Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Apply 80/20 leverage to time, talent, assistants, outsourcing, hiring, salespeople, and low-value work. Use when deciding what to delegate, outsource, stop doing, hire for, trial, or remove so high-value people spend more time on their strongest work.
Design a staged, prunable research experiment campaign for a researcher's idea, hypothesis, or optimization direction, with ponytail-for-experiments taste. Use when explicitly requested, or when a researcher proposes a direction that needs many experiments, ablation branches, or cross-factor sweeps. Observe existing results, grill the researcher to shared understanding, enumerate the maximal experiment space, then prune it with cheap probe experiments whose outcomes decide which cells never run; deliver a decision-tree plan with observation gates and the final metrics/figure design, and hand execution to exp-batch per stage. For a single bounded experiment branch use exp-batch; for one-off spot checks use exp-probe.
Comprehensive financial research agent for market data, news analysis, technical indicators, and report generation. Use when Codex needs to: research stocks/crypto/macro data, analyze market trends, scan financial news, generate investment theses, or produce structured research reports. Integrates with Polymarket for price tracking and supports multiple data sources (Yahoo Finance, CoinGecko, etc.).
Apply first-principles thinking to break down complex problems into fundamental truths and rebuild solutions from the ground up. Use when solving strategic decisions, breaking through blockers, or challenging assumptions. Triggers on first principles, Elon Musk methodology, fundamental truths, strip assumptions, physics of the problem, rebuild from scratch.
Tired of manually juggling disconnected tasks, redundant processes, and bottlenecked workflows? Flow-ai brings intelligent automation to your daily operations, helping you design, optimize, and execute smarter workflows without the chaos. Whether you're streamlining team handoffs, automating repetitive sequences, or mapping complex multi-step processes, flow-ai adapts to how you actually work. Built for operations managers, solopreneurs, and productivity-focused teams who want less friction and more output.
Read a research paper and surface publishable theoretical gaps — unstated assumptions, loose bounds, missing guarantees, unjustified heuristics, and settings the theory does not cover. Trigger whenever the user shares a paper and asks to find weaknesses, gaps, open problems, hidden assumptions, or room to extend it. Also trigger on "lemma autopsy", "weekly referee exercise", or requests to weaken one hypothesis in a lemma and locate the first proof step that breaks before reading the authors' discussion. Do NOT use for literature surveys (literature-triangulation), stress-testing the user's own conjecture (theory-counterexample-hunter), writing a peer review (peer-review-writer), or finding papers.
This skill should be used when the user asks to "generate theories", "theorize about", "what theories explain", "form scientific theories", "literature-driven theories", "hypothesize", "form hypotheses", "generate hypotheses", "what hypotheses explain", "run the theorizer", or wants AI-generated, literature-grounded scientific theories or hypotheses about a research question.
Global content search | Use when keyword search on Xiaohongshu/Bilibili/Douyin, note/video details, comments, or creator/UP upload monitoring is mentioned. Prefer access via Agent Reach / OpenCLI / bili-cli / public read-only APIs; when Agent Reach is unavailable, Guaikei API can serve as a last-resort fallback for Xiaohongshu.
A one-question version of grilling. Used to sharpen the user's plan, decision or idea through follow-up questions, but asks only one question per round to avoid throwing multiple questions at once. Suited to users who explicitly ask to "ask only one question at a time" or who want a slower, more focused design interview.
Initialize new JPKB projects with standardized documentation and folder structure. JPKB-specific version with category folders and fixed base path. Use when creating a new project in the jpkb repository, when the user says "init project", "new project", or when the target is the JPKB projects folder.
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.).
Light research mainline step 1, literature search: online multi-source retrieval (OpenAlex/arXiv/Crossref/Europe PMC/DOAJ, no key required throughout) → the output is **not a list of papers but a "domain map" you can feed straight into idea**: the recent three years' frontier + classic foundations + cross-domain method transfer are **searched and ranked separately as three layers**, synthesizing a research lineage + method genealogy + map of unsolved problems, and pinpointing **the paper most similar to your idea** → feed it into idea-critique for a collision warning, and honestly mark retrieval coverage. When to use: researching a direction / finding surveys / learning what work exists in a field / surveying prior art before proposing an idea / collecting Chinese and English papers, patents, standards, datasets, open-source projects, competition solutions, industry reports. Trigger words: literature search / literature review / research direction / domain map / state of the art / what work exists / related work / related work / literature review / survey / frontier / survey / find papers / collision / novelty check / cross-domain / search query. Core discipline: do not fabricate DOIs/citations (write unknown if not found); rank the three layers separately rather than throwing relevance into one pot; a collision only produces a **signal** and no novel verdict (that belongs to idea-critique); mark coverage honestly according to real HTTP codes.
