“fork”的搜索结果

Create, list, read, message, wait on, fork, rename, archive, and pin Codex threads (sidebar tasks), plus automations and app navigation, using the app-native codex_app tools. Use when the session uses a custom (non-OpenAI) model, for example deepseek-v4-flash or mimo-v2.5, and the user asks to create a thread or a new task or agent, list or read threads, send a message to a thread, wait for a thread, fork or rename a thread, archive or pin a thread, set up an automation or reminder, or open something in the Codex app.

中文简介正在准备中。当前显示原文说明。

Prepare a project for open sourcing: a sanitized fork with secrets and internal references stripped, a sanitizer verdict, README and LICENSE, then a new PRIVATE GitHub repo created and pushed only after GO. The playbook never makes the repo public. Use for "open source this project", "make a sanitized fork", "prepare a public release".

中文简介正在准备中。当前显示原文说明。

When the user requests to create or customize an academic personal website from a GitHub template repository. This skill handles the complete workflow of forking academic template repositories (like academicpages.github.io), extracting structured personal information from memory or provided data, and systematically updating configuration files (_config.yml), navigation menus (_data/navigation.yml), content pages (_pages/about.md), and publication listings (_publications/). It specifically handles academic profiles including personal details, education background, research experience, publications, skills, and contact information. Triggers include requests to 'fork and customize academic homepage', 'build personal academic website', 'create research portfolio', or 'set up GitHub pages with academic template'.

中文简介正在准备中。当前显示原文说明。

创建新技能前，搜索本地环境、市场、GitHub和网页中的现有候选，检查用途匹配度与安全性，帮助判断直接复用、扩展还是重新创建。

• 寻找适合任务的技能
• 创建新技能前检查是否重复
• 选择可扩展的现有技能

查找Storybook指定分支的试验版软件包，必要时执行发布流程，跟踪发布状态，并提供用于新建项目或更新现有项目的命令。

• 查找指定分支的试验版
• 发布来自派生仓库的拉取请求试验版
• 确认发布状态与安装命令

Create a fixed JSON evaluation suite from a repository's existing tests and check its structure for errors. Use the suite with harness-evolve to compare variants against consistent tasks, independently of the repository's normal test command.

中文简介正在准备中。当前显示英语简介。

• Create a fixed evaluation suite from existing tests
• Check evaluation suite structure in CI
• Compare variants across commits using consistent tasks

在原URL或指定的新URL上重放已记录的浏览器操作，用于界面回归测试和复现故障。操作目标找不到时会搜索相似候选并重试，记录成功步骤的比例和判定结果。

• 部署后检查界面操作流程
• 复现已记录的故障
• 重复相同操作以比较截图

Reproduce and fix LazyCodex or Codex defects in a temporary workspace. Verify the change with regression tests and real usage, then deliver an upstream Codex pull request or a LazyCodex issue containing the tested patch.

中文简介正在准备中。当前显示英语简介。

• Implement and verify a reproducible bug fix
• Submit an upstream Codex pull request
• Deliver a tested LazyCodex patch in an issue

Turn a broad coding request into a concrete work plan grounded in the codebase. After user approval, it documents affected files, decisions, dependencies, and verification steps so a separate worker can carry out the implementation.

中文简介正在准备中。当前显示英语简介。

• Planning a large feature before coding
• Turning a vague request into defined tasks
• Preparing an implementation handoff

Take a pull request through repeated code review and fixes, verify that automated checks pass for the latest commit, and combine its changes into one commit when merging. Conflicts with the request’s goal require confirmation.

中文简介正在准备中。当前显示英语简介。

• Reviewing, fixing, and merging a pull request
• Resolving every review finding, including minor issues
• Checking CI results for the commit being merged

Use natural-language requests with Aomi CLI to check crypto prices and balances or prepare swaps, staking, and transfers between chains. Review queued transactions and simulate multi-step batches before separately authorizing wallet signing.

中文简介正在准备中。当前显示英语简介。

• Check crypto prices and wallet balances
• Prepare and simulate a Uniswap swap
• Prepare an ETH stake with Lido

Build Solidity contract tests with Hardhat and Foundry. Check individual functions, contract interactions, gas usage, and varied inputs, and use a local copy of mainnet state to test against existing contracts.

