“llm implementation”的搜索结果

Reviews code for security vulnerabilities and guides secure implementation using OWASP Top 10:2025, ASVS 5.0, the OWASP Top 10 for LLM Applications (2026), and the OWASP Top 10 for Agentic Applications (2026). Use when reviewing code or a diff for security issues, implementing authentication, authorization, sessions, or cryptography, handling untrusted input, files, or URLs, hardening config, dependencies, or CI, or building LLM and AI agent features.

中文简介正在准备中。当前显示原文说明。

UE (user experience engineering) skill for defining end-to-end user experience behavior and interaction logic. Use for tasks like flow design, interaction models, state machines, error recovery, input validation, usability heuristics, accessibility, and turning UX intent into testable acceptance criteria for implementation.

中文简介正在准备中。当前显示原文说明。

Architecture-first UI/UX design skill for Codex that helps agents reason from product truth, user journeys, causal design decisions, art direction, interaction, responsive behavior, imagery, iconography, and motion before implementation, then validate the result through rendered browser critique.

中文简介正在准备中。当前显示原文说明。

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

中文简介正在准备中。当前显示原文说明。

Dual-mode UX quality skill — runs a heuristic/accessibility/motion audit on the current codebase, or validates implementation against design mockups. Fixes all issues found and commits.

中文简介正在准备中。当前显示原文说明。

Create QA checklists for verifying design implementation accuracy.

中文简介正在准备中。当前显示原文说明。

Transforms a rough idea into a detailed design document with implementation plan. Follows Prompt-Driven Development — iterative requirements clarification, research, design, and planning.

中文简介正在准备中。当前显示原文说明。

Translate a vague request or GitHub issue into a concrete, testable spec using five structured elements (problem, scope, acceptance criteria, edge cases, success criterion) before writing any code. Prevents scope creep, PR churn, and mid-implementation pivots.

中文简介正在准备中。当前显示原文说明。

Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.

中文简介正在准备中。当前显示原文说明。

AI/ML Workflow Bundle workflow skill. Use this skill when the user needs AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

中文简介正在准备中。当前显示原文说明。

AI/ML Workflow Bundle workflow skill. Use this skill when the user needs AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

中文简介正在准备中。当前显示原文说明。

Use when comparing two or more code implementations against a spec or requirements doc. Triggers on "which repo is better", "compare these implementations", "evaluate both solutions", "rank these codebases", or "judge which approach wins". Also covers choosing between competing PRs or vendor submissions solving the same problem. Does NOT review a single codebase for quality — use code review skills instead. Does NOT evaluate strategy docs — use strategy-review. Requires a spec file and 2+ repo paths.

中文简介正在准备中。当前显示原文说明。

Map user journeys, onboarding paths, entry points, first actions, trust points, accessibility risks, and SEO/LLM handoffs for public websites without redesigning the visual system. Use this skill when the user asks how new readers, returning users, project reviewers, community members, buyers, or AI agents should move through a site and what each page must make clear before layout implementation.

中文简介正在准备中。当前显示原文说明。

Fast spec-driven implementation from a committed spec. Use after /spec to implement an issue with a phase roadmap, TDD waves, map patching, review, and pre-commit validation.

中文简介正在准备中。当前显示原文说明。

Write a durable feature spec before touching code. Reads the codebase map, reads related models/migrations to ask technical questions (not generic ones), then produces a structured spec doc in docs/specs/. Designed to pipeline with /implementation --issue N. Use before any feature implementation.

中文简介正在准备中。当前显示原文说明。

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

中文简介正在准备中。当前显示原文说明。

METAINFORMANT rules for directory src/metainformant/ml/llm. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

中文简介正在准备中。当前显示原文说明。

METAINFORMANT rules for directory src/metainformant/ml/llm/ollama. Use when editing, adding tests, or reviewing code under this path. Read the linked AGENTS.md first; use uv only, write outputs to output/, real implementations.

中文简介正在准备中。当前显示原文说明。

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

中文简介正在准备中。当前显示原文说明。

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

中文简介正在准备中。当前显示原文说明。

针对美国医疗软件的HIPAA合规评估，检查患者信息的处理、向外部服务发送数据的条件、必要的最小访问权限和审计记录。

• 检查AI诊疗摘要的HIPAA合规问题
• 评估向分析平台发送患者信息
• 设计最小必要访问权限和审计记录

帮助您使用Unsloth，以LoRA和QLoRA微调语言模型，探索减少GPU内存占用的训练方式，并依据官方文档整理的参考资料查询功能与API、实现代码和排查错误。

• 开始使用LoRA或QLoRA微调
• 查询Unsloth功能与API
• 排查训练代码中的错误

支持开发让 AI 使用外部服务的 MCP 服务器，从 API 调研、工具设计与实现，到功能检查和评估题编写，帮助检验多次工具调用下的实际使用效果。

• 将外部 API 接入 AI 智能体
• 用 TypeScript 或 Python 开发 MCP
• 改进工具说明、输入和错误提示

Analyze the last seven days of agent and model token usage to identify unnecessary spending. Recommend changes to model selection, prompt caching, and overlapping work, with estimated dollar savings, percentage reductions, and implementation priorities.

中文简介正在准备中。当前显示英语简介。

• Investigating higher-than-expected AI costs
• Matching model choices to task complexity
• Reviewing prompt caching efficiency