Coding standards, frameworks, refactoring, and code review (16.7K skills)
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 Review merged pull requests, verify user-facing highlights and contributor credits, and deliver unpublished notes alongside a complete changelog preview.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.