中文简介正在准备中。当前显示英语简介。

• Testing token transfers and expected failures
• Checking edge cases with varied generated inputs
• Testing interactions with existing mainnet contracts

Set up OpenMAIC and generate interactive classrooms with multiple AI agents. The skill guides hosted or local use, model configuration, and classroom generation, and also supports customizing the product or building with its SDK, a set of development tools.

中文简介正在准备中。当前显示英语简介。

• Trying classroom generation with the Live Demo
• Setting up and checking a local installation
• Generating a classroom from requirements and materials

Guides large language model reinforcement learning with miles, covering environment setup, low-precision training, consistency between training and inference, and speculative decoding, where a smaller model proposes tokens for a larger model to verify.

中文简介正在准备中。当前显示英语简介。

• Configure reinforcement learning for large MoE models
• Investigate instability in FP8 training
• Set up speculative decoding for faster rollout generation

Update a customized NanoClaw installation with official changes. The skill stages and tests updates in a separate workspace, manages required migrations, restarts the detected service, and restores saved local state if the build or health checks fail.

中文简介正在准备中。当前显示英语简介。

• Apply routine official updates to a customized installation
• Review and resolve conflicts before changing the live installation
• Apply selected upstream commits

Upgrade a customized NanoClaw installation by recording changes in a reusable migration guide and reapplying them to a clean upstream version. The workflow includes backups, validation in a separate working directory, and rollback instructions.

中文简介正在准备中。当前显示英语简介。

• Upgrade NanoClaw while preserving custom settings and code
• Document customizations in a reusable migration guide
• Validate an upgrade in a separate working directory

Route enterprise research questions to specialized skills for clinical studies, R&D finance, market research, or user research. Receive a concise digest of findings, next actions, output files, and assumptions that need human review.

中文简介正在准备中。当前显示英语简介。

• Plan a clinical study and sample size
• Review R&D budgets and spending classifications
• Estimate market size and design surveys

Coordinate project delivery by routing requests to eight specialist skills or running a verified delivery workflow. Use live Jira data for progress analysis and completion forecasts, with recorded evidence and checks before tasks are closed.

中文简介正在准备中。当前显示英语简介。

• Analyze sprint progress and forecast completion ranges
• Produce project health reports from live Jira data
• Route Jira permission and configuration reviews

Route product questions to a specialist for prioritization, research, analytics, experiments, or implementation. Support recurring discovery by tracking interviews and assumption tests, checking how customer needs connect to proposed solutions, and returning results with a concise digest.

中文简介正在准备中。当前显示英语简介。

• Prioritizing features with an explicit framework
• Planning product experiments and sample sizes
• Tracking weekly interviews and assumption tests

Turn long Markdown files into a single HTML file for reading, reviewing code, or presenting slides. Routes each input to a specialized converter and applies shared design settings, with navigation and interaction suited to the document type.

中文简介正在准备中。当前显示英语简介。

• Converting long specifications or reports into navigable HTML
• Presenting code reviews with diffs and severity annotations
• Turning Markdown into slides with keyboard navigation

Route pricing, discount, partnership, sales channel, proposal response, and bookings forecast questions to one of seven specialist skills. Receive a concise digest of findings, recommended actions, and output files to support commercial decisions and human approval.

中文简介正在准备中。当前显示英语简介。

• Review pricing models and product packages
• Assess deal discounts and approval requirements
• Compare partnership terms and channel profitability

Plan a Claude Managed Agent around one clear job, then route work through setup, launch preparation, evaluation, and scheduling. Produce execution plans and curl commands that users run with their own Anthropic API key.

中文简介正在准备中。当前显示英语简介。

• Defining one clear job for a managed agent
• Preparing launch commands for an Anthropic account
• Planning evaluation and revision with an iteration limit

Evaluate existing SaaS providers and vendors using industry-weighted scores, contractual service targets, and four areas of third-party risk. Produce scorecards, service compliance reports, and risk matrices to support renewal reviews and identify potential service credit claims.

中文简介正在准备中。当前显示英语简介。

• Preparing quarterly vendor scorecards
• Reviewing service target breaches and potential credit claims
• Classifying risks across a SaaS portfolio

Route internal operations questions to six specialist skills covering workflows, vendors, staffing capacity, communications, procedures, and procurement. Receive a brief summary of findings, recommended actions, and links to the documents or data files produced.

中文简介正在准备中。当前显示英语简介。

• Finding bottlenecks in internal workflows
• Reviewing vendor performance and purchasing costs
• Planning staffing capacity for the next quarter