开发技能

Draft or refresh Omnigent release notes for a specific version and commit range. Review merged pull requests, verify user-facing highlights and contributor credits, and deliver unpublished notes alongside a complete changelog preview.

中文简介正在准备中。当前显示英语简介。

• Draft release notes before a version tag exists
• Refresh a reviewed draft while preserving editorial changes
• Review breaking changes and upgrade guidance

Split debugging, audits, searches, and code questions into read-only tasks for sub-agents. Combine their structured reports into an evidence-based answer, requesting follow-up investigations when findings conflict or leave important gaps.

中文简介正在准备中。当前显示英语简介。

• Investigating a bug without changing code
• Understanding repository structure and design
• Comparing architectures from multiple perspectives

Investigate a bug's root cause, implement a focused repair, and verify the same behavior before and after the change. Select lasting regression tests, preserve reproduction evidence, and record the corrected user journey when possible.

中文简介正在准备中。当前显示英语简介。

• Investigating and fixing a bug without an existing candidate PR
• Proving a repair with failing-then-passing tests
• Consolidating regression checks into existing tests

Create upgrade guides for changes that make existing code or settings stop working. The skill checks differences and history, then provides specific steps, copyable before-and-after examples, and any available options for postponing the upgrade.

中文简介正在准备中。当前显示英语简介。

• Documenting an API rename
• Explaining removed flags or changed defaults
• Showing code before and after an upgrade

Create an Omnigent agent directory using validated templates for configuration and instructions. Choose how the agent runs, then add web search, shell access, external tool connections, or subagents only when the task requires them.

中文简介正在准备中。当前显示英语简介。

• Creating a minimal Omnigent agent
• Configuring an agent with web search
• Adding shell access or MCP tool connections

Review an existing bug-fix pull request using validated reproduction tests and the complete code diff. Assess root-cause coverage, scope, and regressions, then document behavioral evidence and follow the workflow's branch and approval rules.

中文简介正在准备中。当前显示英语简介。

• Independently verifying an existing bug-fix pull request
• Checking a complete diff for scope and root-cause coverage
• Recording the user journey on the proposed fix

Prepare a structured JSON handoff for bug fixes or pull request reviews. Capture outcomes, test evidence, change impact, publication status, and remaining work so the next person or workflow can understand what is complete and what remains.

中文简介正在准备中。当前显示英语简介。

• Handing off a completed bug fix
• Recording an existing pull request review
• Documenting unresolved checks and remaining work

Move an open pull request, a proposed code change, toward maintainer review by coordinating automated checks, two independent reviews, preview preparation, and live validation instructions, while tracking fixes and unresolved work.

中文简介正在准备中。当前显示英语简介。

• Preparing an open pull request for maintainer review
• Rechecking automated checks and reviews after fixes
• Handing over preview links and live validation steps

Investigate a reported bug before choosing a fix. Trace the actual failure, test competing explanations, and examine design history so the proposed change preserves intended behavior and clearly separates verified findings from unresolved assumptions.

中文简介正在准备中。当前显示英语简介。

• Reconstructing the conditions of a reported bug
• Distinguishing a symptom from its underlying cause
• Checking intended behavior in tests and history

Prepare a bug-fixing run by recovering reproduction details and tests, checking the workspace, and finding existing fixes. Select the appropriate workflow for a reproduction session, CI run, bug ticket, or requested PR changes.

中文简介正在准备中。当前显示英语简介。

• Recover reproduction tests from a session or CI run
• Check the workspace before starting a bug fix
• Find existing fixes before choosing an approach

Inspect imports and agent patterns in existing Python code to identify its framework and recommend an Omnigent executor, the component that runs the agent. Explain unsupported frameworks and suggest available next steps.

中文简介正在准备中。当前显示英语简介。

• Identify the framework used by existing Python agent code
• Choose an executor for Claude SDK or OpenAI Agents SDK code
• Check whether a framework has native support

Run independent development tasks in parallel, each with a separate git worktree and implementation agent. Each agent opens its own pull request, which receives cross-review before being handed to a human for review and merging.

