Results for “reading”

Evidence-grounded AI research workflow for turning supplied economics, finance, management, and social-science papers or structured records into versioned PaperReading artifacts. Use when Codex must ingest text, Markdown, or a text-based PDF; separate source-grounded claims from researcher analysis; bind findings to evidence IDs and locators; review extraction candidates; migrate v0.2 PaperRecord JSON; validate or verify a v0.3 PaperPackage; generate research extensions; export reviewable JSON or Markdown; or safely update a compatible 13-field literature workbook.

The English summary is being prepared. Showing the original description.

Read and understand PDF documents with the pdf_* tools - inspect a document before reading it, extract text in reading order or as reconstructed layout, search a document without reading all of it, recognize scanned pages that have no text layer, and render pages as pictures. Covers scanned documents, chat attachments, page-range and character caps, and the read-only and untrusted-content rules.

The English summary is being prepared. Showing the original description.

Build full-paper Chinese-English side-by-side, figure/table-aware, source-grounded Markdown readers for journal or conference papers from PDF, DOI, arXiv, publisher HTML, or pasted text. Use whenever the user asks to translate or read a paper, make 中英文对照/原文对照/全文翻译解读, extract figures or tables into the right positions, preserve figure/table placement near relevant prose, or keep exact source anchors for every block. This skill must not degrade into a summary-only output unless the user explicitly asks for a summary. Also trigger on general paper-reading and translation requests even without the word "Nature", such as reading/translating an academic paper, literature reading, understanding a paper, and Chinese phrasings like 读论文、精读论文、论文翻译、文献翻译、文献阅读、学术阅读、帮我读这篇文章、翻译这篇paper.

The English summary is being prepared. Showing the original description.

Turn text into speech with ElevenLabs using the sag command line tool. Choose a voice, adjust pronunciation and delivery, play audio locally, or save a file to send as a spoken response.

• Reading text aloud on your computer
• Saving spoken replies as audio files
• Choosing and checking a reading voice

Manage Google Workspace tasks through a command-line tool. Search and send Gmail messages, manage Calendar events, find Drive files, list contacts, update Sheets data, and read or export Docs.

• Searching recent emails and drafting replies
• Creating or updating calendar events
• Finding files and listing contacts

Investigate a question using official documentation, source code, specifications, and first-party APIs. A background agent records the findings in one Markdown file with sources for each claim, following the repository’s existing conventions for research notes.

• Verify API behavior against official sources
• Save research findings with citations
• Delegate reading while continuing other work

Simulate readers encountering a draft for the first time to see whether they open it, where their attention fades, and what they remember. Receive reader comments alongside the text without rewrites or suggested fixes.

• Check whether a post earns a full read
• Find where readers lose interest
• Compare reader reactions after revisions

Handle tasks managed by Paperclip by reading their context, saving documents and deliverable files, updating progress and blockers, and coordinating delegated work. The skill provides procedures for short agent runs, approvals, and traceable task updates.

• Resuming assigned work with its latest task context
• Delivering documents and downloadable files on a task
• Recording completion, dependencies, or pending questions

Summarize the past 24 hours of Gmail activity into items needing action, items worth attention, and informational updates. Orbit presents the daily digest as an opened email in a Gmail-style reading view using an authenticated Gmail connection.

• Reviewing the past 24 hours of Gmail activity
• Checking messages that need action
• Separating noteworthy updates from informational mail

Explore code through structural search: find functions and classes, view file outlines, and open only the implementations you need. It uses tree-sitter, a parser that identifies code structure, to limit how much source text is loaded.

• Finding functions related to a feature
• Navigating the structure of a large source file
• Reading only a specific function's implementation

Write a single-line commit message for Ant Design by reading staged changes, the changes selected for the next commit. It summarizes the full commit intent and follows the style of recent repository commits.

• Write a message for staged changes
• Match the style of recent commits
• Summarize changes across multiple files in one line

Set up radar sensing for contactless heart rate, breathing rate, presence, and distance measurements. It covers supported hardware, firmware, and combining radar with WiFi CSI, sensing data derived from wireless signals, for shared readings and 3D views.

