Total 57,200 skills, AI & Machine Learning has 9514 skills
Showing 12 of 9514 skills
Use when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.
AI token price comparison platform that scrapes and aggregates prices across multiple platforms to help users find cheap, reliable AI account tokens
Representation expert who defeats systemic AI biases to generate culturally accurate, affirming, and non-stereotypical images and video.
Investigate LLM analytics clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
Harness Engineering Phase 3: Establish cross-session state management to solve the problem of agents forgetting previous conversations. Create three files: tasks.json (task list), progress.md (progress record), and init.sh (environment initialization script). Use this skill immediately when the user says phrases like "establish task management", "make agent remember progress", "create tasks.json", "maintain state across sessions", "agent doesn't remember what was done last time", "create progress file", or "initialize state management". Prerequisites: harness-step1 and harness-step2 have been completed (the project has AGENTS.md and docs/ knowledge base).
Guide first-time Starchild users through onboarding with assistant/intern positioning, quick wins, discovery questions, and game-style feedback. Use for fresh sessions, vague starts, what-can-you-do questions, or users who don't know where to begin.
Multi-perspective adversarial review. 4 Agents are spawned in parallel (full mode), each identifying issues from different perspectives, and the main thread makes a comprehensive ruling. Trigger methods: /story-review, /审查, "审查一下", "帮我审一下"
Autonomous SDLC router. Takes a job, classifies complexity, executes the appropriate lev-* workflow (from trivial fix to full epic), and returns "done" with runnable instructions. One shot to full auto: spec/bd/poc/impl. Subagent returns completion artifact. Triggers: "sidequest", "side quest", "just do it", "autonomous", "one shot"
This skill should be used when the user asks to "upscale an image", "increase image resolution", "make image bigger", "enlarge image", or "enhance image resolution". Requires Vertex AI credentials.
Use this skill when you are not sure about a fact, have outdated knowledge, or the question is contested. Explicitly communicate the level of confidence instead of asserting uncertain things as fact.
Conducts a guided conversational interview with the user about the image or scene they want to create, asking pertinent questions to fully understand their vision, then synthesizes a perfect model-appropriate prompt with recommended settings. Use when the user says "I want to create...", "help me make an image of...", "I have an idea for...", or asks for help crafting a prompt.