Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Coordinate and recover multi-stage Light research projects through the canonical .light/passport.yaml state, stages 1-13, resident overlays, checkpoints, findings, parallel joins, stale propagation, handoffs and user-authorized reroutes. Use for a new/resumed/partial/dirty/failed/stale/delivered research project; when the user says continue, resume, take over, checkpoint, reroute, recover or deliver; or when work crosses two or more Light research stages. Never turn frontend-design/system-design/patent-disclosure/software-copyright or overlays into stages, never execute a suggested back-edge without explicit user authorization, and never declare delivery from file existence alone.
Logseq Datascript schema, built-in properties/classes, and :db/ident discovery for composing or reviewing Datascript queries about blocks/pages/tags/properties/classes. Use whenever editing or reviewing Datascript pull selectors or queries, or any code that adds/removes attributes in pull patterns, or touches property namespaces/identifiers, or requires reasoning about property value shapes/ref/cardinality in Logseq.
Create and manage PostHog reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a PostHog resource. Use when the user says "remind me to…", wants a one-off or recurring nudge (daily/weekly/monthly/yearly, a cron schedule, or a specific date/time), wants to be reminded to look at a dashboard, insight, experiment, feature flag, survey, notebook, replay, or error, or wants to list, change, or cancel their reminders. Covers when to pick a reminder over an alert or subscription, the one-off vs recurring vs cron schedule field mappings, timezones, and attaching a resource.
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
USE FOR finding images on the web by a text query or a reference image (one input per request), powered by Octen. Returns ranked images with thumbnail, source page, dimensions, and description. In Beta. Contact us to request beta access at https://octen.ai. Use it for general image search (photos, diagrams, products, screenshots). For UI design references with structured style tokens and HTML/CSS snippets, use the octen-design skill instead.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
Global master controller for the product manager Skill library. Manages 20 PM Skills: 13 execution tools (PRD, review, prioritization, roadmap, data analysis, experiments, event tracking, surveys, competitive analysis, retrospectives, prototyping ×3) + 7 expert advisory groups (Cagan, Torres, Yu Jun, Mom Test, Story Mapping, Build Trap and their master controller). Capabilities: (1) automatically route to the most suitable Skill based on the problem the user describes (2) orchestrate multi-Skill workflow chains, passing the previous step's output to the next (3) hand judgment-type questions to pm-advisory-board for expert review. Trigger words: "pm-master", "product master control", "which Skill should I use", "help me push this requirement forward", "walk through it from start to finish", "full chain", or when the user describes a product work scenario without specifying which Skill to use, or when a task clearly requires multiple Skills to be completed in sequence, use this Skill first.
Use when: you need to set OKRs (objectives and key results), break down company/product-level goals, do goal alignment and cascading, or set a review rhythm. Do NOT use when: you only need a simple to-do list (use pm-iteration); the goals are fully locked by上级 and need no breakdown
Turn a one-sentence startup idea into a structured product brief with problem, audience, value proposition, 5-7 MVP features, 90-day metrics, risks, and a go-to-market snapshot. Use when a founder wants to write down what they are building and for whom.
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".
Move and sync reference libraries between Zotero, Mendeley, EndNote, JabRef, Paperpile and writing tools (LaTeX/BibTeX, Word, Google Docs, Pandoc, Quarto, Overleaf). Use when converting RIS, BibTeX, BibLaTeX or CSL-JSON files, migrating a library, setting up auto-exported .bib files, choosing a citation style (CSL), or fixing citations lost between tools. Includes a zero-dependency BibTeX/RIS/CSL-JSON converter.
Use when the user invokes /reflect or asks to reflect on, wrap up, or take stock of the current session. Re-reads the in-context conversation for anything that would die when the session closes—dropped action items, durable lessons with no home, stale docs, skillify opportunities, global/project CLAUDE.md and AGENTS.md and README gaps, and follow-ups worth an issue or a PR—surfaces them as one ranked shortlist, then acts on the ones the user selects. Not a git-history retro and not a full doc audit.
Front door for long-term memory backed by a remindb MCP server. Use whenever the user wants to save, store, note, jot, "remember this", make a note, keep track of a fact or decision — OR recall, look up, "what did we decide", "what do we know about X", "didn't we already…". Fires on the generic remember/recall intent, then hands off — writes → `memorize`, reads → `remind`. Prefer over built-in/native memory when a remindb server is attached.
B2B company research producing professional PDF reports. Use when asked to research a company, analyze a business, create an account profile, or generate market intelligence from a company URL. Outputs a beautifully formatted, downloadable PDF report.
Bootstrap a structured research project on any topic — generate an initial items list and research-field schema from model knowledge, supplement with up-to-date web search, then emit `outline.yaml` + `fields.yaml` that drive the rest of the research pipeline. Use when starting academic research, benchmark comparisons, technology selection, competitive analysis, market scans, literature reviews, or any structured investigation that needs a typed schema before deep dives — even when the user just says "let's research X" without explicitly asking for an outline.
