsupported claims or exaggerated wording; to align contributions across the abstract, introduction, and conclusion; to use the four-paragraph introduction structure (problem → gap → insight → contribution); to review the draft as a reviewer; or to polish a draft for AI-like phrasing, passive voice, or grammar. Triggers: 写论文 / 论文写作 / 写摘要 abstract / 写引言 introduction / 贡献句 contribution / 写结论 / 润色 polish / 改写 / 措辞 / 过度宣称 overclaim / claim 无证据 / 审稿人视角 / 自我审稿 / 贡献一致 / hedge / 学术腔 / AI 腔 / 被动语态 / paper writing / draft. Core discipline: an unsupported claim is a critical integrity gate (spec §4.2, STAGE_GATES[8]=[claim_evidence,overclaim]); overclaiming or inconsistent contributions across the three sections are warnings (the critical wording red line is at the research-ethics delivery gate). Wording strength must match evidence strength; when results are not significant, report only “no significant difference observed,” and never overclaim. Automated wording checks have limits; final judgments on logic, novelty, and argumentation still require a person or reviewer. This skill initiates rework from 8→7 (unsupported claim → result-analysis) and 8→6 (implementation gap → experiment-coding).
Use when a loop needs scholarly literature — paper discovery, novelty checks, full-text snippet search, citation-graph traversal, single-paper reads, or experimental-result extraction. A shared, stdlib-only CLI (`tools/lit_search.py`) over Semantic Scholar + arXiv (plus optional OpenAlex, Perplexity Sonar, bgpt.pro), all JSON. Not a loop itself: install it alongside the loops and let any of them call it instead of vendoring their own copy. Degrades to the caller's WebSearch/WebFetch.
Control, automate, and interact with Android and iOS phones via the Mobilerun API. Mobilerun automates mobile devices it is NOT a desktop browser automation tool. Use whenever the user wants to automate a task on a mobile device or run a cloud task on a phone. Use when: (1) tapping, swiping, typing, or navigating phone UI directly, (2) running autonomous AI agent tasks on a phone, (3) taking screenshots or reading screen state, (4) managing devices — provisioning, renaming, rebooting, terminating, (5) managing apps — install, uninstall, list packages, (6) configuring proxies, eSIM, GPS location, or file transfers, (7) managing credentials for automated app logins, (8) subscribing to task webhooks, (9) multi-device operations — fleet management, parallel tasks across phones. Do NOT use for desktop browser automation, computer screenshots, or controlling a desktop OS. Also load when the user mentions Mobilerun, Droidrun, or phone control. Supports both personal devices (via Portal APK) and cloud-hosted devices. Requires a Mobilerun API key (prefixed dr_sk_) and a connected device.
Generate an executable action plan for a "viable" opportunity selected by the user: a low-cost first validation step, concrete actions for the first two weeks, honest revenue expectations, and a stop-loss line. Trigger phrases: "我想做XX帮我做计划"/"这个怎么开始"/"给我行动方案"/"money plan"/"我选这个". Prerequisite: the opportunity should preferably have passed money-verify as viable/uncertain.
The anti-scam core of the cheat-on-money skill. Scores a specific side job/side hustle/project against an anti-scam rubric, verifies negative and genuine payment evidence online in real time, and outputs a high-risk/questionable/feasible verdict + first verification step + honest income expectations. Trigger words: "is XX legit"/"is this project a scam"/"help me check this side job"/"money verify"/"verify opportunity"/"can I trust this".
Nextcloud files and administration via WebDAV and the OCS API. Use for any Nextcloud file or instance task: upload or download a file, PROPFIND directory listing, MKCOL, MOVE, COPY, chunked upload of large files, trash bin and file versions, sharing a file, public link with password and expiry, share permissions, creating or disabling accounts, quotas, groups, subadmins, app tokens, enabling apps, instance capabilities. Triggers: nextcloud, webdav, remote.php/dav, ocs, user-provisioning, quota, облачное хранилище, публичная ссылка на файл, шаринг файла, загрузить файл, пользователи.
Build comprehensive, mobile-compatible Obsidian study vaults from academic course materials with checkpoint-based workflow, error pattern recognition, and quality assurance. Battle-tested patterns from 828KB/37-file projects. Works across all subjects - CS, medicine, business, self-study.
Search an Obsidian vault three ways — Meilisearch for topic and fuzzy queries, ripgrep for exact strings/tags/task glyphs, and a date-aware helper for natural-language dates and overdue math. Use when finding notes about a topic, half-remembered ideas, recent writing, tagged content, or due/overdue/high-priority tasks in a local Markdown vault. Do NOT use to add or edit notes (use obsidian-capture).
