Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Control the mouse, keyboard, and read screen content via accessibility. Use this skill when the user asks to click somewhere on screen, type text into an app, move the mouse, press keyboard shortcuts, read what's on screen, get the accessibility tree of the current window, automate desktop interactions, or control the computer.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
This skill MUST be used when a user wants to scan, audit, analyze, or tidy up a folder or collection of files — whether uploaded directly to the conversation, specified by local path, or described verbally. Trigger on requests like 整理檔案、掃描資料夾、幫我分類檔案、檔案整理計畫、資料夾結構建議、file organization, folder audit, help me sort my files, clean up my downloads, rename and categorize files, suggest a folder structure. MUST follow a plan-first, execute-later pattern, and MUST NOT rename, move, or delete anything before the user confirms the full plan.
AI builder daily — tracks top AI builders on X and YouTube podcasts, mixing content into easy-to-read summaries. Use when the user wants to know about AI industry news, what builders are up to, or calls /ai. No API keys or dependencies required — all content is fetched from a central feed.
Query trending GitHub projects, with filtering by programming language, date range, and spoken language (documentation language). Use this skill when the user wants to know about GitHub trending projects today/this week/this month, trending repositories in a specific language, or trending projects with Chinese documentation.
Use this skill when the user requests current information, documentation, coding examples, or web research beyond the knowledge cutoff. Queries Google's AI Search mode to retrieve comprehensive AI-generated overviews with source citations from 100+ websites. Returns markdown with inline footnoted references [1][2][3]. You will receive a detailed Markdown file with references and information summarized directly from Google's AI search. Ideal for you to get new information and clues for further research.
Google Calendar API integration with managed OAuth. Create events, list calendars, check availability, and manage schedules. Use this skill when users want to interact with Google Calendar. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
Apply structured critical thinking — identifying claims, evidence, reasoning chains, hidden assumptions, and logical fallacies — to evaluate or construct specific written arguments rigorously. Use this skill when the user presents a concrete argument, claim, op-ed, research finding, or piece of reasoning to be analyzed for logical validity or flaws, even if they say 'is this argument valid', 'what logical fallacies are in this', or 'what assumptions am I making in this thesis'. Do NOT use for casual plan review, trip planning, project risk brainstorming, or pre-mortems — 'poke holes in my plan' requests are red-team / risk review, not argument analysis.
Apply classical rhetoric — Ethos, Pathos, Logos — to analyze persuasive communication and craft effective arguments. Use this skill when the user needs to make a speech more persuasive, analyze why a piece of communication is effective, write a compelling proposal, or evaluate rhetorical strategies — even if they say 'make this more convincing', 'why is this speech so powerful', or 'how do I persuade the board'.
Read and send email via IMAP/SMTP. Check for new or unread messages, fetch content, search mailboxes, mark messages as read or unread, and send emails with attachments. Supports multiple accounts. Works with any IMAP/SMTP server, including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
Fetch webpage text with a normal HTTP request first, then automatically fall back to jina.ai proxy when direct access fails or returns login/JS-blocked content. Use when extracting content from X (Twitter) or other pages that are hard to read directly.
Use this skill for Jira work items with Atlassian CLI (`acli`). Trigger it whenever the user mentions Jira, JQL, issue or ticket keys like `ABC-123`, assignees, status changes, comments, rich-text Jira descriptions, or Markdown that needs to become Jira ADF. Resolve the project from an explicit issue key or project key first, then `.jira-skill.json` (searching up to repo root), then `~/.config/jira-skill/config.json`, then STOP and ask the user — never auto-select. Do not use it for GitHub PR edits, repo/codebase searches (even if "jira" appears as a package or library name), git branch naming, Confluence, auth setup, REST API scripting, or non-Jira trackers.
