Software Development AI Skills

Prepares leaders for daily effectiveness in an AI-augmented workplace by focusing on the human capabilities that machines cannot replicate. Covers five irreplaceable leadership skills (interpersonal…

Look up WoW Mount, Pet, Pet Battle, Toy, Stable, and Heirloom Collection APIs. Covers C_MountJournal (mount list, filtering, favorites, summoning, display info), C_PetJournal (pet collection,…

Create and modify Frappe DocTypes including schema design, controllers, child tables, and customization. Use when building data models, adding fields, or implementing document lifecycle logic.

Guided codebase exploration for understanding a repo's architecture, patterns, and domain language before contributing. Not issue-specific. builds general understanding. Use when exploring a new repo,…

Создание, запуск, обновление, загрузка и выгрузка информационных баз 1С, Git и ibcmd.

Start a session from the newest project handoff written by /handoff, checked against the repo before any work.

Author Sysdig Secure Posture custom controls (Rego) and custom policies, and emit Terraform via the Sysdig provider. Use when the user wants to "write a posture rule," "create a custom CSPM control,"…

Evidence check before claiming completion. Use before telling the human a task is done, fixed, or working, especially at the end of long or multi-part tasks. Verifies the work actually runs and every…

Use when handing off an in-progress session to another agent or a future session — ending a session with unfinished work, "pick up where I left off", passing a task to a fresh agent/another…

适用于 TypeScript、JavaScript、React 和 Node.js 开发的通用编码标准、最佳实践和模式。

Use for the dependency-injection part of ANY task in a Kotlin, Android, Compose, KMP or Ktor project that uses Koin, even when the request never mentions DI or Koin: adding a feature, screen,…

Odoo 17 development reference for Python models and ORM (search, domain, read_group, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups),…

Analytics and attribution setup — tracking plan, UTM conventions, dashboard design, and attribution model selection. Use when "analytics setup", "attribution", "tracking plan", "UTM", "marketing…

Explain and write effective instructions for OpenAI Codex's `/goal` feature — the persistent self-checking agent loop (plan → act → test → review → iterate). Use when the user mentions Codex `/goal`,…

ecommerce-competitor-analyzer是由buluslan（公众号：新西楼.AI）研发的电商竞品分析Skill，他会帮你拆解竞对的定价、评论、流量结构和差异化空间，把"对手到底强在哪"变成一份可执行的竞品分析报告。 更多跨境电商 AI 实战内容，请关注公众号「新西楼.AI」。 Multi-platform competitor analysis across Amazon /…

在抖音网页版按关键词搜索公开作品、读取 video 或 note 作品详情，并查看公开热门话题。用户要求搜索抖音、查找作品、查看公开作品详情、查看热门话题或解析抖音作品链接时使用。

Creates and improves short, focused Agent Skills. Use this skill when writing or revising a SKILL.md, its description, or its bundled files. Do not use for installing third-party skills or for one-off…

Review a Confluent agent skill in this repo against the Agent Skills spec (agentskills.io), Confluent conventions in CLAUDE.md, the PR template gates, and the evals-as-contract rule. Use this skill…

Generer conventional commit-meldinger med Nav-relevante scopes og breaking change-format

Find and maintain Development Track Notes and PR Review Notes through Qodo tools. Use at task intake or when resuming a development effort, before opening a PR, after opening it to bind its notes, or…

适用于 drpy-node 源修复、调试、测试与可用性评估。用户提到"修源""测试某个源""详情为空""播放不通""搜索异常""源无效""低分评估""源评分低""诊断""排障""修播放""源不通""规则不生效""评估低分"时使用。负责先评估、再分流、再收束上传建议；不直接执行仓库上传/替换/改标签。

Seedance 1.5/1.0 系列视频生成 API 文档（火山方舟平台）。用于通过 API 调用 Seedance 模型实现文生视频、图生视频（首帧/首尾帧/参考图）、有声视频生成等功能，包含完整的请求参数、SDK 示例、提示词技巧和错误码参考。

Creates a simple Todo API with FastAPI, SQLite, and basic CRUD operations.

AppleScript and JXA automation for macOS. Use when user asks to automate apps, control system, run AppleScript/osascript, or integrate with macOS applications.

