发现 Skills

复杂前端 Artifacts 构建工具

视觉设计与艺术创作工具

Makes your writing clearer, stronger, and more professional. Use this skill when the user says "write clearly", "clear writing", "improve writing" or for ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text.

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 dimensions before it enters the main branch.

Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Manage LocalStack Extensions. Use when users want to install, uninstall, list, or configure LocalStack extensions, or develop custom extensions to extend LocalStack functionality.

Manage LocalStack state and snapshots. Use when users want to save, load, export, or import LocalStack state, work with Cloud Pods, create local snapshots, or enable persistence across restarts.

Vroid Studio, VRM format, and VTuber avatar creation

Action definitions and keyboard shortcuts in GPUI. Use when implementing actions, keyboard shortcuts, or key bindings.

Analyze code and generate an Excalidraw JSON diagram of the architecture.

Analyzes PR changes to create ReviewContext.md and DerivedSpec.md artifacts. Handles both initial analysis and resumption after baseline research.

Calculate investment position size using the Kelly formula. Use when a user asks about position sizing, capital allocation, position sizing or the Kelly formula. Supports full Kelly, fractional Kelly and portfolio/combination optimization.

Audit and automatically optimize a lovstudio skill against repo conventions and official Anthropic skill-creator best practices, then bump the semver version and append a CHANGELOG entry. Checks SKILL.md frontmatter/trigger quality, script CLI hygiene, directory naming, README badge, and progressive disclosure structure. Prioritizes issues raised in the current conversation (e.g. bugs the user just hit) over a generic sweep. Use when the user asks to "optimize", "refine", "audit", or "polish" an existing skill, or when they say "bump version", "update changelog", or "fix this skill". Also trigger when the user mentions "优化 skill", "skill 审计", "刷一遍 skill", "skill-optimizer", "bump skill version", "update skill changelog".

Unified skill for managing the entire PDCA cycle. Auto-triggered by keywords: pdca, plan, design, analyze, do, check, act, report, status, next, iterate, gap. Replaces legacy /pdca-* commands. Use proactively when the user mentions the PDCA cycle, planning, design documents, gap analysis, iteration, or completion reports. Do NOT use for simple queries without PDCA context or for code-only tasks.

Asking Claude to self-rate confidence (1-5), routing based on score, calibration prompts, and human-in-the-loop escalation patterns. Maps to CCA Domain 4/5.

Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually

All three files created. Here's what was generated:

Discover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.

Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use when auditing Algorand projects (TEAL/PyTeal).

Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit of success' principles. Triggers: footgun, misuse-resistant, secure defaults, API usability, dangerous configuration.

Use when the design phase is complete and needs to be handed off to the development team. The development handoff summary is generated automatically, consolidating page lists, route structure, functional requirements, and items pending confirmation to produce a developer-facing handoff document. Keywords: design handoff, design delivery, handoff, developer onboarding, delivery documentation.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Code quality auditing skill that runs real analysis tools in the sandbox. Use when: auditing a codebase for security vulnerabilities, checking dependency health, scanning for accessibility issues, measuring performance, running linters, or generating a comprehensive quality report for a project.

Manage tasks with priorities, due dates, tags, and meta using a CLI todo app backed by SQLite. Use when the user asks to create, list, complete, edit, delete, or organize tasks, or when they mention todos, task management, to-do lists, ideas to track, or "rabbithole".