172 个 · 按相关度排序
Analyze a codebase to create project-specific AGENTS.md instructions and supporting rule files. Detect the package manager and relevant conventions, preview proposed changes, or update existing guidance when the project’s tools change.
中文简介正在准备中。当前显示英语简介。
Design criteria for using an LLM to judge AI responses through scoring or comparisons between two answers. Includes checks for order and length bias, plus validation against human judgments to assess evaluation reliability.
中文简介正在准备中。当前显示英语简介。
Add a model page to the SGLang Cookbook using shared templates. Organize verified launch settings and measured benchmarks, create configuration files and documentation, and update navigation, vendor cards, and page validation.
中文简介正在准备中。当前显示英语简介。
Turn user data and interviews into research-backed personas, or representative user profiles. The toolkit also supports mapping user journeys, planning usability tests, and combining research findings to guide and validate design decisions.
中文简介正在准备中。当前显示英语简介。
Refresh installed NanoClaw channel and agent provider code from its registry branches. Update all integrations or a selected subset, check a structured result report, and validate the updated installation with builds and tests.
中文简介正在准备中。当前显示英语简介。
Review database structures and relationships, identify design issues, and generate relationship diagrams. The skill recommends indexes, which help queries find data efficiently, and prepares migration steps with validation and rollback planning.
中文简介正在准备中。当前显示英语简介。
Prepare for FDA medical device quality audits through six evidence-focused questions. Review complaints, adverse event reports, process validation, manufacturing records, corrective actions, labeling, and inspection history, then organize readiness gaps and three next actions with owners.
中文简介正在准备中。当前显示英语简介。
Manage the AI models offered through OpenWork, including model additions, removals, aliases, and pricing discounts. Validate configuration consistency and trigger the GitHub workflow that refreshes models from models.dev, then report its merge or failure result.
中文简介正在准备中。当前显示英语简介。
Expose REST APIs as tools for AI agents through Google Cloud API Gateway using MCP, a protocol for connecting agents to tools. Covers OpenAPI migration, authentication, client connections, validation, and troubleshooting.
中文简介正在准备中。当前显示英语简介。
Create or update Claude skills that capture specialized knowledge and repeatable workflows. Guides the organization of instructions, scripts, references, and templates, then covers initialization, validation, and packaging into a distributable skill file.
中文简介正在准备中。当前显示英语简介。
Evaluate a driving agent on CARLA Leaderboard routes after checking the required setup. Select routes and repetitions, save driving scores and infractions, record runs, and resume interrupted evaluations from a saved checkpoint.
中文简介正在准备中。当前显示英语简介。
Verify whether a reported vulnerability is fixed in the current code without changing repository files. Trace the original attack path, examine possible bypasses and legitimate behavior, and return an evidence-based verdict for each supplied finding.
中文简介正在准备中。当前显示英语简介。
Run TypeScript checks that detect type errors without generating files. When shell execution fails because of environment problems or timeouts, switch to shell_agent to locate tools, address setup issues, and report the check results.
中文简介正在准备中。当前显示英语简介。
Handle one known local bug or testable bug hypothesis through reproduction, independent validation, repair, and regression checks. Produce a local patch commit and evidence reports that help reviewers judge whether the fix is ready.
中文简介正在准备中。当前显示英语简介。
Diagnose slow loading, high memory use, and low frame rates in USD 3D scenes. Coordinate scene structure checks, validation, optimization, and before-and-after performance comparisons, then produce a report documenting findings and changes.
中文简介正在准备中。当前显示英语简介。
Verify whether a reported vulnerability is fixed in the current code without changing repository files. Trace the original attack path, examine possible bypasses and legitimate behavior, and return an evidence-based verdict for each supplied finding.
中文简介正在准备中。当前显示英语简介。
Move NuGet package versions from individual .NET projects into a shared management file. The skill audits version conflicts, preserves project conditions, validates builds before and after conversion, and produces comparison files and a migration report.
中文简介正在准备中。当前显示英语简介。
Compare two or more dotnet new templates using their installed options, features, and supported frameworks. Get a focused comparison table and a recommendation that explains which template best fits the project you want to build.
中文简介正在准备中。当前显示英语简介。
Guide npm package releases through dependency checks, version alignment, publishing procedures, and post-release smoke tests, which are basic installation and operation checks. It also documents fallback steps for failed automation and project-specific rules about who initiates releases.
中文简介正在准备中。当前显示英语简介。
Check package changes against changesets, the files describing release updates, to assess summaries and required version increases. Use it to review pull requests or uncommitted changes and obtain a structured verdict with errors, warnings, and the required bump.
中文简介正在准备中。当前显示英语简介。
Understand how unfamiliar code works from a security perspective. The skill maps architecture, follows untrusted input through the code, and searches for similar vulnerability patterns, with file and line references to support static analysis and finding validation.
中文简介正在准备中。当前显示英语简介。
Turn user data and interviews into research-backed personas, or representative user profiles. The toolkit also supports mapping user journeys, planning usability tests, and combining research findings to guide and validate design decisions.
中文简介正在准备中。当前显示英语简介。
Security considerations for Jackson JSON deserialization in Java applications. Covers timing of validation, raw input interception, and common deserialization attack patterns.
中文简介正在准备中。当前显示原文说明。
Generate JSON Schema definitions for MCP tool input parameters. Creates well-documented, AI-consumable schemas with proper types, descriptions, and validation rules.
中文简介正在准备中。当前显示原文说明。