Loading...
Loading...
Found 3,379 Skills
Request interactive code review from users using the agent-review CLI tool. Automatically captures user feedback on code changes.
Expert prompt optimization for LLMs and AI systems. Use when building AI features, improving agent performance, crafting system prompts, or optimizing LLM interactions. Masters prompt patterns and techniques.
Use when designing futuristic agentic workflows, when wanting AI to proactively act on team communications, or when eliminating the bottleneck of formal specifications
Ensure that all responses from the Agent in this project are in Chinese. When users have any conversations, code explanations, error prompts, or documentations with the Agent, the Agent should always respond in Chinese unless the user explicitly requests another language.
Create a durable handoff file that captures important conversation state for agent continuity. Use when the context window is getting full, when switching agents/sessions, when handing off work, or when asked to summarize progress without losing decisions, constraints, risks, and pending tasks.
Multi-agent feature implementation. Spawns independent solver agents that each implement the feature from scratch, then synthesizes the best elements from each. Use when building complex features where you want diverse approaches and comprehensive edge case coverage.
Browser automation for AI agents. Use when the user needs to navigate websites, read page content, fill forms, click elements, take screenshots, or manage browser tabs.
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Comprehensive Agentforce testing skill with dual-track workflow: multi-turn API testing (primary) and CLI Testing Center (secondary). Execute multi-turn conversations via Agent Runtime API, run single-utterance tests via sf CLI, analyze topic/action/context coverage, and automatically fix failing agents with 100-point scoring across 7 categories.
Use when the user wants to list, search, install, remove, inspect, validate, audit, or update skills. Use when asking "what skills do I have", "is there a skill for X", "check my skills for issues", or "install a skill". Also use when checking skill health across agents (Claude Code, Codex, Agents CLI).
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
Executes DAG waves with controlled parallelism using the Task tool. Manages concurrent agent spawning, resource limits, and execution coordination. Activate on 'execute dag', 'parallel execution', 'concurrent tasks', 'run workflow', 'spawn agents'. NOT for scheduling (use dag-task-scheduler) or building DAGs (use dag-graph-builder).