8.4K skills · sorted by relevance
Agent Ready project design context for navigation, docs links, and interface tone. Use when building or reviewing UI in this repo so patterns match the documented product feel.
The English summary is being prepared. Showing the original description.
Use when adding or repairing Spark regression tests for asynchronous ownership, cancellation, persistence, restart recovery, or cross-surface projections. Not a coverage campaign, performance benchmark, source-text policy check, or full delivery review.
The English summary is being prepared. Showing the original description.
Generates Strategy pattern for PHP 8.5. Creates interchangeable algorithm families with context class, strategy interface, and concrete implementations. Includes unit tests.
The English summary is being prepared. Showing the original description.
Generates State pattern for PHP 8.5. Creates state machines with context, state interface, and concrete states for behavior changes. Includes unit tests.
The English summary is being prepared. Showing the original description.
Generates PSR-3 Logger implementation for PHP 8.5. Creates LoggerInterface implementations with log levels, context interpolation, and LoggerAwareTrait usage. Includes unit tests.
The English summary is being prepared. Showing the original description.
Generates Architecture Decision Records (ADR) for PHP projects. Creates structured decision documentation with context, decision, and consequences.
The English summary is being prepared. Showing the original description.
Generates DDD Anti-Corruption Layer for PHP 8.5. Creates translation layer between bounded contexts or external systems. Includes adapters, translators, facades, and unit tests.
The English summary is being prepared. Showing the original description.
Analyze context and decide on continuation via Stop hook. Use when determining if work should continue, analyzing completion status, making continuation decisions, or implementing the Two-Claude pattern.
The English summary is being prepared. Showing the original description.
Create handoff packages for session transitions. Use when ending sessions, preparing for continuation, saving session state, or creating resumable context.
The English summary is being prepared. Showing the original description.
When the user needs to integrate multiple data sources (Canvas API, user memory, file systems) to create comprehensive academic reports. This skill combines course information, assignment details, submission status, and user context to generate actionable insights. Triggers include requests that involve cross-referencing multiple data sources or creating consolidated academic reports from disparate systems.
The English summary is being prepared. Showing the original description.
Integration patterns for combining Agent-to-Agent (A2A) Protocol with Model Context Protocol (MCP) for hybrid agent communication. Use when building systems that need both agent-to-agent communication and agent-to-tool integration, implementing composite architectures, or when user mentions A2A+MCP integration, hybrid protocols, or multi-agent tool access.
The English summary is being prepared. Showing the original description.
Third step in building instruction context for codebase
The English summary is being prepared. Showing the original description.
4claw — a moderated imageboard for AI agents. Boards, threads, replies, media uploads, bumping (bump=false to not bump), greentext, and automatic capacity purges. Post spicy hot takes (what you're REALLY thinking) — but no illegal content, doxxing, harassment, or minors.
The English summary is being prepared. Showing the original description.
Fourth step in building instruction context for codebase
The English summary is being prepared. Showing the original description.
Fifth step in building instruction context for codebase
The English summary is being prepared. Showing the original description.
Accessibility audit for CSS covering focus styles, color contrast, text sizing, screen reader support, and WCAG compliance. Provides actionable fixes. Use when auditing accessibility or fixing a11y issues.
The English summary is being prepared. Showing the original description.
Adds accessibility annotations (ARIA labels, roles, alt text) to make web content accessible. Use when user asks to "add accessibility", "make accessible", "add aria labels", "wcag compliance", or "screen reader support".
The English summary is being prepared. Showing the original description.
ALWAYS use this skill when user needs ANY API functionality (AI models, image generation, video, audio, text processing, etc.). Automatically search 302.AI's 1400+ APIs and generate integration code. Use proactively whenever APIs or AI capabilities are mentioned.
The English summary is being prepared. Showing the original description.
Final step in building instruction context for codebase
The English summary is being prepared. Showing the original description.
[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, need real-world precedents, confidence <75%, or require reasoning from specialized AI models.
The English summary is being prepared. Showing the original description.
[22] UNDERSTAND. Deep research from all sources — internal (code, git, logs) AND external (web, docs, best practices). Use when choosing libraries, investigating solutions, understanding legal/technical questions, comparing approaches, or anytime you need comprehensive knowledge from both project context and world knowledge. Triggers on "research", "investigate", "find best approach", "what do others do", "compare options", or complex questions requiring multiple sources.
The English summary is being prepared. Showing the original description.
Second step in building instruction context for codebase
The English summary is being prepared. Showing the original description.
在每次回复中使用固定前缀并列出本次实际参考的指令/文件，便于校验是否遵循上下文与规则。
The English summary is being prepared. Showing the original description.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".
The English summary is being prepared. Showing the original description.