AI Skills Directory

Assess and guide safer github.com repository releases. Use when an existing private GitHub repository becomes public for the first time, or whenever an already-public GitHub repository publishes a new…

Select and configure linear solvers for Ax=b systems arising in numerical simulations — choose between direct (LU, Cholesky) and iterative (CG, GMRES, BiCGSTAB, MINRES) methods, analyze sparsity…

Prepare an account team for one specific competitive opportunity - the deal state, who they are actually up against, what the buyer said matters in their own words, the three questions that decide the…

The mounted Cerb documentation -- what lives where, how to find a page without reading it, and when the docs are the authority versus this install. Load it before your first search of `cerb-docs`.

Implements difference-in-differences in R or Python with parallel trends testing, robustness checks, and plain-language interpretation. Use when user asks about DiD, staggered rollout, TWFE, event…

Detect BGP route oscillation and route leaks in Azure Virtual WAN topologies, evaluate candidate solutions. Use when analyzing BGP preference cycles and valley-free routing violations.

Use when the user explicitly asks to run the incremental change cycle after adding code or changing function behavior, especially for long-running or high-token work where checklist continuity and…

Testany platform case 编写助手 - 将传统测试场景拆解为 Testany platform cases，并生成可注册的 case packages

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.

Use when asked to find bugs, hunt for correctness issues, sweep a codebase for defects, or verify a repo behaves as intended. Not for style or architecture review; this is defect-finding only.

Extract and parse content from URLs. Triggers on: user provides a URL to extract content from, another skill needs to parse source material, "parse this URL", "extract content", "解析链接", "提取内容".

Structured safe-change workflow for documented codebases. Reads and writes only canonical YAML artifacts under a resolved structured docs root.

Opens and uses the local roadmap web workspace for visual review. Use when the user wants to inspect projects, tasks, kanban state, or planning views in the browser.

Color grade clips the way a professional colorist does — normalize, balance, match, then build a look — using inspect_color scopes and apply_color (exposure, white balance, wheels, curves, hue curves,…

Nano Banana2 多模态 AI - 支持文生图、图生图、Vision 分析。发送"生图 柴犬"生成图片，发送图片+描述做风格化重绘。底层调用 Gemini，支持 10 种宽高比。关键词：生图、画图、AI画图、文生图、图生图、generate image、Gemini、重绘

Write acceptance criteria for user stories or requirements as Gherkin scenarios (Given, When, Then) or EARS statements, including negative, boundary and permission cases, so that business users and…

End-to-end UI/UX: removes AI slop, redesigns screens around what they must achieve, and verifies on the real screen. Use on "clean the AI slop", "improve the UI", "improve the UX", "redesign this…

Use when the user says "/plan-review", "plan review", or "PRD review" and provides a plan file path that needs critical review and iterative refinement with Codex.

Generates professional AI images using Google Gemini. ALWAYS invoke this skill when building websites, landing pages, slide decks, presentations, or any task needing visual content. Invoke IMMEDIATELY…

Prepare audit workpapers, control tests, samples, evidence, deficiencies, and remediation tracking.

A capture-first kanban board for agent-driven work. Fights chat-to-plan context loss with one rule: every user push AND every agent mid-turn discovery becomes a card the SAME turn, before acting.…

Create GitHub issues for gstack-game improvements — skill gaps, wrong benchmarks, new skill proposals, template bugs. Maps conversation context into actionable issues with proper labels and skill…

Decodes and analyses ESP32-family panics — Guru Meditation errors, register dumps, backtraces, aborts, stack overflows and watchdog timeouts on both Xtensa (ESP32, S2, S3) and RISC-V (C2, C3, C5, C6,…

Cairo smart-contract authoring on Starknet. Trigger on "write a contract", "create a contract", "implement this in Cairo", "add storage/events/interface", "compose components". Guides structure,…

Audit existing Meta custom audiences, their usage, targeting fields, and auction overlap without claiming audience discovery.

Data acquisition for web scraping and data collection. Use when user needs "爬取数据/抓取网页/scrape data". Outputs structured JSON/CSV for analysis.

