Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Analyze gaps by comparing a defined current state with a justified target state, characterizing causes and uncertainty, prioritizing actionable interventions, and producing traceable matrices, roadmaps, and decision records. Use for capability, process, compliance, readiness, maturity, operating-model, or research-evidence gaps. Do not use for a vague list of problems, a standalone root-cause analysis, a generic SWOT, or legal or audit certification advice without a governing standard and qualified owner.
Google Maps via CDP — three modes, all keyless (no Google Places or Directions API key, no quota): (1) local business search returning structured results (name, rating, reviews, price, category, address, hours, coords, place ID, URL) — the data the metered Google Places API sells; (2) --route for real directions (total time + distance, current traffic) for an ordered list of places, in any travel mode (--mode driving|transit|walking|cycling|flights|best, default driving); (3) --optimize for a best-effort fastest visiting order (open-path TSP, fixed start) whose edges are virtualized as straight-line distance — N parallel place lookups plus one real directions call. Use when the user asks to find local businesses, get directions/time between places (by any mode), or plan a multi-stop route order. Requires browser-harness-js on PATH and a running Chromium-based browser with remote debugging.
Create incident communication playbooks for outages, data issues, payment failures, store launch problems, privacy incidents, game economy issues, support backlogs, and degraded product experiences. Use when planning status updates, customer notices, internal coordination, postmortems, support macros, incident timelines, or trust-recovery communication.
Achieve innovation with two systematic methods: recombinational innovation (collect elements outward and recombine them) and mutational innovation (decompose inward and modify existing structures). Every innovation must satisfy three elements at once: a new element + value increment + implementability. Use when you need to break out of existing frameworks, find new products/solutions, or solve the problem of "innovation relying on luck". Not applicable to purely executional optimization (which needs no new element). Key trigger signals: "need new ideas" / "how to innovate" / "out of creative ideas" / "products are severely homogenized".
Builds a structured project knowledge base of 10 canonical .md files at knowledge-base/ (project root). Has dual mode: silent generation from existing source documents in docs/, or interactive iterative creation from scratch. Trigger: When user asks to create, build, or generate a knowledge base for a project, document a project from source documents (.txt, .docx, .pdf), or asks to "armar base de conocimiento" / "crear KB" / "documentar proyecto".
Manage your personal knowledge base of curated resources, bookmarks, and excerpts. Triggers include "knowledge base", "kb", "add to knowledge", "add tabs to", "what do I have on", "what do we know about", "find resources about". Use with safari-tabs skill for bulk ingestion from Safari windows. Location is ~/knowledge/.
Manage the LifeOS Knowledge Archive — a curated, typed graph of People, Companies, Ideas, and Research notes with typed related: links; search, add, harvest, develop, ingest, and graph-navigate. USE WHEN knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, ingest, contradictions, knowledge graph, retrieve, mine conversations. NOT FOR session/ISA context recovery (use ContextSearch), published content semantic search across blog/newsletter/X/LinkedIn, or one-shot URL/YouTube ingestion via the Arbol harvester pipeline.
Full-featured MCP Skill for the Lexiang knowledge base. Use when users mention "乐享", "知识库", "个人知识库", "我的知识库", "lexiang", provide a lexiangla.com link, or involve knowledge base operations such as search, write, edit, file, or configuration.
Assistant for Chinese-language literature search, screening, batch collection, and lawful full-text retrieval. Use when the user needs to find papers, download lawfully available PDF/HTML/XML full texts, generate keywords and search queries, look up DOI/PMID, screen for high-impact-factor or high-quartile journals, check open access, expand citation chains, build batch literature candidate lists, download logs, deduplication lists, or Zotero/BibTeX organization, or troubleshoot papers that are hard to download; bypassing paywalls, pirated downloads, shared accounts, and copyright circumvention are prohibited.
Operate the user's already-open, logged-in Chrome tabs through Chrome DevTools MCP. Use whenever the user asks the agent to jump into their current browser, continue work in an existing tab, fill or submit a form, write or post a comment or reply, update a page, inspect what is open, or interact with signed-in web apps such as Confluence. Also use as the browser-driving companion to melech-debug-mode; do not start a debugging collector for ordinary browser work.
This skill should be used when the user mentions "openclaw", "OpenClaw CLI", asks to "send a message via openclaw", "manage openclaw agents", "configure openclaw gateway", "check openclaw status", "run openclaw agent", or asks about OpenClaw setup, channels, devices, or messaging automation.
Use this skill when the user asks MoviePilot to identify and organize a local or downloaded video/music file, season folder, recording, album directory, or mixed folder that automatic transfer did not handle. If failed transfer history IDs are supplied, use transfer-failed-retry instead.