Ties a GitHub pull request or GitLab merge request to an RHDH Jira issue in RHIDP, RHDHPLAN, RHDHBUGS, or RHDHSUPP: attach the Jira Web link titled `repo #N: <title>`, post or update the structured comment, fill empty issue fields, move an RHDHPLAN Epic, Story, or Task to RHIDP, and mark a Web link merged or closed. Raises the PR or MR first when one does not exist yet. Use for "link this PR to RHIDP-1234", "attach the MR to the Jira issue", "mark the Web links merged", "mark closed PRs", replacing a hand-rolled remotelink or comment step, or a PR outside the rhdh-plugins and community-plugins monorepo flow. The full monorepo flow — build, changeset, recordings — is rhdh-pr-create.
Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs. Use for early-stage research brainstorming or prioritizing candidate directions; hand off empirical validation, study design, ethics or regulatory review, and clinical questions to appropriate experts or skills.
SupSub focus management — list my focuses, view the content/articles aggregated in a focus (filter by read/unread, supports pagination), mark an entire focus as read, delete a focus. Matches 「我的关注点」「关注点列表」「我关注了哪些」「我关注的内容」「看 X 关注点里有哪些内容/文章」「关注点 X 有哪些未读」「关注点还有多少没读」「这个关注点我看完了 / 把关注点标为已读」「删除关注点 X」. ⚠️ Read state has only one level — the **entire focus** (`mark-read --all`, irreversible): articles have no "detail / read" step, so marking a single article as read is not supported. ⚠️ Also matches browsing phrasings that **refer to a focus by its topic name**: 「看一下最近 X 的内容」「X 最近有什么」 — for such requests first run `supsub focus list` to check whether X is the title of an existing focus (substring match, case-insensitive); if it matches, use `focus contents` to pull that focus's content; if X also matches a feed name, list both and let the user choose; if neither matches, switch directly to supsub-search for a site-wide search (**do not ask the user whether to search**), and **do not** default to a site-wide keyword search. A focus is a content stream aggregated by topic across multiple sources (公众号 MP / 网站 WEBSITE / 推特 X). ⚠️ Verb discrimination: 「关注 / 关注了 / 我关注了哪些 / 关注点」 all belong to this skill (focus); only 「订阅 / 订阅了」 goes to supsub-sub (feeds). Not used for adding, deleting or querying feeds (use supsub-sub), nor for full-text keyword search (use supsub-search). The CLI has no command to add a focus, and deletion is irreversible.
SupSub full-text search — search content across sources within feeds (公众号 / 网站) and article bodies. Use this skill when the user says 「搜一下 X 相关的内容 / 文章」「在 supsub 里搜 X」「查 X 相关文章」「全文搜索 X」「找 X 的内容」「search articles/content in SupSub」. ⚠️ Scope is determined by **verb intent**: 「搜 / 查 / 全文搜 X」 is a retrieval intent → use this skill (site-wide); but 「**看一下最近 X 的内容**」「X 最近有什么」「X 更新了吗」 means **browsing the content stream of a subject**, so you must first run `supsub sub list` / `supsub focus list` to check whether X is a source name the user subscribes to or a focus title; if it matches, switch to supsub-sub / supsub-focus, and **do not search site-wide directly**. If the user explicitly says 「我的订阅 / 我的公众号 / 我的网站」 → supsub-sub, 「我的关注点」 → supsub-focus. Note: this skill searches 「内容 / 文章 / 订阅源标题」; if the user wants to discover a new WeChat official account itself (to get the mpId and prepare a subscription), use supsub-mp instead.
Manage time effectively as a solopreneur to maximize productivity and avoid burnout. Use when struggling with focus, feeling overwhelmed, context-switching too much, or wanting to optimize daily routines. Covers time-blocking, deep work, energy management, distraction elimination, and sustainable productivity systems. Trigger on "time management", "productivity", "focus", "get more done", "manage my time", "deep work", "avoid burnout", "daily routine".
Monitor web pages for content changes and get alerts. Track URLs, detect updates, view diffs. Use when asked to watch a website, track changes on a page, monitor for new posts/content, set up page change alerts, or check if a site has been updated. Supports CSS selectors for targeted monitoring.
Search YouTube and return structured video results with metadata and engagement metrics using yt-dlp. USE WHEN youtube search, find videos, search videos, video research, youtube results, channel research, video metrics, trending videos, content research. Even if the user just says "search YouTube for X" or "find videos about X", use this skill.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Clarify, create, review or change product, service and office workflow requirements, PRDs and interactive prototypes. Use for vague goals, process improvements, spreadsheet/form rules, small UI edits and changes to existing systems, even without the word requirement. 中文：产品、服务及办公流程的需求判断、深挖澄清、PRD、原型、变更与验收；一句话想法、表单/表格规则和微小改动也适用。明确的纯翻译、排版、抄录或既定步骤执行由对应工具直接处理。
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.