Software Development AI Skills

Safety guardrails for destructive commands. (gstack)

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.

Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.

Use when reviewing templates, rendered HTML, or shared components related to Create accessible tooltips. Validate the final browser-facing markup, not just the source framework abstraction.

Test an application against the OWASP Top 10 with Strix — autonomous AI agents that attempt real exploits for each category of the current OWASP Top 10:2025 (broken access control including SSRF,…

Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails.

Browser automation CLI using DOMShell MCP server. Maps Chrome's Accessibility Tree to a virtual filesystem for agent-native navigation.

Orchestrates a GitHub PR review loop by delegating triage and implementation to dedicated sub-agents, then repeating until actionable review items are cleared. Use when the user says “address PR…

Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction

Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames,…

Monitor and manage your OpenCode tasks using helper scripts.

Refresh the repo's captured learnings against the current codebase. Use when auditing stale, overlapping, superseded, or drifted learnings; avoid general refactor, debugging, or code review unless the…

Capture decisions and commitments after a meeting and draft a concise follow-up.

This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies,…

AI Berkshire skill: 财务数据获取与交叉验证规范. Source: skills/financial-data.md.

ZKsync Era (Immunefi) completed hunt — 0 findings after exhaustive 5-session audit. Use as a DEFENSE STUDY — learn what makes a protocol unhuntable, which patterns block all 10 bug classes, and when…

SDFormat/SDF model and world authoring, validation, and simulator handoff. Use for `.sdf` files, SDFormat XML, models, worlds, links, joints, poses, frames, inertials, visual/collision geometry, mesh…

Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing,…

Use when testing keyword categorization

Next.js 16 App Router patterns. Trigger: When working in Next.js App Router (app/), Server Components vs Client Components, Server Actions, Route Handlers, proxy.ts, caching/revalidation, Cache…

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track…

Use this skill when the user asks to inspect, diagnose, or directly control a configured qBittorrent, Transmission, or rTorrent instance. It exposes provider capabilities on demand without adding…

Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker…

Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to…

Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and…

当你有一份书面实现计划需要在单独的会话中执行，并设有审查检查点时使用

Run compile and type-check commands and report failures

Provides a complete workflow for implementing verified email retrieval on Android Credential Manager API. Use this skill to integrate a secure, OTP-less email verification flow into an Android app.…

Scans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities — chain halts, fund loss, state divergence. 25 core + 16 IBC + 10 EVM + 3 CosmWasm patterns. Use when…

Produces distinctive production UI and screenshot-grounded visual polish. Use when building or restyling pages, components, or typography. Not for backend logic or data pipelines.

Trigger: broad exploration, multi-file reads, tests/builds, fresh review, or multi-step debug. Orchestrate complex work via delegate_task to protect context.

Codex debugging: codex-rs core/tui/exec/cli/app-server/config.

创建飞书云文档。从 Lark-flavored Markdown 内容创建新的飞书云文档，支持指定创建位置（文件夹/知识库/知识空间）。

Groups existing components into logical business domains to plan service-based architecture. Use when asking "which components belong together?", "group these into services", "organize by domain",…

Generate well-formatted git commit messages following conventional commit standards

Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, mapping data between…

This skill helps users extract structured product details from Amazon using a specific ASIN (Amazon Standard Identification Number). Use this skill when the user asks to get Amazon product details by…

Guide on React patterns, performance optimization, and code quality for Epic Stack

Guides conversion of a pre-.NET 8 Blazor Server app into a .NET 8+ Blazor Web App. USE FOR: migrating apps that use AddServerSideBlazor and MapBlazorHub to the AddRazorComponents/MapRazorComponents…

Hunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering. Mass assignment: send {is_admin:true, role:admin, verified:true} on profile/account/reset endpoints —…

扫描代码库中的深化机会，生成可视化 HTML 报告，然后围绕你选中的候选项继续追问。

Open Knowledge Format (OKF) v0.2 guidance. Use when creating, reading, reviewing, or maintaining an OKF bundle; responding to OpenKnowledge `okf` plugin warnings; or choosing types, provenance, links,…

Orient Claude from Basic Memory before substantial repo work by reading active tasks, open decisions, recent checkpoints, and repo conventions. Use when resuming old work or when the user asks where…

Plan and execute large refactor or rewrite efforts efficiently with parallel multi-agent analysis and implementation. Use when a user asks to refactor many files, split workstreams, analyze a target…

Generate a clean, conventional commit message from a description of your changes.

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms,…

Plan vault restructuring from config changes. Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval. Triggers on "/refactor",…

Initialize uc-taskmanager for the current project. Creates works/ directory and configures Bash permissions in .claude/settings.local.json. Use when the user says "uctm init", "initialize uctm", "uctm…

CTF Web攻击知识库 — PHP弱比较绕过、命令注入空格绕过、eval回显技巧、SSTI注入链、反序列化利用链、PHP代码审计checklist、常见flag位置

Three.js materials - PBR, basic, phong, shader materials, material properties. Use when styling meshes, working with textures, creating custom shaders, or optimizing material performance.