Claude Code Skills · page 82

Building, compiling, and resolving dependency issues across languages

Systematic code review for bugs, security, style, and performance

Working with diverse data formats: binary, text, structured, and custom

Systematic exploration of unknown environments before starting work

Git operations: commits, branches, PRs, and conflict resolution

Writing efficient code that handles large data and tight constraints

Refactor code to improve structure and maintainability

Create new reusable skills from conversation context

Systematic approach to diagnosing and fixing errors

Generate comprehensive test suites for existing code

Thorough verification of completed work before declaring done

Best practices for creating research diagrams with Excalidraw MCP tools

Guidelines for writing well-structured, cited research reports

Best practices for systematic research, source evaluation, and evidence gathering

Comprehensive data analysis skill for CSV files using Python and pandas

Generate pytest test cases for Python functions and classes

Launch Loki Mode autonomous SDLC agent. Handles PRD-to-deployment with minimal human intervention. Invoke for multi-phase development tasks, bug fixing campaigns, or full product builds.

Pause for review every N tasks - selective autonomy pattern

Applies prompt repetition to improve accuracy for non-reasoning LLMs

AI Engineering from Scratch 的阶段测验。用于“给我测验一下”、“测试阶段”、“检查我的理解”、“我掌握第 3 阶段了吗”，也支持 "quiz me", "test phase", "check my understanding", "do I know phase 3" 或 `/check-understanding <phase>`。

>

>

>

>

>

>

>

当（when）变更新增或修改 migrations/ 下的路径时，审查 database migration 文件。合并前使用此 migration Skill 收集正向、回滚、锁定和数据安全证据。

Validate an Agent Skill package and choose the right instruction, capability, or lifecycle primitive before implementation.

在明确的发现 scope 中构建受限的 Agent Skill 目录，并在加载指令正文前报告冲突。

为 Agent Skill 目录设计并测试显式人工、隐式模型或 agent、程序化应用、有界 skill 组合和 harness 激活策略。

在不执行的前提下，依据显式沙箱策略审查 skill 请求的文件系统、命令、网络、secret 或破坏性操作。

在发布前评估 Agent Skill bundle 的结构完整性、触发质量、产物改进、脚本正确性、安全性、已安装目录树完整性和目标宿主可移植性。

Explain any topic, code, concept, or error tailored to a specific audience's level of understanding. Use this skill whenever the user says 'explain like I am', 'ELI5', 'explain this to my', 'break this down for', 'dumb it down', 'simplify this for', or asks you to explain something to a specific person or audience type (e.g., 'explain this to a manager', 'how would I explain this to my mom', 'make this understandable for a 5th grader'). Also trigger when the user mentions wanting to understand something at a particular level, or asks for an explanation targeting a non-technical audience. Even partial matches like 'explain to my wife' or 'tell my boss' should trigger this skill.

Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to refresh project conventions and standards.

Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.

Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.

Use Trellis channel for live multi-agent collaboration, spawned workers, cross-agent review, progress inspection, forum channels, and channel log debugging.

Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.

Resume work on the current task. Loads the workflow Phase Index, figures out which phase/step to pick up at, then pulls the step-level detail via get_context.py --mode phase. Use when coming back to an in-progress task and you need to know what to do next.

Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.

Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents under .trellis/agents/, selectable workflow templates, registry-backed spec refresh, cross-session memory (trellis mem) generated by trellis init, or AI-facing bundled skills (trellis-channel, trellis-session-insight, trellis-spec-bootstrap) and bundled-skill auto-dispatch flow.

Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize.

Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder text.

Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or re-establishing project context.

Captures executable contracts and coding conventions into .trellis/spec/ documents. Use when learning something valuable from debugging, implementing, or discussion that should be preserved for future sessions.

当设计或修改 REST API 响应结构、处理 API 返回值，或生成 Excel/CSV/PDF/对账文件等下游产物时触发。防止 API 设计缺陷导致的字段错位、类型歧义，以及生成产物时关键字段缺失但静默成功的问题。

网关/代理/WAF/CDN 中间件的安全关键词匹配实现规范，防止纯子串匹配误判正常响应内容中的技术术语（如 Cloudflare、502、error）

当 API/任务可能执行超过 10 秒（批量数据处理、远程 API 批量调用、全表扫描、跨租户聚合）时触发。防止同步接口被网关 30s 超时切断、用户重复点击触发并发、状态缓存内存泄漏等问题。提供异步任务状态机标准模板。

当用户操作 .sh、Dockerfile、Makefile、.yml、.yaml 文件，或在 Markdown 中编写 bash 代码块时触发。提供 Bash 编写规范。

当编写新模块、设计接口、重构代码或代码审查时触发。提供经典模块化六原则检查清单（大小适中/调用深度/扇入扇出/边界清晰/作用域内聚/可预测性），适用于 PR/Review/新模块设计场景。