当用户要写出高质量 Goal Prompt，把模糊、战略性、多步骤、证据不足、持续/自动化或容易跑偏的请求整理成可执行、可验证、可暂停的目标契约时使用。适用于写 goal、优化任务提示词、明确 done/success criteria、deep research 后定战略、大改前 inventory、修复跑偏计划、识别可委托的重复 workflow、为 Codex 或 Claude Code…

Rewrite a rough, terse, or under-specified request into a prompt that follows Anthropic's Claude prompting guides (Fable 5.1, Opus 5.5), then carry it out. Add "just the prompt" or "프롬프트만" to only see…

Use Alibaba Cloud Data Agent MCP tools for enterprise database/file analysis, SQL analysis sessions, reports, insights, CSV/XLSX/JSON/TXT uploads, workspaces, custom agents, and session management.…

个人编码习惯与最佳实践总纲 — 命名 / 代码组织 / 风格工具链 / TS 严格模式 / 错误处理 / 测试 / 审查 / LLM 编码 / Git 工作流 / Bun 工程约定 / 文档写作。写码、review、写文档之前先读本 skill 定位要查哪篇。

Configure ruff, mypy, and basedpyright for Python 3.13 projects. Use when setting up linters and type checkers in pyproject.toml and pyrightconfig.json.

Style for edit-video: a white grid page with the speaker in a rounded card along the bottom and their head breaking out above it, dark pills and cards that blur in and out, and one-to-two-word…

Use when writing any user-facing reply — answers, status updates, summaries, or final reports — especially after multi-step work, when tempted to show thoroughness, add headers or bullets to a short…

Use before publishing documentation, merging a docs PR, or reporting a Markdown-heavy repo's navigation as complete — when you want ground-truth confirmation that internal links, heading anchors, and…

Search and read locally-stored Claude documentation covering Claude Code CLI, Claude API (Messages, tool use, vision, streaming, batch), Agent SDK (Python and TypeScript), prompt engineering, and all…

Discover and install agent skills from the open ecosystem (skills.sh), optimized for Japanese users. Use when the user asks 'how do I do X', 'is there a skill for X', or in Japanese…

Stellar dApp / frontend development. Covers the JavaScript stellar-sdk (browser + Node.js), Freighter wallet, Stellar Wallets Kit (multi-wallet), Wallet Standard, smart accounts with passkeys,…

EffectCraft is an open-source, pure-Rust motion-graphics, compositing and VFX app for macOS, Windows, Linux and the web — a clean-room, After Effects-shaped studio with compositions, layers,…

Finalize an autoresearch session into clean, reviewable branches. Use when asked to "finalize autoresearch", "clean up experiments", or "prepare autoresearch for review".

Maintains and improves the project-scaffolding skill. This skill should be used when the user asks to "update the scaffolding skill", "refresh framework versions", "are the versions stale", "check for…

Scaffold a new Deep Agents (LangChain) agent, a dcode CLI agent, or both, from one command. Use ONLY when the user explicitly runs /new-dcode-agent; never auto-trigger. It interviews the user (form,…

Expert knowledge in mobile app development for iOS, Android, and cross-platform solutions

Draft a commit message strictly for the work done in THIS session, identifying exactly which files belong in the commit. Ignores pre-existing dirty files.

PHP development intelligence. 12 domains, 8 stacks, 300+ entries. Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check PHP code. Domains: pattern,…

Apply Corbin Crutchley's Git workflow when implementing repository changes, drafting or reviewing commit messages, organizing commits, synchronizing branches, or preparing a push. Commit incrementally…

Skyline 组件开发技能。涵盖 scroll-view 及其增强模式（列表/嵌套滚动）、swiper 高级特性、表单组件、图片/文本组件、半屏可拖拽组件、共享元素动画等。适用于需要开发滚动列表、轮播、表单输入、页面过渡动画等场景。

Use this skill when calculating control system performance metrics such as rise time, overshoot percentage, steady-state error, or settling time for evaluating simulation results.

Profile a dataset without changing it: shape, dtypes, missingness, duplicates, distributions, anomalies, candidate group/target/time columns. Emits profile.json.

Build a persistent context system (atlas) for any repository — generates directory maps with entrypoints, documents architecture and module boundaries, traces critical flows, catalogs external…

Decomposes a feature into scoped agent tasks before a multi-agent sprint. Reads ARCHITECTURE.md layer ownership, CLAUDE.md agent model, and VECTOR.md constraints to generate a structured task manifest…

Publish a new version via GitHub Actions. Use when user says "publish", "release", or "bump version".

Write internal corporate communications — announcements, org changes, policy updates, launch messages — with clarity, honesty, and calibrated warmth. Use when the user writes company-wide emails,…

TDD cycle and code quality guardrails for the implementer and reviewer agents during /speq-implement. Not for general coding.