Generate production-ready Dockerfile for any GitHub project. Supports monorepo, multi-stage builds, workspace detection, and iterative build-fix cycles. Use when user asks to create, generate, write,…

Orchestrating design-to-implementation pipelines (code to visual to code closed loop), persisting a project design system across agents. Not for a single prototype (Forge) or direction only (Vision).

B2B-Outreach-E-Mails im deutschen und DACH-Kontext konservativ entwerfen und prüfen. Nutze diesen Skill für Kaltakquise-Mails, Nachfassnachrichten, Betreffzeilen und Outreach-Sequenzen an…

Check how much of a ticket is already implemented and save a per-requirement status report.

Use when a team wants every developer's coding agent (Claude Code or Codex) to follow the same rules on a Maven Spring Boot 4 repository: setting up AGENTS.md, guardrails, shared agent settings, or…

Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.

Use this skill when the user asks about "altitude and horizon framework", "Shreyas Doshi altitude", "working at the right level", "am I too in the weeds", "I'm too tactical", "how do I work at the…

This skill should be used when working with gpio for GeoParquet inspection, validation, optimization, and distribution. Covers GeoParquet best practices using gpio CLI and DuckDB.

Security-agents-only scanner using all 12 parallel specialized subagents without discovery, data flow tracing, false positive analysis, or triage. Use when asked to "agents-only scan", "raw agents…

从多个视角并行生成多轮追问对话，作为公众号文章的原始素材。用户输入一个起始问题，AI 自动从不同视角展开深度对话

Execute a card end to end — pick it up, implement following the guidelines, validate, open the PR, chain into /watch-pr. Full flow authorized by invocation (automode) — zero questions in the happy…

Codify project review rules as deterministic guards — ast-grep structural rules (with TDD-style rule tests) for mechanical checks, REVIEW_GUIDELINES.md for qualitative ones, wired into the project…

Use this skill when the user asks to create, edit, or manipulate images programmatically — including diagrams, charts, infographics, thumbnails, social media graphics, image processing (resize, crop,…

Bounded clarification/refinement pass for planning. Use before finalizing a phased plan when unresolved [?] markers or plan-changing ambiguity remain. Triggers on: 'use clarify mode', 'clarify',…

Designs technical solutions and architecture. Use when user says "design solution", "architecture design", "technical design", or "方案设计" WITHOUT mentioning PRD. For PRD-specific work, use prd-planner…

Generate agile release plans with sprints and roadmaps using unique sprint codes. Use when creating sprint schedules, product roadmaps, release planning, or when user mentions agile planning, sprints,…

Write integration tests using .NET Aspire's testing facilities with xUnit. Covers test fixtures, distributed application setup, endpoint discovery, and patterns for testing ASP.NET Core apps with real…

Use when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for…

Integrate Univer Sheets, Docs, or Slides into React, Vue 3, HTML, or Node.js projects. Use when embedding Univer, choosing preset or plugin mode, initializing instances, configuring…

Manages flight bookings made with the FlightClaw MCP server. Lists orders, shows booking references and status, quotes flight change options and cancels with a refund quote first. Use when the user…

Build a workflow to protect sender reputation through automated bounce monitoring. Auto-suppresses contacts above a configurable bounce threshold, alerts on hard bounces, and flags high-bounce…

Decompose a game concept into individual systems, map dependencies, prioritize design order, and create the systems index. Run after /brainstorm and before /design-system when a concept exists but…

Phase 1 circuit topology and anchor-component discussion expert. ALWAYS invoke this skill when the user wants to discuss circuit structure, pick a topology, choose anchor parts, or extend a project…

Diretor de edição de vídeo curto (Reels, TikTok, Shorts, YouTube, LinkedIn) — edita os takes que você gravou (corte por palavra, jump cut, rosto + tela, textos e imagens aparecendo em cima de quem…

Generate a detailed content brief for a specific article or page. Use when the user asks to "create a content brief", "write a brief", "article outline", "blog brief", "writing brief", "content…