Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
A lightweight systematic review and literature-screening workflow: inclusion/exclusion criteria, bibliographic screening records, and a summary of PRISMA process intent and checklist items. Complements literature (writing and citations); does not replace the full official PRISMA guide. Suitable for contexts such as “systematic review”, “PRISMA”, “inclusion/exclusion”, and “screening flowchart”.
Analyse complex systems from elements to relationships, from parts to the whole, and from static to dynamic. Suited to situations where problems keep recurring, where one change affects everything, and where piecemeal fixes fail. When you find that "the harder you try, the worse it gets" or that "the problem always comes back", you need to switch to systems thinking to find the root solution. Not applicable to simple single-cause problems or urgent situations requiring fast action. Key trigger signals: "why does this problem keep recurring", "changing A only broke B", "it feels like being stuck in a dead loop".
Prepare an evidence-based team retrospective, monthly delivery review, report, or presentation from a private team profile; it collects its own planning and delivery evidence, unlike briefing. Use when the team runs a retrospective or monthly delivery review, or needs a report or presentation from its own profile. Russian discovery terms: ретро, итоги месяца, месячный отчёт, презентация команды.
Review or update an evidence-based team roadmap from a private team profile without creating work items. Use when the manager reviews or updates the team roadmap from evidence without creating work items. Russian discovery terms: дорожная карта, роадмап, квартальные итоги, планы команды.
Telegram CLI for AI agents. Use when the user needs to read or search Telegram, send or edit a message, download media, organise Saved Messages, monitor conversations, or automate a Telegram task. Triggers on “check my messages”, “send a message”, “search Telegram”, “read unread”, “listen to chat”, “download from Telegram”, тэг сохранёнок, чаты, каналы, and @peer names.
Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the `claim-verifier` agent in a fresh context (never a conversation fork) so it never sees the draft — then reports which claims are supported, contradicted, or unverifiable. Use when user says "verify these citations", "check the claims in X", "did I hallucinate anything", "fact-check this draft", "run CoVe on this", or after any text generation that asserts facts about papers, datasets, or numerical results. NOT for style/grammar review (use `/proofread`) or substance review (use `/review-paper`).
Transform Obsidian video notes from the Vault into published notes on joelclaw.com. Use when publishing video notes, converting vault video content to the site, or when asked to 'publish a video note,' 'turn this video into a note,' 'publish from vault/videos,' or any task involving /Vault/Resources/videos → joelclaw content. Triggers on references to video notes, vault video files, or publishing video content to the blog.
All network operations must be handled through this skill, including: searching, web scraping, post-login operations, dynamic page interaction, and more. Trigger scenarios: the user asks to search for information, view web page content, access sites requiring login, operate web interfaces, scrape social media content (Xiaohongshu, Weibo, Twitter, etc.), read dynamically rendered pages, and any network task requiring a real browser environment.
Summarizes WeChat official account article content. Use this skill when the user provides a WeChat official account article link (mp.weixin.qq.com) and asks to summarize, outline, abstract, or quickly understand the article. Also applies to requests such as "help me see what this article is about," "what does this official account article say," or "summarize this link." Whenever you see a mp.weixin.qq.com link and the user wants to understand the content, you should use this skill.
A standalone Skill for crawling, filtering and exporting public WeChat Official Account articles. Use when the user mentions WeChat Official Account, Official Account articles, mp.weixin, wcx, searching Official Accounts, exporting the last N days or a given year of articles, batch crawling, resumable crawling, full-text completion, tutorial article filtering, or saving WeChat article links. Supports Markdown/JSON/CSV, uses wcx to fetch the index and Playwright to extract the body by default; the paid Metaso fallback requires explicit authorization.
ZenTao (禅道) product plan management — list product plans and get product plan details. Triggers when the user says: 'query product plans', 'product plan list', 'what plans are there', 'productplan 列表', 'view product plan', 'plan details', '禅道产品计划'.
Channel the strategic thinking of fastest-growing AI startup founders. Use when asked to analyze current state, brainstorm strategy, set OKRs, or create execution plans. Provides founder personas, strategic frameworks, and battle-tested patterns from Anthropic, OpenAI, Mistral, Scale AI, and others.
This skill should be used when the user asks about "survey design", "questionnaire construction", "Likert scale", "question wording", "response bias", "survey tool", "Google Forms", "Qualtrics", "SurveyMonkey", "Typeform", "pilot testing", "survey distribution", "act as a survey builder", "survey builder mode", "survey instrument", "closed-ended questions", "open-ended questions", "rating scale", "semantic differential", "survey flow", "skip logic", "branching logic", "response rate", "survey fatigue", "questionnaire validation", "pre-test survey", "online survey", "survey analysis", "Cronbach's alpha", "factor analysis", "survey consent form", "demographic questions", or needs expertise in designing, building, distributing, and validating survey instruments. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).
Help a PhD student recover motivation, reframe setbacks, and rebuild momentum after rejection, failure, stagnation, or burnout. Use whenever the user feels stuck, discouraged, or lost in their PhD — including phrasings like "I don't know why I'm doing this", "my paper got rejected again", "my experiments keep failing", "I feel behind everyone else", "I'm thinking of quitting", "my advisor doesn't believe in me", "I haven't made progress in weeks", or "is a PhD even worth it". Also use proactively when the user seems demoralized mid-conversation. This is not a therapy replacement — it is structured support for navigating the specific emotional and cognitive patterns that make PhD work hard, grounded in the reality of what research actually is.
