“init”的搜索结果

Set up language servers for GitHub Copilot CLI to enable definition lookup, reference search, hover details, and type information. Detects the operating system, installs the appropriate server, and merges user or repository configuration while preserving existing entries.

中文简介正在准备中。当前显示英语简介。

• Enabling definition lookup and reference search in Copilot CLI
• Adding language support to an existing configuration
• Creating shared language server settings for a repository

Create a Kotlin Spring Boot project with database connections, API documentation, and local services managed through Docker Compose. Set up dependencies and configuration files, then run Gradle tests to check the initial project.

中文简介正在准备中。当前显示英语简介。

• Starting a Kotlin Spring Boot project
• Setting up local Redis, PostgreSQL, and MongoDB services
• Adding API documentation and architecture test dependencies

Set up a new Google Tasks list and populate it with initial tasks. Add task titles, supporting notes, and due dates where needed, then list the tasks to review what was registered.

中文简介正在准备中。当前显示英语简介。

• Create a task list for quarterly goals
• Add a task with notes and a due date
• Register several initial tasks

Create an expense tracker in Google Sheets with columns for date, category, description, and amount. Add an initial expense entry, then give a manager read-only access to the spreadsheet.

中文简介正在准备中。当前显示英语简介。

• Creating a new expense tracking spreadsheet
• Adding column headers and an initial expense entry
• Sharing expense records with a manager for viewing

Start NanoClaw’s initial setup by directing the user to its terminal script. The script handles dependencies, the container image, credentials, the service, the first agent, and optional channel connections, with Claude-assisted recovery if an error interrupts setup.

中文简介正在准备中。当前显示英语简介。

• Install NanoClaw for the first time
• Set up credentials, the service, and the first agent
• Connect an optional channel during initial setup

Build repeatable business reports from connected data sources or uploaded CSV and XLSX files. Define metrics and comparisons, check the calculations, deliver a concise summary and Excel workbook, and save the report definition for future or scheduled runs.

中文简介正在准备中。当前显示英语简介。

• Comparing sales by location with last year
• Reviewing overdue receivables by age
• Tracking labor costs as a percentage of revenue

Create or update a product roadmap, compare priorities, and adjust timelines. Organize initiatives by timeframe or goals, show owners and dependencies, and summarize what changed alongside risks and team capacity limits.

中文简介正在准备中。当前显示英语简介。

• Adding an initiative and deciding what to postpone
• Reprioritizing after customer feedback
• Assessing the impact of a dependency delay

Define a product’s target customers and distinctive value, then turn that positioning into market-entry plans, competitor comparison guides, launch plans, and sales materials. Includes workflows for customer validation and adapting messaging for international markets.

中文简介正在准备中。当前显示英语简介。

• Defining target customers and product value
• Preparing competitor comparison guides for sales
• Planning product launches and market entry

Define service reliability targets, choose measurements that reflect user experience, and calculate error budgets—the failures a target allows. Generate alert thresholds and review existing definitions for unrealistic targets, unclear metrics, and missing response policies.

中文简介正在准备中。当前显示英语简介。

• Defining reliability targets for a new service
• Calculating allowed downtime and alert thresholds
• Reviewing existing reliability definitions

Rewrite a feature-based roadmap around the changes customers and the business should experience. The result pairs each initiative with an outcome statement, success metrics, sequencing notes, and context connecting the plan to company strategy.

中文简介正在准备中。当前显示英语简介。

• Turning a feature list into measurable outcomes
• Connecting roadmap initiatives to company strategy
• Defining success metrics for planned work

Review skill and agent definitions for structural issues and whether their instructions meet expected behavior. Four modes cover structure, test specifications, category criteria, and coverage reports that reveal missing specifications or checks.

中文简介正在准备中。当前显示英语简介。

• Check one skill or all skills for structural issues
• Compare skill or agent instructions with a test specification
• Review definitions against category criteria

Manage shared iii configuration with JSON Schema, a definition of allowed value structures. Covers validated settings, automatic change notifications, YAML edits, temporary overrides, and default initialization that preserves existing values.

中文简介正在准备中。当前显示英语简介。

• Sharing validated settings between workers
• Reacting to manual YAML configuration edits
• Initializing defaults while preserving existing values

Define the structure and available components for AI-generated JSON screens or videos. Build generation prompts, process incremental updates, connect values to application state, and validate or repair definitions before passing them to a renderer.

