发现 Skills

Guide and tooling for Ralph Driven Development (RDD), a spec runner that repeatedly invokes Codex (or other agents) over ordered specs until a magic phrase signals completion. Use when setting up or operating an RDD workflow with plan.md, specs/, done.md, agent-run.log, and a ralph.py runner, or when customizing the runner CLI and prompt contract.

Produce a mobile feature spec — user story, technical approach, component breakdown, platform-specific considerations, edge cases. Use when asked to 'add a screen', 'spec this feature', 'mobile feature', 'new tab', 'push notifications', or 'deep link'.

Use when the user EXPLICITLY requests "custom integration", "custom component", "Python for HA", "HACS", or "config_flow". Not for: YAML automations (use the home-assistant skill), Node-RED flows (use the node-red skill), or ESPHome device configurations (use the esphome skill).

Role-based social media operations skill. Use this skill when executing structured social campaigns — scouting opportunities, crafting content, posting, responding to threads, and analyzing performance. Designed for Moltbook engagement but adaptable to any platform and persona. Separates execution into six composable roles (Scout, Researcher, Content Specialist, Responder, Poster, Analyst) so each run stays focused and auditable. Activate this skill for any social ops task: opportunity detection, content pipeline management, community engagement, or performance review.

Systematic methodology for reading and understanding large codebases efficiently. Use when (1) understanding a new or unfamiliar codebase quickly, (2) preparing to modify or extend existing code safely, (3) debugging complex issues requiring deep code understanding, (4) onboarding new team members to a codebase, (5) performing code audits or security reviews, (6) refactoring legacy code with confidence, (7) creating documentation for existing systems, (8) tracing execution flows and data transformations.

A generic requirement/problem clarification workflow. Use when a user/client request is ambiguous, underspecified, or hard to execute/verify. The skill reframes the request, defines scope, constraints, inputs, and acceptance criteria, then outputs a concise one-page definition and a minimal question set to close gaps. Suitable for product/feature requests, content requests, ops tasks, research asks, and decision-making prompts.

brainbaseにおけるGitコミットのルールとフォーマット。コミットメッセージの書き方、type一覧、自動提案タイミングを定義。コミット作成時に使用。

Creates durable, resumable workflows using Vercel's Workflow DevKit. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of 'workflow', 'durable functions', 'resumable', 'workflow devkit', or step-based orchestration.

Template skill for repository authors; excluded from public publishing.

Read, compose, search, and organize emails in Apple Mail.app on macOS. Use for checking inbox, drafting messages, managing mailboxes, or automating email workflows. Triggers on queries about email, mail, inbox, drafts, or contacting someone via email.

通用代码审查和代码优化指南，包含代码规范、架构设计原则和最佳实践

Update project documentation after code changes. This skill should be used when significant changes have been made to features, APIs, infrastructure, database schema, or architecture. Triggers on: "update docs", "sync documentation", "docs are stale", "documentation is outdated", or when Claude detects code changes not yet reflected in docs/.

Apply when deciding whether and how VTEX IO apps should use Master Data v2 for custom data. Covers entity boundaries, schema lifecycle, indexing strategy, and when Master Data is the right storage mechanism versus another data approach. Use for reviews, wishlists, forms, or other custom data modeling decisions in VTEX IO apps.

Apply when implementing localization and translated copy in VTEX IO apps. Covers the `messages` builder, `/messages/*.json`, `context.json`, frontend message usage, and how VTEX apps integrate with `vtex.messages` for runtime translation. Use for storefront, admin, or backend flows that should use VTEX IO message infrastructure instead of hardcoded strings.

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative Gemini review. Use when the user says "refine my approach", "help me refine the plan", "decompose this problem", "polish my idea", "refine research plan", "detail the research plan", or wants a concrete research method that stays simple, focused, and ready for top venues instead of a vague or overbuilt idea.

Evaluate CEOs and companies using Thorndike's Outsider framework. Trigger on: "Is this CEO a good capital allocator?", "How should a company use excess cash?", "Should management buy back stock?", "Is this a well-run company?", "Evaluate this CEO's track record".

Code writing and automation. Triggers: code, script, tool, automate, batch, crawler, API, programming, automation

Create, modify, and optimize n8n workflows using nodes, connections, and configurations. Use this when working with n8n automations, referring to workflows, or needing to integrate services.

Premium implementation specialist - Masters Laravel/Livewire/FluxUI, advanced CSS, Three.js integration

Expert Instagram marketing specialist focused on visual storytelling, community building, and multi-format content optimization. Masters aesthetic development and drives meaningful engagement.

A Dianping (大众点评) number-taking skill for Chinese users. It parses the number-taking page, reads the count of queued tables in one pass, takes a queue number following a real browser flow, and — when the agent is periodically awakened — takes a number or sends a departure reminder based on user thresholds.

AI dress remover — erase a dress and replace with a bikini while keeping body proportions

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple agents to investigate and fix independent problems concurrently

Use when refactoring code - test-preserving transformations in small steps, running tests between each change