Generate and edit images from the CLI using picture-it. Use this skill whenever the user asks to create, edit, or manipulate images — blog headers, social cards, hero images, product comparisons, YouTube thumbnails, movie posters, magazine covers, Instagram edits, background removal, or any visual content. Also trigger when the user mentions picture-it by name, wants to composite images, apply color grading, add text to images, remove or replace backgrounds, crop/resize photos, or needs any kind of image generation or photo editing from the terminal. This skill covers multi-pass AI image editing workflows that chain composable operations together.
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
- 📁 .github/
- 📁 analytics/
- 📁 architecture/
- 📄 .ggshield.yaml
- 📄 .gitguardian.yaml
- 📄 .gitignore
Routes DigitalOcean App Platform tasks to specialized sub-skills. Use when working with App Platform deployments, migrations, database configuration, networking, or troubleshooting.
- 📄 code-analyzer.yaml
- 📄 pmd-ruleset.xml
- 📄 SKILL.md
Run Salesforce Code Analyzer on Apex, Trigger, Flow, or metadata files. Use after writing or modifying .cls, .trigger, .xml, or flow files. Also use when asked to scan, lint, or check code quality.
- 📁 .github/
- 📁 .superpowers/
- 📁 archon-cli/
- 📄 .gitignore
- 📄 archon-context.json
- 📄 archon-self.json
Archon can be invoked as a skill by AI agents during the development loop to provide architectural context and validation.
- 📁 agents/
- 📁 evals/
- 📁 outputs/
- 📄 SKILL.md
Create low-friction coursework deliverables for general education, elective, and low-stakes college assignments, including PPT slides, short papers, reading reports, reflection essays, presentation scripts, discussion posts, and course summaries. Use this skill whenever the user mentions 水课, 通识课, 选修课, 小论文, 课程论文, 读书报告, 观后感, 汇报PPT, 课堂展示, 演讲稿, or asks to turn scattered course materials into a polished student-style deliverable. --- # Coursework Helper Skill Produce practical course deliverables from messy prompts, readings, course slides, topic requirements, and user notes. The goal is to help a busy student quickly get a usable PPT, short paper, speech script, or reflection while keeping claims grounded in provided material. ## Architecture ```text User request -> Intake: infer task type, deadline pressure, source materials, tone, and format -> Setup: index materials, check official file skills, initialize output directory -> Plan: choose deliverable path and create a lightweight outline -> Draft: produce content, slides/script, or paper -> Polish: add citations/evidence notes, fix tone, export requested formats ``` | Path | Use when | Primary output | |------|----------|----------------| | `slides` | PPT/class presentation/课堂展示/汇报 | `final_slides.md`, optional `.pptx`, speech script | | `paper` | 小论文/课程论文/读书报告/观后感/心得体会 | `final_paper.md`, optional `.docx`/`.pdf` | | `script` | 演讲稿/发言稿/答辩稿/课堂分享 | `final_script.md` | | `mixed` | User asks for PPT + paper + script, or task is ambiguous | combined deliverables | ## Startup Layer ### 1. Low-Friction Intake Infer as much as possible from the user's words and files. Ask only when the missing answer would change the deliverable.