涉及浏览器、编辑器、CDN/WAF、IM 平台、操作系统剪贴板、第三方 SaaS 等"外部黑盒系统"的代码编写或 bug 调试时触发。强制先抓真实环境数据再推理,避免连续 2 轮"凭代码推理"的修复 no-op。关键词:粘贴/复制异常、跨平台显示不一致、第三方 API 怪结果、CDN/WAF 拦截、本地复现失败、HTML→MD 转换丢属性。

当重构涉及字段映射（dataIndex、枚举映射、类型转换）时触发。防止字段名推测错误，确保字段映射的正确性。

前端开发规范，包含 Vue 3 编码规范、UI 风格约束、TypeScript 规范等

Go 开发规范，包含命名约定、错误处理、并发编程、测试规范等

Java 开发规范，包含命名约定、异常处理、Spring Boot 最佳实践等

当代码涉及多租户隔离（TenantContext、tenantId、租户拦截器/过滤器、X-Tenant-Code）时触发。防止租户越权访问、数据串租户等安全问题。

当用户执行系统级命令（sysctl、iptables、systemctl、Docker 配置、数据库 DDL）或进行服务器运维操作时触发。提供运维安全规范。

当代码涉及支付回调、webhook 通知、notify_url、微信支付/支付宝回调处理时触发。防止回调伪造、重放攻击、金额篡改等支付安全问题。

Python 开发规范，包含 PEP 8 风格、类型注解、异常处理、测试规范等

当代码涉及循环内查询、批量 ID 查询、IN 子句、BFS/递归遍历、嵌套 service 调用时触发。防止 N+1 查询、IN 子句过长、递归内存炸裂等性能陷阱。

当用户操作 Redis 相关代码（go-redis、Jedis、redis-py、ioredis）时触发。涵盖禁止 KEYS 命令、SCAN 替代、大 key 控制、Pipeline 批量、TTL 规范等安全与性能要点。

当用户要求重构代码（提取组件、合并重复逻辑、重命名变量、优化结构）时触发。提供重构安全检查清单，防止丢失原始上下文。

当用户执行 /ruanzhu 命令或请求生成软著源代码文档时触发。提供软著源代码 DOCX 生成规范。

Rust 开发规范（聚焦 Axum + Tokio 后端栈），覆盖工具链、错误处理、异步陷阱、模块组织、依赖管理与测试规范

Review changed code for reuse, quality, and efficiency, then fix any issues found. Also scans project files for size limit violations.

当使用 MinIO/OSS/S3 等对象存储、设计文件上传下载功能时触发。提供存储 URL 策略选择规范，防止 URL 过期、访问失败等问题。

当代码涉及 Excel/CSV/JSON/PDF 大文件导出、批量序列化、内存里构建大对象时触发。防止 OOM、临时文件残留、同步导出阻塞 HTTP 线程等内存安全陷阱。

当代码出现 LocalDate.now() / LocalDateTime.now() / Instant.now() / new Date() / Date.now() / time.Now() 等"当前时间"调用，或涉及周/月/日起点、跨时区比较、数据库时间字段时触发。防止生产环境时区漂移导致的统计错乱。

专业级 UI/UX 设计规范，需要高质量界面设计时手动触发或描述"设计感/专业UI"时自动触发。覆盖视觉层次、配色体系、排版节奏、交互微动效、响应式适配等。日常前端开发由 frontend-dev skill + frontend-design 插件覆盖。

结构化技术设计工作流，适用于显式 design doc 或 checklist 生成；不负责需求盘问、bug 修复或正式代码审查。

前后端接口契约安全规范，适用于接口新增或调整、联调、列表分页异常与临时兼容治理；用于避免响应结构漂移被前端兼容长期掩盖。

当设计或修改 REST API 响应结构、处理 API 返回值，或生成 Excel/CSV/PDF/对账文件等下游产物时触发。防止 API 设计缺陷导致的字段错位、类型歧义，以及生成产物时关键字段缺失但静默成功的问题。

网关/代理/WAF/CDN 中间件响应判定与关键词匹配安全规范。适用于 proxy/gateway/waf/cdn/nginx/openresty/rewrite/redirect 等代码,防止把正常长正文中的 Cloudflare、502、bad gateway、error 等技术术语误判为上游错误。

当 API/任务可能执行超过 10 秒（批量数据处理、远程 API 批量调用、全表扫描、跨租户聚合）时触发。防止同步接口被网关 30s 超时切断、用户重复点击触发并发、状态缓存内存泄漏等问题。提供异步任务状态机标准模板。

Bash、Shell、Dockerfile、Makefile 与命令片段规范，适用于脚本修改、命令编写和文档中的 shell 示例；不负责运维审批策略。

当编写新模块、设计接口、重构代码或代码审查时触发。提供经典模块化六原则检查清单（大小适中/调用深度/扇入扇出/边界清晰/作用域内聚/可预测性），适用于 PR/Review/新模块设计场景。

结构化 git commit message 生成工作流，适用于显式 commit message、提交说明或 commit-msg 场景；不负责实际执行 git commit。

