Software Development AI Skills

Управление расширениями конфигурации в информационной базе 1С. Используй когда нужно узнать какие расширения подключены к базе, выполнить проверку применимости или синтаксическую проверку, изменить…

Scans your project for outdated npm, pip, Cargo, Go, or Ruby packages. Runs a CVE security audit. Fetches changelogs, summarizes breaking changes with Gemini, and opens one PR per risk group (patch,…

Use when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling backend enforcement, or managing token refresh.

Author, validate, run, and participate in Prowl Agent Workflows — the `prowl.workflow/v1` bundles that orchestrate several live coding agents (launch, message, loop on verdicts, collect outputs, run…

Design and generate Convex database schemas with proper validation, indexes, and relationships. Use when creating schema.ts or modifying table definitions.

BDD patterns for acceptance test design - Given-When-Then structure, scenario writing rules, pytest-bdd implementation, anti-patterns, and living documentation

Use when writing, rewriting, or reviewing PR/CL descriptions, commit messages, or code-change summaries that explain what changed and why. TRIGGER on "write PR description", "improve this commit…

Analyze a codebase for high-leverage architectural improvements and explain evidence, tradeoffs, and next steps. Use explicitly for architecture audits or deep-module refactoring opportunities.

Profile and optimize application performance. Use when asked to improve speed, reduce latency, fix memory leaks, find bottlenecks, or optimize a slow function or endpoint.

Commits, pushes and remotely verifies authorized repository changes; does not create releases.

Refactor, simplify, or clean up code for improved maintainability without changing business logic

Use this skill when creating, running, reattaching to, listing, stopping, or removing Docker Sandboxes (the standalone `sbx` CLI that runs AI coding agents in isolated microVMs), even if the user just…

Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring, reviewing, choosing…

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore,…

Use when creating complete generated audio with qwen-audio-3.1-tts-next, including podcasts, radio drama, advertisements, multiple speakers, reference voices, ambience, sound effects, or background…

Generate images using OpenAI's Codex backend API with gpt-image-2 tool. Use when the user asks to generate images via Codex, ChatGPT image generation, or gpt-image-2. Triggers on "codex image", "codex…

AST-based code search and refactoring via ast-grep MCP

Use when developing, deploying, or debugging Butterbase serverless functions, or when the user needs to add backend logic like webhooks, scheduled jobs, or custom API endpoints

Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript,…

Complement an answer or discussion with a first-principles visual HTML explanation, saved in Grain when connected. Use when explaining how something works, why it changes, or how options differ and a…

Use this skill to instrument a Jetpack Compose composable with `@TraceRecomposition` from `skydoves/compose-stability-analyzer` so per-recomposition diffs (which state or parameter changed, what value…

Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or…

USE THIS when asked to create a new eslint plugin rule for the eslint-plugin-cds package

Initialize a PartCAD package in the current directory by running the installed PartCAD CLI (`pc init` / `partcad init`). Use when the user runs /pc:init or asks to initialize or create a PartCAD…

Update the title and body of one or more pull requests.

Builds and runs Qt Quick Test (qmltestrunner / CTest) for a QML project, then writes a Markdown report. Use for "run qml tests", "run qmltestrunner".

推荐并生成合适的数据可视化图表，使用 GPT-Vis 库。支持两种输出模式：（1）语法模式——生成 Syntax 或 JSON 配置；（2）代码模式——生成完整的运行代码。支持 26 种图表类型。

Translate SQL queries into plain language business logic. Use when documenting queries, explaining analysis to non-technical stakeholders, code reviewing for correctness, or building a query catalog.

Invoke a dedicated coding agent (Codex, Claude Code, OpenCode, pi, or Cursor Agent) for bug fixes, feature implementation, file edits, repository changes, or targeted validation when the user wants…

Manage prompt versions, run A/B tests across agent prompts, track performance regressions, and safely roll out prompt changes in production. Covers prompt diffing, semantic versioning, canary…

Use when assessing use of named design-system components or tokens across a defined sample of product artifacts, including adoption and deviation questions.

Cross-browser, cross-platform, and cross-device compatibility testing ensuring consistent experience across environments. Use when validating browser support, testing responsive design, or ensuring…

Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a…

Create the TestDriver client, authenticate, and connect to a sandbox

Transform the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery using the ElevenLabs Voice Changer (speech-to-speech) API. Use when converting…

Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK. Use when the user wants to implement Airflow tasks in Java/JVM, asks about…

Use proximity and spacing to show relationships

Implement one todo or review-fix task supplied by a coordinator, verify it, create one focused commit, and report evidence through the current Superconductor session. Use when launched by /execute,…

中国互联网品牌感知监测统一工具。聚合全网热榜追踪（hub）、小红书/抖音/公众号近30天深度讨论研究（cn30）、豆包/Kimi/DeepSeek AI 搜索品牌可见度分析（geo）三个互补模块，帮助品牌方/市场运营/内容创作者从「话题热度—真实口碑—AI 回答」三层视角全面感知品牌。当用户需要研究中国社交媒体热点、分析品牌舆情、对比竞品口碑、分析品牌在 AI 搜索中的表现、做 GEO…

Build a LinkedIn content system for thought leadership. Use when someone needs to establish authority, attract inbound leads, or build a consistent content presence. Covers positioning, content…

技术负责人 Agent — 技术架构决策、代码审查、团队技术管理、技术规划与路线图

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create…

Talk to a senior product advisor who thinks in Ivan Zamesin's Next Move Theory / Advanced Jobs To Be Done methodology (distinct from generic Christensen JTBD). A multi-turn conversational skill — ask…

Free DeFi analytics across all chains — TVL, token prices, DEX volumes, fees/revenue, stablecoins, and bridges

Defines one feature or major change: required behavior, technical design, failure handling, and acceptance checks. Use when consequential decisions must be settled before delivery. The spec is the…

Synthesize a PRD (Product Requirements Document) for a big new feature. Synthesis (not interview) — uses existing project context and explicit ADRs. Asks before gh issue create. Use when scoping a…

Multi-turn consultation with Codex CLI for second opinions, brainstorming, or collaborative problem-solving. Use when the user asks to "consult codex", "ask codex", "get codex's opinion", "brainstorm…

Builds features with A/B testing in mind using Ronny Kohavi's frameworks and Netflix/Airbnb experimentation culture. Use when implementing feature flags, choosing metrics, designing experiments, or…

Use when extending the Unreal Editor from C++ with detail customizations, editor utility widgets, menus, editor modes, asset definitions or editor subsystems. Also use when the user mentions…

AI-assisted coding with Claude Code, Cursor, Copilot, Codex, Aider, or Windsurf. Use to build or debug generated code.

Use when code generation, repository understanding, or coding-agent tasks need Alibaba Cloud Model Studio Qwen Coder models (`qwen3-coder-next`, `qwen3-coder-plus` and related coder variants).