Loading...
Loading...
Found 65 Skills
Review the latest changes and check whether they comply with the project's documented guidelines (AGENTS.md, CLAUDE.md, or equivalent). Use when reviewing local diffs, recent commits, or feature work and you need a findings-first assessment of architecture, reuse, testing, and repo-specific rules.
Enforces Rust language and module standards for maintainable codebases. Use when writing Rust code, structuring modules, separating SQL/prompts from code, and enforcing one-thing-per-file discipline.
Validates code changes against DeepRead's mandatory patterns and standards defined in AGENTS.md. Use this after writing or modifying code to catch violations before committing.
Implement tasks from the change, writing actual code following the specs and design. Trigger: When the orchestrator launches you to implement one or more tasks from a change.
Proxy2.0 Java CRUD Interface Implementation Workflow: A 10-step standard process from requirement to full delivery. Use when: (1) Implementing new CRUD features for an entity, (2) Adding new API endpoints with full stack (DO/Mapper/VO/Service/Controller/SQL), (3) Following the standard implementation workflow for new business entities.
Perform a code review with linting, standards checking, and priority-ranked findings
Unified management of SVG icons in React TypeScript projects; supports icon component encapsulation, naming conventions, and migration guidance; applicable to scenarios such as project icon refactoring, new project icon specification formulation, and icon maintenance optimization
Audit code compliance with AGENTS.md project guidelines. Checks adherence to project conventions, naming, patterns, and standards. Read-only analysis. Use before PR. Triggers: review agents.md adherence, check guidelines, project standards compliance.
Hierarchical exception system with HTTP status codes, machine-readable error codes, and structured responses for consistent API error handling across all endpoints.
Use when developing custom Checkstyle checks, filters, and plugin integrations for project-specific Java code standards.
Deterministic 3-phase GitHub PR review comment extraction: Authenticate, Mine, Validate. Use when mining tribal knowledge from PR reviews, extracting coding standards from review history, or building datasets for the Code Archaeologist agent. Use for "mine PRs", "extract review comments", "tribal knowledge", or "PR review history". Do NOT use for analyzing patterns, generating rules, or interpreting comments — that is the Code Archaeologist agent's responsibility.
Automatically detect code quality issues and provide improvement recommendations