Loading...
Loading...
Found 345 Skills
Use xurl to access AI agent conversations via agents:// URIs. Invoke when the user: gives an agents:// URI, a provider shorthand like provider/..., or a bare thread/session ID; mentions conversations, threads, or sessions from any AI coding agent; wants to search, read, summarize, compare, or continue agent threads; asks what they worked on, what an agent said, or references past agent interactions; wants to delegate work to or start a conversation in another agent.
Summarize bundle components from agent-bundle.json and repo skill/agent counts. Use when packaging or auditing distributable bundles. NOT for live plugin installs.
Parse, navigate, and query materials science ontology structures — browse class hierarchies, inspect individual classes and their properties, look up object and data property definitions with domain/range, search for ontology terms by keyword, and parse or summarize raw OWL/XML files. Currently supports CMSO and ASMO; the broader OCDO ecosystem (CDCO, PODO, PLDO, LDO) is planned. Use when exploring what classes or properties an ontology provides, finding the right CMSO term for a crystal structure or simulation concept, understanding parent-child class relationships, or onboarding to an unfamiliar materials ontology, even if the user only says "what ontology terms describe my FCC copper simulation" or "show me the CMSO class hierarchy."
Read, search, summarize, and triage AgentMail inboxes through the connected MCP server. Use for ANY request to look at, search, or process mail — even a simple 'search my inbox for X' or 'any new mail?'; the read workflow applies regardless of task size. Also use to summarize conversations, inspect attachments, manage read/unread labels, or find messages needing a reply; do not use for sending or drafting (agentmail-send-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports. Three depth modes user picks per invocation — transcript (just words, fast/free), visual (transcript + ffmpeg frame extraction + Claude vision pass on key moments), multimodal (Gemini native video ingestion if $GEMINI_API_KEY set, else dense Claude vision). Uses MLX-Whisper local on Mac for transcription, falls back to platform-provided transcripts when available (Loom, Riverside, YouTube auto-subs). Saves to ~/Documents/videos/<source>-<slug>-<date>/ and optionally captures summary to second-brain raw/ as call-/meeting-/note-. Triggers on "/watch-video <url>," "watch this video," "transcribe this loom," "analyze this video," "summarize this recording," "key moments from this," "what happened in this video." This skill replaces and broadens the prior youtube-transcript skill.
When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to capture to second-brain raw/ as a highlights- file. Four modes — notes (default, chapter-by-chapter), summary (whole-book TL;DR + 3–5 takeaways), quotes (pull-quote highlights only), study (notes + Q&A spaced-rep prep). Triggers on "/read-book," "read this book," "extract notes from this PDF," "what's in this book," "summarize this ebook," "pull quotes from this." Sibling to watch-video (same content-consumption pattern, different medium).
Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by cross-referencing autocapture events on the same page, and can create a saved heatmap the user opens in PostHog, then summarizes the behavior and proposes improvements. TRIGGER when: user asks what a heatmap shows, why people aren't clicking something, where users rage-click, how far they scroll, what to change on a page based on heatmap/click data, or to 'analyze/assess/review the heatmap' for a URL. DO NOT TRIGGER when: the user only wants to create a saved heatmap screenshot with no analysis (use heatmaps-saved-create directly), or is asking about session replay in general (use investigating-replay).
Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that selects sessions, and — crucially — estimating observation volume and checking the org's monthly quota before creating, so a broad scanner doesn't exhaust the budget on its first scheduled sweep. TRIGGER when: user asks to create, set up, or configure a Replay Vision scanner, OR when you are about to call vision-scanners-create, OR when widening an existing scanner's query or sampling_rate via vision-scanners-update. DO NOT TRIGGER when: only reading scanners or observations, deleting a scanner, or running an existing scanner against a single session on demand (vision-scanners-scan-session).
Generate long HTML articles for human reading — organize existing materials, experiences, and data clearly before writing. Each time it is triggered, first use AskUserQuestion to clarify 4 key parameters in one go: [Who is it for / What will readers gain after reading / Depth level / Style + Focus], then output according to the 6-stage framework. **The only output format is HTML** — this skill should not be used if the user requests markdown or direct chat responses. It is triggered when the user says phrases like "do a retrospective", "summarize this", "compile into HTML", "create a tutorial/study guide", "explain X clearly", etc., which require structured reading content of over 500 words. It is not applicable for: project plan reports/framework plans/version roadmaps (use issue-pool, which has built-in md2html), PRDs/requirements documents/test cases (use prd-test-writer), interface design drafts (use design-exploration), naming (use product-naming), writing code/fixing bugs/modifying files, or questions that can be answered in one or two sentences.
Full Lifecycle Management of Issue Pool (Development Paradigm v1 Planning Phase). The core is an issue-driven process: users throw in ideas casually, and you turn vague issues into actionable tasks—what you deliver is "problem definition", not "solution implementation"; the carrier is a single markdown file named ISSUES.md at the root of the repository, without introducing kanban or new formats. Five actions: Record (add original content to the pool + relevance check), Merge (merge homogeneous requirements), Break Down (discuss and decompose, guide users to reveal the real needs behind the proposed solutions), Transfer (deliver outputs), Pending (if the issue is still vague after two rounds of discussion, record the bottlenecks and put it back into the pool, and avoid making fake plans to wrap up). The only criterion for judging during Transfer is "whether it can be delivered in one version": If yes → simple task, write a paragraph plus 3~5 acceptance criteria under the pool entry; If no → complex plan, place it in docs/plan/ and write the framework plan content following the seven steps in references/plan-writing.md (explain "why to do it / what constitutes completion / what steps to take", without involving fields or interfaces), the end must remain vague, and break down the next batch only after delivering one batch. When users say "record an issue", "add/summarize issues", "break down an issue / decompose"
Multi-perspective in-depth analysis. Use multiple Sub-agents to act as consultants with different thinking frameworks, conduct independent analysis on the same material, then cross-summarize consensus and differences, and produce a structured diagnostic report. Triggered when the user says "Help me with multi-perspective analysis", "Multi-dimensional analysis", "Look at it from multiple perspectives", or "Help me diagnose it".
Eva Review 2.2.8 Post-Publication Review Entry for All Platforms. It is used to review published content such as short videos, Xiaohongshu graphics and texts, WeChat Official Accounts, etc. It reads backend screenshots, Excel, CSV, Markdown tables or multiple historical records to decide what to test as priority for the next piece of content, and continuously maintains the account review record library of the current project after the user's first authorization. Triggers: /eva-review, Eva Review, Review this published content, Check where this content might get stuck after publication, Backfill last result, Review recent content, Summarize rules of recent content, What do I talk about that performs better. Pre-publication review, direct creation of new content, and platform metaphysical issues without publication objects are not covered by this Skill.