中文简介正在准备中。当前显示英语简介。

• Define allowed components for AI-generated screens
• Build prompts for generating or editing JSON definitions
• Assemble definitions from streamed AI responses

Add PyTorch FSDP2 to training scripts so model state can be split across GPUs. Covers distributed initialization, mixed precision, CPU offloading, and checkpoint saving and loading for models that exceed a single GPU's memory.

中文简介正在准备中。当前显示英语简介。

• Training a model that exceeds one GPU's memory
• Adding FSDP2 to an existing training script
• Configuring mixed precision and CPU offloading

Turn business goals and customer problems into a product roadmap. Define initiatives, rank priorities, check dependencies and team capacity, and organize releases with clear reasons stakeholders can review and discuss.

中文简介正在准备中。当前显示英语简介。

• Planning a quarterly or six-month product roadmap
• Prioritizing competing initiatives across teams
• Explaining roadmap choices to executives

Build initial research reports on publicly traded companies, connecting an investment thesis with forecasts, valuation, and risks. Organize supporting sources, distinguish evidence from assumptions, and identify missing information and questions requiring further research.

中文简介正在准备中。当前显示英语简介。

• Start research coverage of a publicly traded company
• Organize an investment thesis and evidence that could disprove it
• Plan forecasts and valuation analysis

Create and maintain a reusable skill that records metric definitions, trusted data sources, and analytical caveats. Preserve supporting evidence and unresolved conflicts so future Data Analytics work can consult and cite the same documented context.

中文简介正在准备中。当前显示英语简介。

• Save shared metric definitions for future analyses
• Document trusted sources and conflicting definitions
• Update or repair an existing semantic layer

Audit custom subagents, the specialized assistants used by Claude Code and Codex. Check whether definitions load, identify overlapping roles, review model choices and tool access, and receive scores with prioritized fixes and optional confirmed edits.

中文简介正在准备中。当前显示英语简介。

• Checking agents when joining a project
• Reviewing newly added or imported agents
• Investigating delegation to the wrong agent

Install or update BMad-Method (V6) in a project after checking existing installations. The skill also fixes a known output-folder issue, updates Git ignore rules, and provides next steps for using the installed workflows.

中文简介正在准备中。当前显示英语简介。

• Set up BMad-Method (V6) for Claude Code
• Run a quick update on an existing V6 installation
• Check for an older V4 installation before setup

Organize project architecture, conventions, and module details into root and module-level CLAUDE.md files. Add a structure diagram and navigation links, track scanning coverage, and update existing documentation incrementally when the skill runs again.

中文简介正在准备中。当前显示英语简介。

• Preparing project context for an AI agent
• Documenting a repository with multiple modules
• Updating existing CLAUDE.md files

Set up or update BMad-Method V6 in a project, detect older installations, fix a known output folder issue, and adjust Git ignore rules, with guidance on what to do next.

中文简介正在准备中。当前显示英语简介。

• Installing BMad-Method V6 in a project
• Updating an existing V6 installation
• Checking for an older V4 installation

Locate function and class definitions, usages, and relevant files with ripgrep, using text patterns and file filters. Search Git history to see when text appeared or disappeared and investigate who changed specific lines.

中文简介正在准备中。当前显示英语简介。

• Finding function or class definitions
• Locating usages of a particular function
• Narrowing searches by file type or path

Set up an AI agent team by proposing roles and names for a project, then creating shared team files after confirmation. Initialize member context, decision records, and logs so the team starts with a common project background.

中文简介正在准备中。当前显示英语简介。

• Set up an AI team for a new project
• Review team roles before creating files
• Give agents shared project context

Read when the user asks what OpenKnowledge is, wants to install it on a repository, wants to open or preview a single markdown file that is not part of an OpenKnowledge project, wants to share an OpenKnowledge project with collaborators, asks whether OpenKnowledge supports a particular capability, or asks how `ok init` / `ok cowork` / OK Desktop set up a project. Do NOT load to perform OpenKnowledge reads/writes — the runtime guidance for editing markdown inside an initialized OK project ships as a separate project-local skill installed into each detected agent's skills dir (for example `.claude/skills/open-knowledge/`) whenever `ok init` runs.

中文简介正在准备中。当前显示原文说明。