通用防御性编码规范，适用于跨语言代码修改中的最小改动、真实边界处理、定向验证，以及约束假想风险驱动的过度兜底或抽象；不负责语言细节、正式 review 或结构化 debug。

涉及浏览器、编辑器、CDN/WAF、IM 平台、操作系统剪贴板、第三方 SaaS 等"外部黑盒系统"的代码编写或 bug 调试时触发。强制先抓真实环境数据再推理,避免连续 2 轮"凭代码推理"的修复 no-op。关键词:粘贴/复制异常、跨平台显示不一致、第三方 API 怪结果、CDN/WAF 拦截、本地复现失败、HTML→MD 转换丢属性。

当重构涉及字段映射（dataIndex、枚举映射、类型转换）时触发。防止字段名推测错误，确保字段映射的正确性。

结构化 bug 修复工作流，适用于显式 fix 或 debug 场景；不负责语言规范、正式 review 或运维审批。

前端开发规范，包含 Vue 3 编码规范、UI 风格约束、TypeScript 规范等

Go 开发规范，适用于 Go 源码、包结构、错误处理、并发和测试相关任务；不负责 review、debug 或运维流程。

>

Import recorded driving sensor data (GPS, camera, lidar, actor tracks, lanes) into scenariobuilder.* objects (GPSData, CameraData, LidarData, ActorTrackData, Trajectory, laneData) and run preprocessing — synchronize, offset correction, crop, normalizeTimestamps, convertTimestamps. Also: compute actor tracks from lidar when no annotations exist, attach camera/lidar mounting + intrinsics, export to MAT/workspace/timetable/script. Use for raw driving dataset files (KITTI, nuScenes, Waymo, Pandaset, ROS/ROS2 bags, .mat, .csv, .mp4) or driving/vehicle/sensor logs that need wrapping. drivingLogAnalyzer (DLA) is OPT-IN ONLY — invoke only on explicit user request ('DLA', 'open in DLA', 'inspect/explore/analyze the recording') or reported sensor problem (sync drift, timestamp mismatch, overlay misalignment). NEVER auto-launch DLA after wrapping (Rule 0). For 'build scenario / export to RoadRunner / drivingScenario / OpenSCENARIO / Unreal / simulate', hand off to matlab-scenario-builder.

Generate driving scenes, scenarios, road surfaces, and 3D content from already-wrapped scenariobuilder.* sensor data (GPS, camera, lidar, actor tracks) using Scenario Builder for Automated Driving Toolbox. Use to BUILD, EXPORT, or AUGMENT a virtual scenario/scene/map: ego or actor trajectories, trajectory smoothing, OpenCRG road-surface extraction, 3D asset generation, static-object placement, point-cloud georeferencing + elevation, lane-based ego localization, sensor-fusion tracking, scenario-event extraction (cut-ins, hard brakes, near-misses, ADAS disengagements), or export to RoadRunner, drivingScenario, OpenDRIVE, OpenCRG, OpenSCENARIO, or Unreal Engine. Also: log-to-scenario, scenario harvesting, accident/near-miss reconstruction, SOTIF (ISO 21448) and ISO 26262 scenario coverage, USGS-aerial-lidar scene augmentation, traffic-sign placement from camera+lidar logs. NOT for raw-data import or multi-sensor sync/crop/offset/timestamp normalization — route those to matlab-driving-data-importer.

>

>

>

>

Build, modify, and diagram SimBiology models — API reference, helper functions, and layout patterns. Use when constructing or editing models programmatically or visually.

Fit SimBiology model parameters to data — fitproblem, population NLME, virtual patients, and NCA. Use when asked to fit, estimate, calibrate, or compute PK metrics.

Simulate SimBiology models — ODE, stochastic (SSA), scenarios, and sensitivity analysis. Use when asked to run, simulate, predict, explore what-if, or identify influential parameters.

Display images and annotations for image processing, computer vision, and visual inspection. Use when displaying images with imageshow, creating image viewers with viewer2d, adding Regions of Interest (ROI) or annotations, overlaying masks or segmentations, streaming video frames, or building apps with image display.

Display 3-D image volumes, medical image volumes, surface meshes, and annotations for 3-D image processing. Use when displaying 3-D images or isosurfaces with volshow, creating volume viewers with viewer3d, adding Regions of Interest (ROI) or annotations, overlaying masks or segmentations, streaming volumetric data, or building apps with volume display.

>

Patterns for using blockedImage to process large images, harness parallel compute for image processing, and write custom adapters. Use when writing code that creates, processes, or visualizes blockedImage objects, when implementing images.blocked.Adapter subclasses, or when a user needs help with large image data. Always use this skill when working with TIFF,GeoTIFF, .svs, .ndpi, .czi or other WSI, satellite imagery or microscopy volume image formats.

>

Create, edit, and run plain-text MATLAB live scripts (.m files) with rich text formatting, LaTeX equations, section breaks, and inline figures. Use when generating tutorials, analysis notebooks, reports, documentation, or educational content, when modifying existing live scripts, or when converting existing binary .mlx files to .m for version control. Requires R2025a+.