Browse 182,820 skills across 14 categories.
Atomic file update patterns to prevent corruption. Use proactively when writing to any shared file to prevent data loss...
Auxiliary script management rules for Ralph agents. Use proactively when creating helper scripts in .claude/session/.
Brand identity, design tokens, and anti-pattern philosophy shared across all platforms.
Cancel active Ralph loop
Generate CHANGELOG.md from conventional commits with semantic versioning.
Docker containerization patterns for Node.js/TypeScript development and production
Commit and push the user's shared Claude config to the `~/.claude-config` sync repo, rebasing first so a push never buri...
Context window auto-reset procedures for Ralph agents. Use when context fills up during long tasks.
Creates verified shared.md research context through plan-workflow. Use when gathering codebase context, preparing shared...
Context window auto-reset procedures for Ralph agents. Use when context approaches 70% capacity during long tasks. Use p...
Project-wide conventions and patterns that apply to all apps/modules. Use when: asking about project structure, coding s...
PM coordinator for both event-driven and single-agent orchestration modes
Core orchestration concepts - session structure, status values, heartbeat, commit format. Single source of truth for all...
Universal safety rules, workflow structure, and update priority for dependency management across all platforms.
分析电话号码与设备之间的共享关系，支持单号码共享设备扩散、两个号码是否共用设备、单设备挂载号码和设备池线索分析。适用于共享设备/同设备池问题；输出仅作为风险线索，不等同于最终团伙认定或可靠跨省同实体联动判断。
Clean up a shared drive nobody owns — the ownership-first move, the top-down audit that finds the 80% (stale projects, d...
Environment variable management with validation, documentation, and .env.example generation.
File read/write permissions for all Ralph agents. Use proactively when unsure about file ownership or write permissions.
Git for data science — versioning notebooks, datasets, and pipelines. DVC, nbstripout, .gitignore, and reproducible data...
Environment configuration, Zod validation
共享层与通信机制模块。当需要定义消息类型、添加共享常量、设计 Extension-Webview 通信协议时使用。涵盖类型定义、消息格式、双向通信模式等。
Shared libraries guidelines for Quantum Skincare's TypeScript shared code (types, validation, utils). Covers type defini...
Process lifecycle management and auxiliary script rules for Ralph agents
Reuse and maintain a shared literature library across research projects. Use before downloading or extracting papers, cr...
Message delivery and processing via bidirectional named pipes in Ralph V2 event-driven mode. Use when connecting agents...
File-based message queues for agent communication. Uses Glob/Read/Write tools - no PowerShell.
Code review patterns, feedback principles. Use when reviewing PRs, implementations, or making approval/rejection decisio...
Use when a duplication gate flags cloned component code — a jscpd failure, a qlty `similar-code` comment, or two compone...
Nx monorepo build system — workspace configuration, project graph, task pipelines, caching, generators, plugins, and rel...
A skill with a name that might conflict. Use for testing conflict detection.
Standard NFR concerns, output format, and flexibility rules shared across all platforms.
Reusable patterns and templates for skill and hook development.
Use when implementing shared connection pool for multiple services in same application - provides complete setup steps f...
Unified process lifecycle management for all Ralph agents. Use proactively when starting any background process (dev ser...
PM coordinator for single-agent orchestration mode - no polling, handoff-based
Single source of truth for Ralph Orchestra - event-driven architecture, status values, exit conditions. Use when referen...
Handoff protocol for single-agent orchestration mode
Single Ralph iteration with full visibility - learn before going AFK
Routes to appropriate Ralph skills based on agent role and task signals
Worker loop - execute tasks assigned by coordinator
Tech Artist worker loop - execute visual asset tasks assigned by coordinator
Generate comprehensive README.md with project overview, setup instructions, and usage documentation.
Task memory management and retrospective contributions for Ralph agents
Severity definitions, approval gate protocol, and fix constraints shared across all review and test skills.
Security output format, core refusal policy, and purpose statement shared across all platforms.
Shared configuration patterns for project setup commands. Provides security hooks, Claude framework structure templates,...
Manages shared ledgers for family or team collaboration, including shared account summaries, spending statistics, and me...
Coordinate a moving surface and its content with shared spring progress and a decaying relative offset. Use when content...
File ownership, atomic updates using Edit tool, concurrency rules for Ralph agents
End-to-end Xcode workflow for architecting, debugging, profiling, and shipping a shared SwiftUI app on iOS and macOS.
TDD policy — red-green-refactor workflow and evidence requirements for all platforms.
Biome v2 unified linter, formatter, and import organizer — single Rust-powered tool replacing ESLint + Prettier with 97%...
