Software Development AI Skills

Forces Claude to pause before picking an implementation approach and ask: "Is there a cleverer, cheaper way?" Triggers when the request involves generating data or fixtures (lists, datasets, sample…

当用户明确要求“测试项目”、 “运行 auto-test-project”或“进行项目级测试”时使用。对完整项目执行多轮 A 轮批判性测试与 B 轮质量检查，发现、记录、修复并验证问题。⚠️ 不适用：用户只是想优化功能、询问项目问题，或没有明确测试意图。

Implement and execute approved research Experiment, Tuning, or Design Cards with reproducible logs, metrics, environment, and artifacts. Use for bounded coding, debugging, and runs; not for changing…

Use when the user wants one or more GitHub issues run in parallel through a Codex CLI validate pass, a separate Codex CLI plan pass, and a Claude subagent build that opens a pull request (PR) per…

高德地图实时路况查询与最优自驾路线规划技能。基于高德交通态势API和路径规划API，提供实时拥堵信息和最快路线建议。

Deployment option comparison (serverless, dedicated, self-hosted, batch) and Workflow execution patterns. For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference.

Generate unit and UI tests for specified code with edge cases and mocks. Triggers: "generate tests", "write tests", "add tests", "test coverage".

Power Platform Solution Architecture. Use when: selecting app type (Code App vs Canvas vs Model-Driven), designing solution structure, environment strategy, integration patterns, security…

UI craft: build, redesign, or visually review an interface and its design system. Not for backend or other non-visual work.

Interrogate a UX idea, requirement, flow, feature, or design direction before execution. Use when a designer asks to be challenged, wants assumptions exposed, wants a red-team review of the premise,…

Core conventions for writing HTML styled with Bullframe CSS. Use before any other Bullframe skill, and whenever choosing a build, scaffolding a page, theming with tokens, or deciding whether to write…

Convert MP3/WAV/FLAC audio files to MIDI (.mid) and MusicXML (.musicxml) with full music analysis. Two engines: Basic Pitch (general-purpose polyphonic) and Piano Model (high-accuracy piano, 96.7%…

Generate a native, editable PPTX deck from an outline, notes, or source material with the PPTwise CLI. Use when the user asks to create a PPT, deck, presentation, or slides and wants a deterministic,…

Build, launch, and visually test iOS/SwiftUI apps in the Simulator using computer use. Automated screen navigation, crash log analysis, state testing (empty/error/loading), and memory leak detection.…

Guidelines and instructions for Agent execution state rollback rules

Maps a reference (site, screenshot, Figma, CSS, brand book) to OpenDesigner dials, or writes its Taste Index. Copies structure and quality, never another brand's identity.

Use this skill when picking a brand archetype, propagating it across product and marketing surfaces, or auditing brand-voice consistency. Trigger when designing the voice of microcopy, marketing…

Comprehensive skill for GSAP (GreenSock Animation Platform) and ScrollTrigger plugin. Use this skill when creating web animations, scroll-driven experiences, timelines, tweens, scroll-triggered…

Turn an app idea or an existing React Native app into a Nav Read - tab structure, route tree, push/modal/sheet decisions, deep links, Android back plan - without building any screens. Use when…

End-to-end reviewer for a completed multi-phase feature at the end of a phase-orchestrator run. Use after all requested phases are finalized: inspects the whole feature against the plan and PRD/spec,…

Use when building or updating the design system's catalogue site and its machine-readable registry - component gallery, auto-extracted props tables, token explorer, lifecycle/status board, adoption…

Audit a web page for RGAA v4.1.2 Theme 11 – Forms accessibility compliance. Checks that form fields have labels, labels are relevant and visible, labels are properly associated, related fields are…

Use when verifying the codebase against the UX scenario base (batched, evidence-backed, report in docs/ux/audits/). Triggers: "ux audit" / "UX-аудит", "run the scenarios" / "прогони по сценариям". Not…

Execute a single deterministic Python script to compute all derived financial metrics (EBITA, Invested Capital, Tax Rates, Summary Table) from extracted financial data.

路演构造术：从产品仓库、GitHub URL、讲稿或既有 PPT 提炼证据与产品视觉风格，用 RW 生成整页图片初稿，再转换为保留版式的可编辑 PPTX。用于比赛答辩、产品路演，以及“rwppt 初稿转可编辑”的完整流程；支持从已有图片稿或部分可编辑稿续做，并按需交付讲稿、时间表、Demo 预案与评委问答。

This skill should be used when designing or building an API — endpoints, routes, request/response shapes, error formats, pagination, versioning, or deciding REST vs GraphQL. Trigger phrases include…

Fix detached or missing variable bindings in Figma — typography (fontFamily, fontStyle, fontSize, fontWeight), padding/spacing (paddingTop/Right/Bottom/Left, itemSpacing, counterAxisSpacing), corner…

Discover, validate, or draft a project-owned DESIGN.md before adding or revising UI in an existing frontend. Use during design-playbook initialization when a repository already has pages, components,…

Comprehensive GitHub code review with AI-powered swarm coordination

Refactor a JS, TS, React (JSX/TSX), CSS, Sass, Vue, Svelte, or Astro file with improved naming, simplified logic, dead code removal, and modern syntax, without changing behavior. Usage:…

Router for ambiguous metrics prompts — "metrics", "help with metrics", "where do I start?", `/metrics-help`. Asks one scoping question and points to the right skill. Fallback only — the seven…

Audits an existing SVG file or animated React scene and returns ranked findings with fixes: render-target safety (GitHub README image proxy, browsers), accessibility, motion quality, file weight and…

Independent adversarial code review via Codex CLI to eliminate Claude self-review bias

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Development conventions and patterns for ECC. JavaScript project with conventional commits.

Ask which skill or flow fits your situation. A router over the skills in this repo.

Delegate coding tasks to the Blackbox AI multi-model CLI.

Launch and automate VS Code Insiders with the Copilot Chat extension using @playwright/cli via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel,…

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should…

DCE-safe require() patterns and edge runtime constraints. Use when writing conditional require() calls, guarding Node-only imports (node:stream etc.), or editing define-env-plugin.ts / app-render /…

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple…

Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit,…

QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or…

Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.

Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For…

Guidelines and tools for reviewing pull requests in the Angular repository.

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple…

Evaluate and carry out non-trivial software-system changes from first principles. Use when assessing RFCs, issues, designs, features, refactors, migrations, dependency changes, or proposed fields,…

Extract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing /understand knowledge graph.

Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says…