Verify scholarly references and claim-citation support for Light stage 10. Use when auditing a manuscript, claim map, bibliography, DOI/arXiv/PMID/ISBN/URL, BibTeX/CSL, citekeys, chimeric or fabricated citations, retraction/correction alerts, or preparing a canonical citation registry for typesetting. Builds provenance-preserving inventories, confirms metadata with independent authoritative sources, distinguishes CONFIRMED/CONFIRMED-MISSING/UNAVAILABLE/UNRESOLVED, records Crossref update direction, and emits the citation gate plus delivery artifacts.
Light research mainline step 3 · idea generation: structurally diverge from a vague direction/data/literature (stimulate the computation system to generate, not generic brainstorming) → produce tiered candidate ideas that are worth doing and doable (moonshot sprint / solid steady / safe fallback), each answering why it is worth doing · the innovation point · how it beats the existing state · what concrete problem it solves · what venue tier it can target, and carrying a pre-emptive collision self-check at proposal time (closest prior work + delta, feeding off the upstream literature-search domain map). When to use: the user asks "what can this direction/data do" / wants innovation points, research directions, topic selection, breakthroughs / asks me to help think of ideas / brainstorm research ideas / whether an idea holds (generate first, then send to idea-critique for strict review). Trigger words: propose idea / think of idea / innovation point / research direction / topic selection / breakthrough / differentiation / what can this direction do / what is there to do / brainstorm / research idea / ideation / new idea / project initiation. Core discipline: never issue the final verdict of novel/non-innovative (that is idea-critique's critical gate; the generation side only produces collision warn signals); constrain candidates along the lineage evidence root → mechanism/hypothesis delta → information gain → minimal discriminating experiment; pass the innovation_engine anti-stitching gate, binding the typology of originality source (new problem/new mechanism/new measurement/new data/new theory/cross-domain transfer/engineering increment) to claim strength; count/seven angles are advisory only, mechanism diversity is the hard gate.
Always-on Light skill for runtime project memory and project management: land "how far the project got / what was decided / which version shipped / how terminology is unified / where we left off" in each project's own .light/ directory (project card + decision log + version history + controlled glossary + cross-session handoff card), reusing the passport.py engine to manage the DAG ledger (no reinvention). It owns the consistency source of truth: change a definition and the change broadcast rescans all materials; it is the memory substrate for the controller's "automatically report where we left off at session start". When to use: long-running/cross-session projects, when background/progress/version/decisions must be remembered, resuming or taking over at session start, logging important progress immediately, handing off as context runs out, after changing terminology/metric/innovation-point definitions. Trigger words: memory / project management / project card / decision log / version history / version record / resume / take over / where we left off / next step / handoff / startup prompt / glossary / change broadcast / archive / ledger / .light / passport / cross-session. Core discipline: memory goes into explicit .light/ files (not vector retrieval); convert relative dates to absolute; external mutable facts carry [snapshot]; for self-consistency use pm.py audit and its exit code (don't just say "it's recorded"); irreversible decisions (archiving / writing back lessons) stop and ask the user.
Light research mainline step 5 · research plan and experiment design: break the idea cleared by idea-critique and the data feasibility into a truly executable, paper-ready, reproducible question/estimand, experiment matrix and preregistration package. When to use: the idea has passed review and needs to land / experiments, ablations, comparisons, sensitivity, generalization, robustness need designing / writing a research plan PROJECT_PLAN / locking the primary outcome, exclusion/stopping rules or preregistration / planning sample size, seeds and statistical power / computing an experiment compute budget / reproducing an existing paper / worrying that the baseline is watered down or the hypothesis cannot be falsified. Trigger words: research plan / experiment design / experiment matrix / hypothesis / control baseline / ablation / fair comparison / falsifiable / statistical power / how many seeds / reproduction / reproducibility / research plan / experiment design / reproducible. Core discipline: unfair comparison (watered-down baseline) / non-falsifiability = critical veto (spec §4.2, STAGE_GATES[5]=[fair_baseline,falsifiable]); an ablation that doesn't isolate / underpowered = warn; power is back-computed at the planning stage, not a post-hoc result check; lint is heuristic and bounded, and the final verdict on fairness/falsifiability still needs human/domain judgement — never claim "proved the comparison is absolutely fair".