Operates a shared git working tree where many agents commit concurrently: commits by path with the task-id prefix, never...
Use only when explicitly requested with `$shared-understanding`, or through the full `github-issue-delivery` or `azure-d...
Type-check, lint, test, build validation sequence. Use proactively before every commit across all agents.
Base worker behavior for all Ralph agents - worker pool model, exit conditions, heartbeat. Extend for agent-specific beh...
Game Designer worker behavior - extends shared-worker with GDD-specific workflows
Worker pool architecture with ActorSupervisor spawning agents. Use proactively when implementing worker agent behavior o...
Retrospective contribution format for Developer, Tech Artist, QA, and Game Designer workers. Use proactively when retros...
Git worktree setup and management for parallel agent development. Use proactively when setting up parallel development b...
Git worktree practical examples for parallel agent development
Orchestrate parallel workflow documentation generation for all agents. Use proactively during PRD Starter Phase 11 to ge...
Git worktree setup and management for parallel agent development. Use when working in isolated git worktrees to avoid me...
Maintain a wiki-style world bible for collaborative fiction. Use for long-running story worlds, shared universes, member...
共有ラッパー（*Shared）と非共有本体（*）、Handle の使い分け、ArcShared+ToolboxMutex、SharedAccess/Clone の設計判断を扱う。共有の要否を判断し、shared_vs_handle ガイドに...
ShareFlow 项目全局上下文。执行任何 ShareFlow 开发任务前必须加载此 Skill，包含完整的架构规范、目录结构、编码约定和技术决策。
总结股东信中的长期战略、经营变化、资本配置与管理层信号。适用于长期跟踪优质公司、年度复盘、更新投资主线等场景。
查询A股上市公司股东大会信息（market.ft.tech）。用户问股东大会、股东会议、股权登记日、投票日期、会议提案时使用。
Build shared real-time experiences using GroupActivities and SharePlay. Use when implementing shared media playback, col...
Build, integrate, and troubleshoot SharePlay GroupActivities features, including GroupActivity definitions, activation f...
Read and write SharePoint sites, document libraries, files and lists through Microsoft Graph. Use when the user asks abo...
Guide and run a SharePoint audit locally. Collect inputs, confirm PowerShell 7.4+ and Python 3.10+ are available, call P...
Author HTML that renders in SharePoint's OneUp HTML viewer and publish it into the user's own OneDrive / SharePoint. Use...
Configure ShareX capture, recording, OCR, and custom uploader workflows with CLI or API integrations.
Manage sharing permissions (Attio-style) for tables, workflows and agents from the CLI. Use when the user asks to share...
Use when writing a Slack post that shares backend work with the wider dev team, backend peers, or the backend lead — an...
The user wants to share or hand off what was found in a video — "send this analysis to my team", "make a page I can shar...
Use when access must reach past the record owner's role hierarchy. Trigger keywords: sharing rule, criteria-based sharin...
Contribute skills back to upstream via branch and PR
Use when contributing skills back to the community. Follow git workflow: sync upstream → create branch → develop skill →...
User-invoked reverse-engineering + enhancement protocol for any source artifact: repos, codebases, docs, PDFs, screensho...
Pitch a business idea to a Shark Tank-style panel of Claude sub-agent investors who grill it, hear a founder agent answe...
SHARK v3.0 — SM Conviction + Liquidation Cascade Hunter. Consolidated from v1.0's 8-cron pipeline into a single scanner....
Task lifecycle management using the shark CLI for tracking implementation progress, status updates, and team visibility
高性能Node.js图片处理库。使用libvips最快速地调整JPEG、PNG、WebP、AVIF和TIFF图片大小。
Processes images with Sharp, the high-performance Node.js library for resizing, converting, and optimizing images. Use w...
Two-layer performance skill combining disciplined THINK layer (surgical edits, simplicity) and terse SPEAK layer (cavema...
Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when revie...
Identify error-prone APIs and dangerous configurations
Review APIs and configuration for dangerous defaults, misuse-prone interfaces, cryptographic footguns, and security clif...
sharp-edges
Living catalogue of 7 known hazard entries (SE-01 through SE-07) specific to agent-studio: Windows backslash paths, prot...
Identify dangerous API footguns, surprising default behaviors, and sharp edges in codebases and dependencies. Adapted fr...
Conventions for writing sharp, concise prose and Markdown, for human readers and AI agents. Read before writing or editi...
Sharpen a task before starting: the expert approach, what the user is really after, and the right level of specification...
Make a task deeper, not bigger, then rewrite the prompt. Use for /sharpen.
Use for /sharpen to clarify a task before work.
Rewrites the prompt typed after the command before any work starts, then works from the rewrite. Splits a mixed-up messa...