Total 50,652 skills, AI & Machine Learning has 8490 skills
Showing 12 of 8490 skills
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace URL (e.g. /llm-observability/traces/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs.
Curated documentation reference for developers building with Pinecone. Contains links to official docs organized by topic and data format references. Use when writing Pinecone code, looking up API parameters, or needing the correct format for vectors or records.
Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.
Use when context is growing large (50k+ tokens), performance is degrading, instructions are being ignored mid-conversation, or planning multi-agent workflows. Triggers on "lost context", forgotten instructions, or sessions exceeding 30 minutes.
Give an AI agent an encrypted inbox with the masumi-agent-messenger CLI. Use when agents need to message other agents, read durable inboxes, manage threads, coordinate async multi-agent workflows, request human approval, or automate inbox operations with JSON output.
Command-line interface for Novita AI - An OpenAI-compatible AI API client for DeepSeek, GLM, and other models.
Interactive CLI for Uni-Mol molecular property prediction training and inference workflows.
Full optimization workflow, sub-agent launch templates, agent communication contracts, default configurations, tuning strategy, and knowledge base update protocol. Use when: (1) starting an optimization cycle, (2) launching a Profiler or Designer sub-agent, (3) interpreting or formatting agent communication, (4) updating the knowledge base after a profiling or implementation iteration, (5) deciding default configurations or tuning strategy for a kernel.
Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "队列实验", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is insufficient for 10+ jobs that need orchestration.
Use this skill whenever users want to build, inspect, debug, automate, or publish workflows in Agentforce Grid (AI Workbench) using Salesforce plus the Grid MCP or direct Grid REST calls. Trigger it for Grid workbook creation, worksheet setup, Object/Reference/AI/Agent/AgentTest/Evaluation/PromptTemplate/InvocableAction column design, prompt drafting inside Grid, worksheet execution troubleshooting, Grid YAML `apply_grid` specs, and Windows-specific Grid setup issues. Also use it when users mention AI Workbench, Grid Studio, workbook IDs, worksheet IDs, Grid Connect, or ask for recipes like "top opportunities with AI email drafts", "agent test suite in Grid", or "build this worksheet from YAML". Do not use it for generic Salesforce work unrelated to Agentforce Grid.
Internal conversation-entry router for Claude Code. Performs a lightweight intake pass at the start of substantive work: decide whether a more specific skill should be invoked first, whether specialized agent delegation is warranted, how much context is actually needed, and whether the task needs planning or can proceed directly. Not a user-facing slash command.