Comprehensive Confluence documentation management. Use when asked to "upload to Confluence", "download Confluence pages", "convert Markdown to Wiki Markup", "sync documentation to Confluence", "search Confluence", "create Confluence page", "update Confluence page", "export Confluence", "publish to Confluence", or "Confluence CQL query". Handles Wiki Markup conversion, Mermaid/PlantUML diagrams, image handling, large document uploads without size limits, and Git-to-Confluence sync with mark CLI.
Break down an article and extract reusable material (opinions, data, cases, quotable lines, analogies, methodologies), label it by category, and store it in the material library. Use when the user says "拆解素材", "入库", "收集这篇文章", "提取素材", "分析这篇文章的要点", or feeds in an article hoping to retain valuable content. Even if the user merely shares an article and says "这篇不错", consider whether it should be stored.
This skill should be used when the user asks to "query my NotebookLM notebook", "ask NotebookLM about these sources", "get a citation-backed answer from my documents", or "search my NotebookLM library". Provides browser automation, library management, and persistent auth for querying Google NotebookLM notebooks directly from Claude Code, returning source-grounded answers from Gemini instead of general knowledge.
Use when: you need to continuously monitor competitor activity, set up competitor intelligence alerts, regularly produce monthly competitor monitoring reports, or track competitor changes in version/pricing/features/sentiment/funding. Do not use when: you only need a one-off competitor study (use pm-market / pm-search --type=competitor); the product has no clear competitors yet.
Use when: you need to design user interview/user research plans, write interview outlines, plan samples and recruitment, or define interview execution and analysis methods. Do not use when: you only do desk research on requirements (use pm-demand); a clear conclusion already exists and you only need to validate a single assumption without interviews.
Professor Skill creates a university-course skill from slides, syllabi, exams, transcripts, notes, and chat logs. Use when the user wants a review-first, exam-focused, teacher-style skill that models how a professor highlights topics, writes questions, and deducts points.
Read an existing research outline and fan out independent background agents to deeply research each item, producing one structured JSON per item against the shared field schema. Resumable, batched, with output disabled per agent (each agent has its explicit output file). Use when `outline.yaml` + `fields.yaml` from `/research-outline` are in place and you want to parallelise the per-item investigation — academic paper deep-dives, product comparisons, benchmark fills, multi-target competitive analysis. Trigger this after `/research-outline`, before `/research-report`.
Summarise a completed deep-research run into a single markdown report — full coverage of every defined field, automatic skipping of uncertain values, and a navigable table of contents with user-chosen summary columns. Generates a fresh `generate_report.py` per run (against a stable spec) and executes it. Use after `/research-deep` finishes when you want a readable artifact for sharing, archiving, or comparing items across the chosen schema.
Power-user audit of Origin's pending surfaces. Most users want `/brief` for revisions. That handles the daily flow. Use `/review` only for explicit deep-walk audits after bulk imports, or when you want to walk the full queue rather than the top 3 shown in /brief. Invoked as `/review captures` or `/review revisions`.
Supplies the craft of writing good RHDH Jira work in RHIDP, RHDHPLAN, RHDHBUGS, and RHDHSUPP: the Feature, Epic, Story, Task, and Bug description templates with filled examples, the RHDH challenge matrix that stress-tests scope, sizing, acceptance criteria, and Epic independence, the T-shirt and Fibonacci sizing scales, keyword duplicate detection, and the tracer-bullet rules for breaking a Feature into Epics or an Epic into Stories. Use when drafting or judging the text and shape of an issue such as RHIDP-1234 — how big is this, is this AC testable, should this be one Epic or three, does this already exist. Prose and estimation craft only; it runs no Jira command.
