1580 个 · 按相关度排序
Generate or update up to nine project documentation files using agents that inspect the code directly. Check documentation against the implementation, review existing files without writing changes, or explicitly regenerate all documentation.
中文简介正在准备中。当前显示英语简介。
Review medium to large code changes using checks selected for the actual patch. Analyze the change and surrounding code, assign focused reviews by function, file, or feature, and combine findings with locations, confidence levels, and supporting evidence.
中文简介正在准备中。当前显示英语简介。
Review the current codebase for ignored errors, embedded credentials, unused exports, and obvious type-safety gaps. Receive a report ordered by severity, with file and line references, while all source files remain unchanged.
中文简介正在准备中。当前显示英语简介。
Run an AI vulnerability scan on uncommitted changes, changes against main, or an entire codebase. Filter candidate files, investigate potential security issues, and review findings with severity ratings, with options to revalidate and export results.
中文简介正在准备中。当前显示英语简介。
Find other occurrences of a known bug across a codebase by tracing its root cause. Gradually broaden search patterns, assess matching candidates, assign severity, and document findings with rules to help prevent recurrence.
中文简介正在准备中。当前显示英语简介。
Audits arithmetic code for mixed units, decimal precision mistakes, and scaling errors. Adds comments identifying each value’s units and produces a summary of findings, unit definitions, and files reviewed.
中文简介正在准备中。当前显示英语简介。
Scans code for security vulnerabilities with CodeQL by tracing data across functions. Builds and checks analysis databases, models project-specific APIs, and saves findings in SARIF, a structured results format, with broad or focused scan options.
中文简介正在准备中。当前显示英语简介。
Build or update a Figma design system to match a codebase. Organize reusable design values, light and dark themes, component variants, and documentation, then check component structure, appearance, and bindings to those values.
中文简介正在准备中。当前显示英语简介。
Investigate unfamiliar codebases before fixing bugs, adding features, or refactoring. Follow relevant code paths, plan focused changes, and verify results, while recording useful discoveries in .notebook/ so later sessions can build on earlier investigation.
中文简介正在准备中。当前显示英语简介。
Analyze TypeScript and JavaScript code for reusable design structures known as GoF patterns. Get detection reports, quality scores, and prioritized refactoring suggestions that account for the frameworks and libraries already used in the project.
中文简介正在准备中。当前显示英语简介。
Learn the complete OpenSpec workflow through a small task in an actual codebase. The agent explains each stage while creating a proposal, specifications, design, and tasks, then implements the change and archives its records.
中文简介正在准备中。当前显示英语简介。
Introduce nullable reference types into an existing C# project, making explicit which references may be null. Plan a staged migration, resolve compiler warnings, and clarify public API annotations while preserving runtime behavior.
中文简介正在准备中。当前显示英语简介。
Examine a plan or design through focused questions, each with a recommended answer. Work through connected decisions to reach shared understanding, using codebase exploration to resolve questions that the code can answer.
中文简介正在准备中。当前显示英语简介。
Organize large coding tasks with Claude Fable directing lower-cost subagents. Delegate bounded research, edits, and tests, then have Fable verify evidence, resolve conflicting findings, integrate changes, and review the final result.
中文简介正在准备中。当前显示英语简介。
Build a compact overview of an unfamiliar codebase with TLDR. Summarize its file tree, functions, classes, and calls between components, then highlight complex functions while reducing the amount of source text the agent needs to read.
中文简介正在准备中。当前显示英语简介。
Turn feature requests and conversation context into an implementation plan and handoff document. Review existing code, clarify complex requirements, and organize concrete tasks, affected files, verification steps, assumptions, and risks for review before implementation.
中文简介正在准备中。当前显示英语简介。
Search a codebase with WarpGrep to find functions, variables, imports, and other text. Use regular expressions to match text patterns, limit searches to a directory, or replace the contents of a specified file.
中文简介正在准备中。当前显示英语简介。
Get oriented in an existing codebase by identifying its technologies, important files, and architecture. The skill gathers your goals and creates a YAML handoff record with priorities and suggested next actions.
中文简介正在准备中。当前显示英语简介。
Investigate how an existing codebase works and document its components, connections, and file references. Combine current code findings with historical notes to produce a research document grounded in specific paths and line numbers.
中文简介正在准备中。当前显示英语简介。
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。
Compare feature requirements with an existing codebase to identify missing capabilities and integration challenges. Evaluate extending existing code, building new components, or combining both, then save findings and open research questions to inform the design phase.
中文简介正在准备中。当前显示英语简介。
Document a project's purpose, technical choices, and organization patterns as persistent reference files for agents. Compare existing guidance with the codebase, identify mismatches, and propose additions while preserving user-written content.
中文简介正在准备中。当前显示英语简介。
Audit an area of the codebase and propose the smallest structural moves that improve it - untangle boundaries, kill duplication, fix seams, break cycles. Produces a prioritized plan and decision records, not a rewrite. Use when a codebase feels tangled, hard to change, or is becoming a ball of mud, or when asked to improve or refactor architecture.
中文简介正在准备中。当前显示原文说明。
Guided journey from a working codebase grown slow and tangled to one measurably fast, cleanly bounded, and readable. Orchestrates eight skills phase by phase - working-with-legacy-code, clean-architecture, software-design-philosophy, refactoring-patterns, system-design, ddia-systems, release-it, pragmatic-programmer - every phase carries its method inline so it runs standalone, asking the user questions at every decision point and recording results in the project docs/ folder (PERFORMANCE.md, ARCHITECTURE.md, ARCHITECTURE-OPTIMIZATION-PLAN.md) so the journey resumes across sessions. Use when the user wants to make an app faster, untangle drifted boundaries, fix slow endpoints and queries, or says 'it works but it is slow and getting worse'. For an untested prototype, improve-code-quality; for an aged codebase you fear to touch, remove-technical-debt; for greenfield structure, design-code-architecture; for marketing-site page speed, improve-website. For one framework in isolation, invoke that skill directly.
中文简介正在准备中。当前显示原文说明。