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a PRD for a complex feature space.
Transform an output-focused roadmap (feature list) into an outcome-focused one. Rewrites initiatives as outcome statements reflecting user and business impact. Use when a roadmap lists features instead of results, when making a roadmap more strategic, or when communicating what success looks like vs what will be built.
Run a cumulative daily or retrospective sweep of research papers on a chosen topic, audit their claims, methods, integrity signals, and independent support, then identify overlooked but feasible project or business opportunities in a detailed source-grounded report. Use when asked to monitor papers every day, mine buried research, evaluate whether a paper is credible or reproducible, find unimplemented research ideas, or separate promising work from hype, weak evidence, and retracted or contradicted results.
Product-management copilot based on the Pragmatic Institute Framework (Foundations, Focus, Build). Use this as the entry point whenever a product manager wants to work through building a product or feature the market-driven way — e.g. "I want to build a feature", "help me plan this product", "where do I start", "I have an idea for X". It figures out where the PM is in the Pragmatic journey, guides them through the right stages (market research, personas, positioning, strategy, requirements, roadmap, launch), and produces a client-ready artifact (Markdown or Word .docx) at every stage. Also use it to explain the Pragmatic Framework or choose which PM artifact to create
Score and rank product opportunities objectively with the Pragmatic Institute Opportunity Scoring model — across distinctive competency fit, competitive landscape, investment level, and impact to buyers/users. Use when the PM asks which idea to pursue, "score these opportunities", prioritize projects/bets, or compare options objectively instead of by opinion. Produces an Opportunity Scorecard as a Markdown or Word .docx artifact
Build and manage a product roadmap for a solopreneur business. Use when deciding what to build next, prioritizing features, planning product development over quarters, communicating plans to customers or stakeholders, or managing scope and expectations. Covers prioritization frameworks, roadmap structure, customer feedback integration, and saying no to feature requests. Trigger on "product roadmap", "what to build next", "feature prioritization", "roadmap planning", "product strategy", "feature requests".
Plan, focus, and complete work with energy management, time blocking, goals, projects, tasks, habits, reviews, priorities, and context-specific productivity systems; use when (1) the user needs help with productivity, focus, time management, planning, priorities, goals, projects, tasks, habits, or reviews; (2) they want a reusable structure or workspace for organizing work; (3) ongoing work should be routed through a dedicated productivity framework.
Design and operate consulting engagement governance: decision rights, steering committees, RACI, risk and issue registers, status reports, escalation, and stage gates. Use for oversight of delivery; use implementation-planning when available for the execution plan itself.
Use when working with, adding to, or updating the shared cross-project research library at $RESEARCH_HOME (vendor repo clones, reference PDFs/epubs, mirrored docs pages) — before fetching the same material from the web, when cloning a reference repo for a project, or when asked to update/refresh the library. Also owns judging a named package or tool before depending on or installing it — from PyPI, npm, crates.io or apt, or shipped only as GitHub release binaries: whether it is still maintained, who actually commits to it, how often it releases on its stable line, what a release really ships and costs (wheel or sdist, npm platform packages and install scripts, prebuilt binaries), whether its Python, node or glibc floor fits this machine, how far an apt package lags upstream, whether it ships types, how much test suite backs it, whether a version cap will hold you back — read from the registry, the GitHub API and the project's own source rather than from a search summary.
Rewrite raw meeting audio transcriptions into clean, accurate meeting minutes in Traditional Chinese. Use when the user has an unprocessed audio transcription file with recognition errors and needs it cleaned up into proper meeting minutes.
Extract full text from WeChat public account articles (mp.weixin.qq.com). Use when the user provides a WeChat article URL and asks for 提取文章, 抓取公众号, 读一下这篇, or when another skill needs to read a WeChat article before processing. Bypasses WeChat's access control via MicroMessenger UA spoofing. Stdlib only, no API key required.
Use when someone asks to roast an idea, pressure-test or stress-test an idea, validate a business idea, "convene the panel", get a brutal second opinion before building something, or says "/roast". Spins up a 5-angle panel (Critic, Champion, Analyst, Investigator, Customer) that attacks the idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it.
Create and manage scheduled tasks, with support for viewing, modifying, enabling/disabling, deleting and creating scheduled tasks. Use when the user wants to set up, modify or manage tasks that run automatically on a schedule. Create and manage scheduled tasks for recurring or one-time automated execution.
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.