中文简介正在准备中。当前显示英语简介。

• Implementing independent changes in parallel
• Assigning separate working directories to agents
• Preparing an individual pull request for each task

Create reference documentation directly from source code for public functions, classes, command-line commands, and endpoints. Organize parameters, defaults, return values, errors, and runnable examples, then check that the documentation matches the implementation.

中文简介正在准备中。当前显示英语简介。

• Writing reference docs for a public module
• Documenting command-line arguments and defaults
• Adding minimal usage examples for an API

Commit a validated bug fix and follow the selected publication path: keep it local, prepare it for a CI publisher, or open a pull request. Organize the description, regression test evidence, and handoff details for review.

中文简介正在准备中。当前显示英语简介。

• Keeping a validated fix in a local commit
• Preparing a pull request description and test evidence
• Handing publication over to a CI workflow

Plan and review new Omnigent harness integrations, the adapters connecting agent runtimes to the platform. Compare SDK and subprocess approaches with native interface wrappers, using capability matrices and checklists for implementation and testing.

中文简介正在准备中。当前显示英语简介。

• Plan a new agent runtime integration
• Compare SDK and native integration requirements
• Review approval, streaming, and session support

Review code changes with an independent agent from a different model provider. After tests pass, check a fixed diff against acceptance criteria, send blocking issues back to the implementer, and repeat until review passes.

中文简介正在准备中。当前显示英语简介。

• Get an independent review from another model provider
• Check a pull request against acceptance criteria
• Turn blocking findings into concrete fix tasks

Look up how to configure and organize Omnigent agents. Use examples to choose an executor, the agent's runtime, arrange instructions and skills, add local tools or external services, and define specialized child agents.

中文简介正在准备中。当前显示英语简介。

• Check agent directory layout and config.yaml settings
• Choose an executor and harness
• Add skills, custom tools, or MCP services

Keep chat-ui model settings aligned with the HuggingFace router. Add descriptions for newly available models, check reasoning support, enable artifact panels based on model size, and remove settings for models no longer served.

中文简介正在准备中。当前显示英语简介。

• Add newly released models to chat-ui settings
• Remove settings for models no longer served
• Check reasoning support and artifact eligibility

Identify maintenance problems across code, architecture, tests, dependencies, documentation, and infrastructure. Rank them by impact, risk, and effort, then produce a prioritized backlog with business reasons and a phased improvement plan alongside feature development.

中文简介正在准备中。当前显示英语简介。

• Deciding which parts of the codebase to refactor first
• Organizing maintenance issues across technical areas
• Explaining the business reasons for technical improvements

Create a Claude Cowork plugin through guided conversation, from defining its purpose to designing components and checking files. Receive a packaged .plugin file containing the skills and integrations needed for the agreed workflow.

中文简介正在准备中。当前显示英语简介。

• Creating a Claude Cowork plugin from an idea
• Packaging work instructions as reusable skills
• Designing a plugin with external service connections

Review code changes for security, performance, correctness, and maintainability. Get findings tied to files and lines, severity ratings, practical suggestions with code examples, and a recommendation to approve, request changes, or discuss further.

中文简介正在准备中。当前显示英语简介。

• Reviewing a pull request before merging
• Checking authentication and injection risks
• Finding excessive database queries and resource leaks

Compare technology options, review a system design, or plan a new component from requirements and constraints. The skill organizes the reasoning into an architecture decision record, a document covering alternatives, trade-offs, consequences, and next steps.

中文简介正在准备中。当前显示英语简介。

• Compare technologies before choosing one
• Document the reasoning behind a design decision
• Review a proposed system design

Investigate errors and unexpected behavior through reproduction, isolation, diagnosis, and a proposed fix. Receive a structured report covering the root cause, necessary code or configuration changes, and suggested tests to prevent the issue from returning.

中文简介正在准备中。当前显示英语简介。

• Investigate an error message or stack trace
• Diagnose behavior that differs between staging and production
• Trace a failure that appeared after deployment

Plan a system or service from requirements through components, APIs, data storage, and reliability. Produce a structured design document with diagrams, stated assumptions, trade-offs between choices, and decisions to revisit as usage grows.

中文简介正在准备中。当前显示英语简介。

• Planning the architecture of a new service
• Defining APIs, data models, and service boundaries
• Reviewing scaling and reliability plans