Loading...
Loading...
Found 38 Skills
Use when reviewing or scoring AI-generated unit tests/UT code, especially when coverage, assertion effectiveness, or test quality is in question and a numeric score, risk level, or must-fix checklist is needed
This skill should be used when user asks to "generate UML", "create sequence diagram", "生成时序图", "生成类图", "generate PlantUML", or discusses generating UML diagrams for new interfaces or API design.
Analyze code repository logging coverage to ensure all function branches have LOGE/LOGI logs and identify high-frequency log risks. Supports multiple programming languages (C++, Java, Python, JavaScript, etc.)
Automatically sorts C/C++ header files (#include statements) with full support for conditional compilation blocks. Use when Claude needs to organize
Debug HarmonyOS ArkWeb applications using Chrome DevTools Protocol. Use when Claude needs to: (1) Start ArkWeb debugging sessions, (2) Connect Chrome DevTools to HarmonyOS apps via hdc, (3) Inspect webview elements, console, and network, (4) Test ArkWeb applications with Chrome DevTools MCP, (5) Troubleshoot webview debugging issues, or (6) Manage port forwarding and debugging sessions. Automatically detects project configuration, device connection, and debugging sockets. Works with ohos-app-build-debug skill for complete workflow.
Execute ArkTS-Sta code snippets and files via the Playground HTTP API. Use this for testing ArkTS syntax, learning ArkTS features, verifying code logic, or demonstrating code execution results.
Analyze HM Desktop PRD documents, extract requirement information, verify completeness, check chapter order (Requirement Source → Requirement Background → Requirement Value Analysis → Competitor Analysis → Requirement Description), inspect KEP definitions, detect requirement conflicts, and generate structured analysis reports. Applicable to user requests: (1) Analyze or review PRD documents, (2) Extract KEP lists from requirements, (3) Check PRD completeness or consistency, (4) Map requirements to module architecture, (5) Verify PRD format compliance, (6) Verify completeness of competitor analysis chapters. Keywords: PRD analysis, requirement extraction, KEP verification, completeness check, chapter order validation, competitor analysis check, analyze PRD, requirement extraction, completeness check, chapter order validation
Parallel C++ Core Guidelines code review using multiple specialized sub-agents. Use when reviewing C++ code, modules, or files against C++ Core Guidelines to identify violations. Each sub-agent reviews against a specific guideline section (Functions, Classes, Resource Management, etc.) and outputs findings to separate markdown files in the review/ directory, followed by a consolidated summary.
Review a GitCode pull request from a PR number or URL when `oh-gc` must fetch PR metadata, diff, and comments, local repository code must be inspected for context, and the output should be concrete findings or a GitCode submission draft. Use for GitCode PR review or comment-submission requests that depend on `oh-gc`. Do not use for generic local review, GitHub/GitLab flows, or automatic submission without explicit user confirmation.
Use this skill when users want to report, collect, organize, classify, or standardize issues encountered while using AI tools. It applies to any scenario, including coding Agents, chat assistants, office assistants, search, writing, data analysis, and internal AI systems. The skill converts free-form descriptions into structured feedback reports with clear issue categories, tags, severity, scenarios, impacts, and suggestions for additional information.
Use when managing GitCode repositories from the terminal with oh-gc CLI — auth, issues, PRs, reviewers, testers, labels, releases, and repo config. Triggers on oh-gc commands, GitCode issue/PR management, or when user wants to interact with GitCode without a browser.
In-depth code problem analysis and root-cause localization. Used to analyze technical issues such as abnormal code behavior, execution-flow problems, and configuration errors. Use when the user needs to: 1) analyze code execution flow to find the root cause, 2) understand complex code logic and call chains, 3) identify the cause of abnormal behavior, or 4) troubleshoot configuration or state issues. Trigger phrases: problem localization, problem analysis, code analysis, root-cause analysis.