查找技能

Extract and verify text, numbers, objects, and sequences from images, documents, and video. Record where each finding appears, check exact labels and values, and build answers whose supporting evidence can be traced back to the input.

中文简介正在准备中。当前显示英语简介。

• Extracting and checking numbers in documents
• Tracing video events to timestamps
• Reading and verifying labels in images

Build features or fix bugs by writing a small test first, checking that it fails for the expected reason, and making the smallest code change needed. Run related tests and review the changes for unintended effects.

中文简介正在准备中。当前显示英语简介。

• Reproducing a bug with a regression test
• Defining expected behavior before implementing a feature
• Checking parser, routing, or UI behavior changes

Coordinate meetings across participants and time zones by checking availability and travel buffers, proposing suitable times, and creating or updating authorized events. Read back calendar details before preparing participant notification drafts.

中文简介正在准备中。当前显示英语简介。

• Finding meeting times across several participants
• Coordinating schedules across time zones
• Updating the details of an existing meeting

Use Claude Code to manage Odysseus tasks, email, calendar events, stored facts, and documents through a permission-scoped API. You can also start, inspect logs for, and stop Cookbook model servers using the access granted by your token.

中文简介正在准备中。当前显示英语简介。

• Creating a task with a timed reminder
• Reading email and preparing a reply draft
• Saving calendar events, preferences, and documents

Use Codex to manage Odysseus todos, calendars, memory, and documents, and read or draft email. Through its permission-scoped API, the skill also supports reminders and launching, inspecting, or stopping Cookbook model servers.

中文简介正在准备中。当前显示英语简介。

• Create a timed reminder as a todo
• Check calendar events and add appointments
• Read email and prepare an editable reply draft

Review support requests, rank urgency by impact and timing, and identify the responsible internal team. Record evidence, next actions, and response deadlines, then prepare customer reply drafts and an escalation summary organized by urgency.

中文简介正在准备中。当前显示英语简介。

• Prioritizing a backlog of support requests
• Identifying owners and next actions for urgent incidents
• Preparing customer reply drafts for review

Turn scattered messages, meeting notes, and documents into sourced action lists and status briefs. The skill reconciles updates, separates facts from tentative inferences, and highlights decisions, dependencies, risks, and unanswered questions.

中文简介正在准备中。当前显示英语简介。

• Build a sourced action list from meeting notes
• Combine messages and documents into a status brief
• Assess feasibility using dependencies and blockers

Find the smallest set of tools suited to a task, check their required inputs and effects, and inspect the results. Use a small read-only check when the environment or target is uncertain.

中文简介正在准备中。当前显示英语简介。

• Choosing suitable tools from a large collection
• Checking required inputs before a tool call
• Investigating failures caused by incorrect parameters

Find official documentation for a library, framework, or API and apply it to the task at hand. Check the relevant version, distinguish documented facts from assumptions, and verify code changes with a focused test or concrete command.

中文简介正在准备中。当前显示英语简介。

• Checking how an API or option works
• Implementing behavior for a specific version
• Applying official guidance to an existing project

Prepare reviewable updates for clients, partners, or leadership from internal messages and documents. The skill checks current figures, dates, and commitments, flags unresolved discrepancies, and excludes private internal details from the draft.

中文简介正在准备中。当前显示英语简介。

• Draft a client progress update from internal records
• Check corrected figures before preparing a partner update
• Prepare a leadership brief with uncertainties flagged

Diagnose failed, timed-out, or incomplete terminal commands using command output and environment checks. The skill guides targeted retries, avoids duplicate long-running jobs, and verifies that the intended files, processes, or service state were produced.

中文简介正在准备中。当前显示英语简介。

• Diagnose a command failure from its error output
• Investigate missing dependencies or incorrect paths
• Check a long-running command after a timeout

Create a complete first version of a requested file or other deliverable early, then refine it and check its format, required content, location, and usability before reporting the work as finished.

中文简介正在准备中。当前显示英语简介。

• Creating a report with all required sections
• Saving a deliverable in a specified location
• Checking that a generated file opens correctly

Update app data, files, or service records by confirming the target, changing only what was requested, and reading the result back. Check that unrelated values remain intact and that external actions have an observable outcome.

中文简介正在准备中。当前显示英语简介。

• Updating selected fields in an app record
• Checking the outcome of a file move or deletion
• Verifying the status of a send or scheduling action

Research current public information by checking original sources, recording relevant passages, dates, and URLs, and using browser interaction when needed. Cross-check important claims and clearly separate supported facts from inference.

中文简介正在准备中。当前显示英语简介。

• Checking current information against official sources
• Comparing evidence across multiple web pages
• Researching pages that require browser interaction

Use when the user asks Claude Code to read or write Odysseus data (todos, email, calendar, memory, documents) or to launch/monitor/stop a Cookbook model-serve task through the scoped Claude Agent API. Requires ODYSSEUS_URL and ODYSSEUS_API_TOKEN.

中文简介正在准备中。当前显示原文说明。

Use when the user asks Codex to read or write Odysseus data (todos, email, calendar, memory, documents) or to launch/monitor/stop a Cookbook model-serve task through the scoped Codex Agent API. Requires ODYSSEUS_URL and ODYSSEUS_API_TOKEN.

中文简介正在准备中。当前显示原文说明。