• Setting up contactless heart rate and breathing measurements
• Detecting presence and approximate distance in a defined zone
• Combining radar and WiFi CSI readings

Detect and classify unusual readings from Cognitum Seed devices, including spikes, flatlines, and drift. Review anomaly scores, recommend quarantine for scores above 0.9, and save detected patterns for future reference.

• Investigating unusual device readings
• Checking health before advancing a firmware canary
• Triaging health alerts across a device fleet

Review whether pages remain understandable and usable without CSS. Check reading order, headings, form labels, instructions, and errors, then suggest HTML changes that preserve meaning when styles fail or users apply their own.

• Check page usability with CSS disabled
• Review reading order and heading structure
• Inspect form labels, instructions, and errors

Guide browser work inside the Claude desktop app, including reading page text, opening tabs, and handling existing sign-ins. Covers site approvals, browser visibility, and connection problems when a cloud session uses the desktop browser.

• Read web page text in the Claude desktop app
• Open a page in an additional browser tab
• Guide a user through sign-in or verification

Resume unfinished Codex work in Muse Code by reading a local session log selected by the user. Recover the latest request, decisions, and pending changes, then check current files and continue the task.

• Continue unfinished Codex work in Muse Code
• Resume work from a session ID or log path
• Recover prior decisions before continuing a task

Read Slack conversations and thread replies, decide when a response is needed, and send messages, files, or reactions. Keep updates and results in the original conversation, with support for direct messages sent on the user's behalf.

• Reading a thread before replying
• Sharing work updates and files in the original conversation
• Sending a direct message on the user's behalf

Plan and review systems where several AI agents work together. Assess whether multiple agents are useful, choose roles and communication methods, and define shared files, verification, and resource limits to address conflicts, spreading errors, and uncontrolled execution.

• Deciding between one agent and several agents
• Designing agent roles and communication
• Reviewing shared files and context boundaries

Work with large scientific arrays by storing data in smaller blocks and reading selected portions. Guides compression, cloud storage, format migration, and NumPy, Dask, or Xarray integration while preserving dimensions, units, and other metadata.

• Reading selected regions of large scientific arrays
• Choosing data blocks and compression settings
• Working with scientific arrays stored on S3 or GCS

Create an editable, single-slide PowerPoint research poster from author-approved local text and images. Check physical dimensions, image resolution, contrast, reading order, and file security, with reports to support manual review and printing.

• Create an editable PowerPoint conference poster
• Check print dimensions and image resolution
• Review contrast, reading order, and alternative text

Implement Azure Cosmos DB document operations in Rust using its NoSQL SDK. The skill covers authentication, database and container clients, creating and reading records, replacing or patching fields, and deleting items with partition keys.

• Connecting a Rust application to Azure Cosmos DB
• Creating and reading documents
• Replacing documents or patching selected fields

Create or repair a JSON specification for an editable PowerPoint deck. Define exact object positions, sizes, styles, and layering, alongside reading order and image descriptions, so the build process follows an explicitly authored layout.

• Specifying exact positions for PowerPoint slide objects
• Repairing margins, gaps, and overlaps in a slide specification
• Keeping labels and values editable as native objects

Forecast sales, demand, or sensor readings with Google's pretrained TimesFM model, without custom training. Check hardware and dataset memory needs, include external factors such as prices or holidays, and obtain forecasts with uncertainty ranges.

• Forecasting future sales or demand from CSV data
• Including prices and holidays in sales forecasts
• Forecasting multiple stores' time series in batches

Set up Curviate CLI, authenticate your machine, connect a LinkedIn account, and verify access by reading your profile live and from stored data. The guide also explains diagnostic results and common credential or account setup failures.

• Installing and authenticating Curviate for the first time
• Investigating credential or account errors with curviate doctor
• Connecting LinkedIn and selecting the default account