Build auditable peer-review revision and author-response packages for Light stage 13. Use after receiving reviewer comments, a decision or meta-review; when drafting a rebuttal or response letter; when triaging major/minor revisions; when simulating a pre-submission review; or when a rejection may require a user-chosen 13→3 novelty, 13→5 experiment, or 13→8 writing back-edge. Consumes the selected venue/context and real PDF facts, preserves reviewer wording, atomizes issues, binds claims/evidence/actions/provenance, separates PLANNED from DONE, checks current venue limits without borrowing another venue's rules, and emits the stage-13 gate without changing venue, manuscript, evidence, citations, figures, PDF, or passport automatically.
Create comprehensive business strategy with premise deconstruction, business model stress test, pricing, go-to-market plan, and competitive positioning. Runs a 4-layer premise audit before strategy, then generates a full market research report with SWOT, 4P, 10-point business model validation, and constraint analysis. Use when the user has an idea and needs a strategic plan, competitive analysis, pricing strategy, GTM plan, or says 'business plan', 'strategy', 'pricing', 'go-to-market', or 'competitive analysis'.
Naval Ravikant’s mental operating system. Conducts in-depth research based on his books, podcasts, tweets, decision records, and external criticism, distilling 5 core mental models, 8 decision heuristics, and a complete expressive DNA. Once activated, immersively role-play Naval and answer directly from the perspective of “I.” Use when the user mentions “use Naval’s perspective,” “what would Naval think,” “Naval mode,” “Naval perspective,” or “switch to Naval.” It can also be triggered by questions such as “Does this job have leverage?”, “What is specific knowledge?”, “What is true wealth?”, “What should I do about having too many desires?”, or “What is the permissionless path?” Do not trigger for general decision questions such as “What should I choose?” or “Help me think this through”—activate only for Naval’s core concepts, such as leverage, specific knowledge, desire management, and the definition of wealth.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Query the Open Library catalog from the terminal: search books and authors, look up works, editions, and ISBNs, enumerate every edition of a work, read community ratings, and resolve cover-image URLs. Fully keyless public API. Includes the OL…M/W/A key-graph reference, ISBN 302-redirect resolution, search query syntax, covers-host rules, and worked pipelines. Do not use for library-IT administration (Koha/MARC/ILS migration), commercial book-data feeds, or managing your reading account on Open Library itself.
Run end-to-end product experiments from assumption to decision: translate assumptions into testable hypotheses and experiment briefs, select the right method among qualitative interviews, prototypes, concierge tests, fake doors, feature flags, and A/B tests, and produce readouts that update the roadmap and decision record. Do not use when a qualitative or prototype test is the clearly right answer without statistical measurement; do not prescribe A/B testing by default; do not treat statistical significance as the only decision criterion or hide ethical and guardrail considerations.
Prepare the reproducibility, transparency and open-science parts of a paper, including data and code availability statements, reproducibility checklists (NeurIPS, ICML, ICLR, ACL Responsible NLP, Nature reporting summaries), research artifact packaging (Zenodo DOI, CITATION.cff, environment lockfiles, seeds), ethics/broader-impact statements, CRediT author contributions, competing interests and AI-use disclosures. Use when a venue requires any of these statements or checklists, or when preparing code/data for release alongside a paper.
Chain web research, atomic extraction, and durable note capture when the same research-to-notes sequence must repeat. Do not use this skill to design or evaluate an investigation; use `research-methodology` for research questions, methods, and evidence assessment.
Fetch Slack thread from URL using API directly (no MCP server needed). Use when: - User provides a Slack message URL - User says "read this slack thread" or "fetch slack thread" - User wants to see conversation context from Slack - User wants to search Slack messages - User wants to fetch channel history (e.g., Google Calendar DM)
Create concise executive stakeholder updates using the BLUF (Bottom Line Up Front) framework. Use when asked to write a status update, progress report, project communication, or executive briefing for leadership or stakeholders. Produces a BLUF-led update with status, key metrics, risks, upcoming milestones, and decisions needed — readable in under 2 minutes.
Retrieve and summarize all unread emails from your inbox, organized by category, sender, and date. Use this skill when the user asks to summarize unread emails, get an overview of unread messages, organize inbox emails, or review pending email communications. Provides a structured summary with categorization and timeline analysis.
Identifies, monitors, and analyzes industry trends including technology adoption, market shifts, regulatory changes, and emerging patterns using weak signal detection and trend forecasting. Use when the user requests trend analysis, industry forecasting, emerging technology tracking, or wants to identify market opportunities and threats.
Tune the Wispr Flow dictionary from real dictation history through a local CLI: find the names, products, and commands it mishears, fix them safely, and check the fixes worked. Use when the user reports a Wispr Flow transcription mistake ("I said X, it wrote Y"), wants mistakes found in a time window, asks about their Wispr Flow dictations, or wants dictionary words, rules, or snippets changed.
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.