Automatically OCR, rename, and sort receipt images/PDFs/videos by date, amount, and project, with summary reports and D365 expense mapping. Use when sorting receipts, organizing expense files, OCR renaming, receipt sorting, レシート仕分け, or D365経費カテゴリマッピング.
Judges whether RHDH Jira work that already exists is ready to move forward — in RHIDP, RHDHPLAN, RHDHBUGS, and RHDHSUPP. Checks an issue, a JQL result, a sprint, or a backlog against the exit criteria for its status, then reports missing fields, hierarchy gaps, likely duplicates, unaddressed comments, stale work, and Feature Exploration readiness. Use for "is RHIDP-1234 ready", "refine this", "refine the backlog", "backlog hygiene", "what's missing on this epic", "run the Feature Exploration checklist", or "which of these are stale". Assesses existing work; it does not open new issues and does not build a sprint.
Builds the planning package for an RHDH scrum team's next sprint from Jira RHIDP, RHDHPLAN, RHDHBUGS, and RHDHSUPP: carryover from the active sprint, three-sprint velocity, per-member capacity, the ready-for-planning queue, available capacity, suggested fill, critical customer bugs, and retro action items. Use for "plan the sprint", "sprint planning prep", "what's our capacity next sprint", "what can we commit to", or "what's carrying over". Works on a team and a sprint, not on one issue — a bare key such as RHIDP-1234 is not a sprint. Looks forward at the sprint that has not started; summarizing the one that just ended is a different job.
Build and query fully local RAG knowledge bases from documents (PDF, MD, code, etc.) using RLAMA and Ollama — no cloud, no data leaving the machine. Triggers on 'local knowledge base', 'search documents', 'document Q&A', 'RAG query', 'ingest files', 'semantic search'.
Systematic framework for evaluating scholarly and research work based on the ScholarEval methodology. This skill should be used when assessing research papers, evaluating literature reviews, scoring research methodologies, analyzing scientific writing quality, or applying structured evaluation criteria to academic work. Provides comprehensive assessment across multiple dimensions including problem formulation, literature review, methodology, data collection, analysis, results interpretation, and scholarly writing quality.
Make rational, objective decisions with a four-step process: stay focused on the goal and filter out trivia → find a third option to break past the either-or constraint → sidestep cognitive biases → score quantitatively to make the final choice. Use when facing a major decision and feeling stuck, when options seem to be either-or, or when you worry about being misled by intuition. Not applicable to everyday low-risk small decisions (over-quantifying just wastes time). Key trigger signals: "torn between A and B" / "don't know how to choose" / "unhappy with both but must pick one" / "help me make a decision".
Slack API integration with managed OAuth. Send messages, manage channels, search conversations, and interact with Slack workspaces. Use this skill when users want to post messages, list channels, get user info, or automate Slack workflows. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
Deep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any task requiring verified information. Triggers on "조사해줘", "리서치", "research", "investigate", "fact-check", "비교 분석", "검증해줘".
Manage technical programs made of multiple related projects, products, teams, or vendors: establish the program mandate and benefits, align component work, manage cross-project dependencies and shared capacity, govern risks and decisions, coordinate transformation and adoption, and communicate program health to executives, delivery teams, and partners. Use when the work is a coordinated change larger than one project or when component projects are locally green but the combined outcome is at risk. Do not use for single-project control, detailed implementation planning, product portfolio or capital-allocation decisions, enterprise architecture design, release approval, or live incident command; route those to the named specialists.
Turn abstract math or ML ideas into minimal examples, counterexamples, sanity checks, and tiny simulations. Use for theorem intuition, debugging derivations, constructing stress tests, converting a research idea into small checkable cases, or when a concept is too abstract or a claim needs intuition or falsification.
Use when fact-checking a single wiki page against its cited sources — verifies that every footnote actually supports its claim and surfaces uncited factual claims. Run after ingesting a high-stakes page or any time you want confidence in one page's accuracy.
Read and use comments attached to the current PostHog task, its artifacts, and any canvas through the PostHog MCP exec dispatcher. Use when the user mentions task comments, artifact or canvas comments, annotations, selected-text feedback, replies, unresolved comments, or asks an agent to inspect or act on feedback left in PostHog Desktop. Covers exec discovery and calls, target filtering, pagination, full-thread retrieval, anchor/version context, task-scoped access, and standalone canvas comments that have no task
Manage a Zurl short link service — create, update, delete, search, and list short URLs, and fetch URL metadata. Trigger whenever the user asks to "shorten this link", "generate a short URL", "create a short link", "短链接", "缩短", "短链", manage short links, or pastes a long URL and asks to make it shorter. Do NOT skip this skill just because the user didn't explicitly say "短链接" or "short URL" — even "帮我缩短这个链接" or "把这个 网址变短" should trigger it. Any request involving URL shortening, short link management, or batch URL operations should use this skill.
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.