Opens new work in RHDH Jira and decides what kind of work it is — Feature or Feature Request in RHDHPLAN, Epic, Story, Task, Spike or Vulnerability in RHIDP, Bug in RHDHBUGS, support conversation in RHDHSUPP — then interviews, drafts, and creates it with the right fields and parent link. Use for "file a ticket", "create a feature", "open an epic for this", "raise a bug", "log a spike", "we should track this in Jira", or turning an RHDHSUPP support case into an RHDHBUGS defect or an RHDHPLAN feature request. Picking the issue type is this skill's job, not the caller's. Editing or transitioning an issue that already exists, such as RHIDP-1234, is not creation.
Guidance and workflow for planning, writing, submitting, revising, and publishing scientific manuscripts in high-impact journals. Use when Claude needs to advise on research quality, study design, manuscript structure, journal selection, peer review responses, or publication strategy.
Analyze file contents in a directory tree and intelligently rename files based on what they contain, optionally reorganizing them into a logical folder structure. Use this skill whenever the user wants to clean up messy file names, organize downloaded files, sort documents by content, rename files that have meaningless names (like IMG_20240101.jpg or document(3).pdf), or tidy up any folder where file names don't reflect their actual content. Also triggers when users mention bulk renaming, file cleanup, content-based organization, folder restructuring, collecting files by topic or purpose (e.g., "gather resume-related files", "gather dataset files", "identify disposable files"), or filtering and grouping files by category.
Steve Jobs' thinking framework and way of expressing himself. Based on deep research into 30+ primary sources, including the authorized Isaacson biography, the Stanford speech, the Lost Interview, the D Conference series, and Make Something Wonderful, it distills 6 core mental models, 8 decision heuristics and a complete expression DNA. Purpose: to serve as a conversational thinking advisor — analyzing your products, decisions and ideas from Jobs' perspective, creating intellectual friction and sparking inspiration in back-and-forth dialogue, and helping you internalize "Jobs-level" thinking as your own ability. Use when the user mentions "from Jobs' perspective", "what would Jobs think", "Jobs mode", "steve jobs perspective", "switch to Jobs", "if Jobs", "Jobs thinking", or "expression DNA". It should also trigger even if the user only says "help me think about it from Jobs' angle", "what would Jobs do", or "switch to Jobs".
Guide for managing tasks within a session using bd (beads) for subtasks and local todo lists. Use this skill when breaking down plans into issues, tracking progress, managing dependencies, or coordinating work across sessions and agents. Triggers include requests to "manage tasks", "track progress", "break down this work", or questions about bd workflow.
TC 天策创业解题 Skill is an AI business-problem-solving coach for ordinary founders, compatible with dontbesilent's DBS business toolbox. Use it when the user types "/tc", "TC", "tc" or "$tc", or needs to deal with starting a business, side hustles, self-media, personal IP, AI applications, project validation, customer acquisition and closing, delivery retrospectives, partnership trade-offs, or entrepreneurial anxiety. It turns a messy narrative into one real problem, finds the earliest link in the money-making chain that lacks evidence, and then gives one action that can immediately face real market testing. It also applies to zero-based users with no direction, resources or record of asking for help, but it only generates project hypotheses to be validated: it does not recommend high-profit projects, does not guarantee returns, and does not output vague advice.
TC startup action push. Use it when the user types "/tc-action", or already has a judgment or project hypothesis but lacks real-world evidence, has an oversized plan, keeps studying and holding meetings, needs to validate demand, or needs to push a quote toward closing. It compresses the judgment or hypothesis into a ten-minute start, a twenty-four-hour market delivery, a single seven-day metric, a cost ceiling, stop conditions and the data to bring back; it checks the current public market when tools are available and states the unknowns explicitly when they are not, and the action must involve contact with real people.
TC startup problem reframing and definition. Use it when the user types "/tc-diagnosis", or needs to find the single business bottleneck in situations such as a messy narrative, entrepreneurial anxiety, multiple directions, partnership disputes, traffic that does not convert to revenue, or a product that will not sell. It first separates facts, interpretations, emotions and hypotheses, then forms a real problem with a subject, a goal, constraints and validation criteria; once the end conditions are met it must stop asking questions and return to /tc or tc-action, and it does not treat the diagnosis itself as a result.
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.