Pilot a spatial canvas from the CLI — create canvases, generate images/text/video/agent responses, read results, recall past work, and manage nodes. The canvas is a shared workspace visible in the browser; this skill gives you a live cursor on it. Use this skill whenever the user wants to interact with the canvas platform, asks to generate images or videos on canvas, mentions "canvas", "Neo", "Agent Neo", wants to draw/create/generate visual content on the spatial canvas, references past canvas work, or says anything that implies operating on the canvas. Also triggers on /canvas-pilot.
Activate when the user faces an important decision and needs systematic checking for omissions, when the user is overconfident in their own experience or judgment, when the user is a domain expert but is dealing with a complex or high-risk situation, or when the user needs to orchestrate their own mental models into a repeatable decision process. Typical trigger signals: the user says "I'm very experienced, I don't need a checklist"; the user makes decisions under high pressure; the user admits "in hindsight I missed a key factor." Not applicable to simple, low-risk everyday decisions or purely creative/exploratory thinking.
Use when reading or changing anything in ClickUp via the `cup` CLI - tasks, sprints, comments, Docs, Chat, views, webhooks, or workspace structure. Triggers: task queries, status updates, sprint tracking, creating subtasks, posting comments, threaded replies, standup summaries, searching tasks, checking overdue items, assigning tasks, ClickUp Docs and doc pages (read, create, edit), ClickUp Chat channels and messages, views and view tasks, webhooks, exporting or archiving ClickUp data (knowledge transfer, off-boarding), creating or renaming spaces, folders, and lists, list templates, opening tasks in browser, checking auth or config, setting custom fields, deleting tasks, managing tags, managing checklists, editing comments, task links, time tracking, attachments, file uploads, listing members, listing fields, duplicating tasks, bulk operations, goals, key results, saved filters, favorites.
Provides systematic approaches for solving constraint-based scheduling problems, such as finding meeting times that satisfy multiple participant availability windows, preferences, and existing calendar conflicts. This skill should be used when tasks involve scheduling with constraints, calendar conflict resolution, time slot optimization, or finding valid time windows across multiple inputs with hard and soft constraints.
Count how many independent origins are behind news coverage of a claim, instead of counting URLs. Queries GDELT for matching articles, collapses reprints and wire copy into single origins, and flags publication bursts that indicate syndication. Use when a claim appears to be confirmed by many outlets and you need to know whether that's many sources or one source many times.
Help users identify and escape psychological traps that are holding them back. Use when user feels stuck, unable to progress, facing a deadlock, or experiencing decision paralysis. Provide diagnostic frameworks and specific strategies to help users understand which trap pattern they're in and find a path forward.
DeepKnow knowledge and retrieval assistant — manage and import knowledge; search internal materials, professional literature, food standards, and policies on controlled official websites; read summaries and full text as needed; and query real data from 食品伙伴网 and tables.
When the user feels like a bottleneck, needs to hand off responsibilities, wants to free up their time, or says things like 'I'm the bottleneck,' 'I need to delegate,' 'I'm doing too much,' 'what should I stop doing,' 'how do I hand this off,' 'I can't scale myself,' 'team can't operate without me.' Maps to the 5 Levels of CEO Evolution: Doer → Delegator → Director → Designer → Decider.
Invoke when the user reacts disproportionately strongly to losing (or about to lose) something, or rushes to "break even" after a loss and cannot cut their losses. Typical trigger signals: sunk cost trap, gambler's escalation, irrational bidding in auctions, inability to abandon a failing project in which large resources have already been invested. Not applicable to general investment valuation (use value-assessment) or herding behavior (use misjudgment-checklist).
Use when the user asks to list, show, or review open issues — from the tracker recorded in docs/agents/issue-tracker.md, whether GitHub, Jira, local markdown, or another backend, or from a repository or project the user names. Read-only: not for creating, editing, closing, or triaging issues.
Generate a FigJam project plan board from a PRD plus codebase context. Interactive flow: research → propose sections → per-section deep research → per-section content + block-shape proposal → create FigJam → skeleton → fill → diagrams → wrap. Each content block (section, nested section, intro callout, table, multi-column text, sticky column, diagram section, metadata strip) has its own subskill reference file. Use when the user asks for 'project plan in FigJam', 'interactive project plan', '/generate-project-plan', or provides a PRD and wants per-section confirmation on content + rendering.
Get Image [from] Internet Link - Zero-setup CLI for downloading full-resolution images from iCloud, Dropbox, Google Photos, and Google Drive share links. Four-tier capture strategy, browser automation, HEIC conversion, album support. Node.js/Playwright.
Use the bundled Google Workspace CLI (gws) to read, create, update, and delete Google Calendar events, list calendars, and show agendas. Use when the user asks to connect or operate Google Calendar, or to manage events on their Google Calendar, or says "谷歌日历"、"Google 日历"、"看看我 Google 日历上的安排".
Use only when the user explicitly names grill-me or explicitly asks for an interactive grilling of a plan, decision, or idea. Stress-test the decision by resolving facts from available evidence, asking one unresolved decision-changing question at a time, and stopping when no material branch remains; do not implement the plan.
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.