资深软件架构师顾问——分析模块间关系、评估重大改动方案、解答架构疑惑。 当用户说"帮我分析架构"、"这个改动合理吗"、"我想重构 X"、"这样设计有什么问题"、 "帮我评估方案"、"架构上怎么看"、"我有个大改动"时立即触发。 也适用于："这个模块怎么拆"、"依赖关系合理吗"、"接口怎么设计"、 "该用哪种模式"、"迁移方案怎么做"、"这个 PR 改动太大了"等架构决策场景。 只要用户面临影响多个模块、涉及接口变更、或需要权衡取舍的技术决策，就应使用此 skill。 --- # Architect — 架构顾问 Skill 以资深软件架构师的视角，分析**模块之间的关系与边界**，评估变更影响，给出有理有据的建议。 核心关注点是：**谁依赖谁、谁负责什么、消息/数据如何在模块间流动**——而不是某个模块内部的实现细节。 --- ## 第一步：建立项目上下文 先阅读架构层面的文档，不深入源码实现。**并行执行**： ``` read_file("CLAUDE.md") # 项目架构说明（最重要） glob_files("**/Cargo.toml") # Workspace 模块结构（Rust 项目） bash("git log --oneline -15") # 近期改动方向 ``` 如果存在 spec/global/ 目录，还需读取： ``` glob_files("spec/global/**/*.md") # 全局架构文档 ``` > 目标：搞清楚项目有哪些模块、它们之间的依赖关系是什么、数据流的大方向——然后才能讨论改动的影响。 --- ## 第二步：理解问题 明确用户面临的决策点： - **涉及哪些模块**：改动横跨哪几个模块/crate/组件 - **现有的模块关系**：它们目前如何交互（调用、事件、共享状态、消息传递） - **想改什么**：计划中的边界或接口变化 - **驱动原因**：解耦、功能扩展、性能、可维护性 如果问题描述不够清晰，**先问清楚再分析**。 --- ## 第三步：架构分析框架 核心视角始终是**模块边界与模块间关系**，而非单个模块的内部实现。 ### 3a. 评估一个变更方案 逐一检视有实质内容的维度： | 维度 | 关注点 | | ---------------- | ---------------------------------------------------------------- | | **依赖方向** | 变更后依赖是否保持单向？是否引入循环依赖？ | | **接口稳定性** | 跨模块的契约（trait/API/消息格式）是否被破坏？调用方需要改多少？ | | **职责归属** | 每个模块的边界是否清晰？有没有职责被错误地放到了边界另一侧？ | | **数据流清晰度** | 数据/事件在模块间的流动路径是否可追踪、可推理？ | | **模块耦合度** | 改后模块间的耦合是增加还是减少？是紧耦合还是通过抽象层解耦？ | | **迁移成本** | 需要同步修改哪些调用方？能否分阶段落地而不一次性破坏所有接口？ | ### 3b. 诊断一个架构问题 先描述**症状**（难以扩展、边界模糊、牵一发动全身、职责重叠），再追溯**根因**（哪两个模块的关系出了问题、为什么），最后给出**最小有效改动**。 ### 3c. 比较多个方案 用结构化表格从模块关系角度对比，最后给出**明确推荐**和**推荐理由**。不要给出"都可以，看你喜好"——那不是架构建议，那是回避。 --- ## 第四步：输出结构 根据问题复杂度选择格式： **简单问题（单一决策点）**：直接给结论 + 核心理由，不超过 200 字。 **中等复杂度（涉及 2-3 个模块的关系）**： ``` ## 当前模块关系 <描述涉及模块之间现有的依赖/交互方式> ## 问题所在 <哪个边界有问题，或哪两个模块的关系不对> ## 建议调整 <推荐的模块关系，说明为什么这样划分更合理> ## 注意事项 <迁移时需要同步调整的接口、潜在的破坏性变更> ``` **大型变更（跨多个 crate / 重新划定模块边界）**： ``` ## TL;DR <一句话结论> ## 当前架构关系图（文字描述） ## 变更后架构关系图（文字描述） ## 方案对比 ## 推
- 📁 rules/
- 📄 AGENTS.md
- 📄 metadata.json
- 📄 README.md
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
- 📁 glab-alias/
- 📁 glab-api/
- 📁 glab-attestation/
- 📄 README.md
- 📄 SKILL.md
- 📄 VERSION
Comprehensive GitLab CLI (glab) command reference and workflows for all GitLab operations via terminal. Use when user mentions GitLab CLI, glab commands, GitLab automation, MR/issue management via CLI, CI/CD pipeline commands, repo operations, authentication setup, or any GitLab terminal operations. Routes to specialized sub-skills for auth, CI, MRs, issues, releases, repos, and 30+ other glab commands. Triggers on glab, GitLab CLI, GitLab commands, GitLab terminal, GitLab automation.
RESTful API design conventions including endpoint naming, HTTP methods, status codes, pagination, error handling, and versioning patterns. Use when designing APIs, creating endpoints, or reviewing API contracts.
- 📁 .claude-plugin/
- 📁 .cursor-plugin/
- 📁 .github/
- 📄 .DS_Store
- 📄 .gitignore
- 📄 .markdownlint-cli2.jsonc
Use when working with OpenTelemetry - configuring collectors, designing pipelines, instrumenting applications, implementing sampling strategies, managing cardinality, securing telemetry data, troubleshooting observability issues, writing OTTL transformations, making production observability architecture decisions, or setting up observability for AI coding agents (Claude Code, Codex, Gemini CLI, GitHub Copilot, and others)
Translate changed English locale keys into all other languages
