deepgram-js-conversational-stt
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-23 00:13
Agents & models
24,561 results
duan-yongping-perspective
Duan Yongping's (Dadao) thinking operating system. Based on in-depth research of the Xueqiu Q&A records (investment logic volume + business logic volume), NetEase blog collection, public interviews and decision records, distilling 6 core mental models, 9 decision heuristics and a complete expression DNA. Purpose: As an investment and business thinking advisor, use Duan Yongping's perspective to analyze problems, examine decisions, and provide feedback. When the user mentions "from Duan Yongping's perspective", "how would Duan Yongping see it", "Dadao mode", "Du…
wezterm
Manage WezTerm mux servers for AI agent swarms on high-RAM servers (512GB+). Use when wezterm mux unresponsive, agent sessions need rescue, tuning scrollback,…
elirox_bot_manager
Elirox bot manager — connect an Elirox account and launch, stop, or manage CFD trading robots. Use when the user mentions Elirox, robots, bots, trading,…
fix-llm-artifacts
Applies fixes from a prior review-llm-artifacts run, with safe/risky classification. Respects verify-llm-artifacts output when present to skip false positives.
dspy-prompting
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular…
mcp-development
Use when building "MCP server", "Model Context Protocol", creating "Claude tools", "MCP tools", or asking about "FastMCP", "MCP SDK", "tool development for…
multimodal-models
Use when "CLIP", "Whisper", "Stable Diffusion", "SDXL", "speech-to-text", "text-to-image", "image generation", "transcription", "zero-shot classification",…
oma-coordination
Coordinate assigned specialist tasks and handoffs manually. Use when supervising a multi-agent project step by step.
fstack
The fstack front door. Invoke /fstack alone to list every skill, or with a task to route it to the right one.
icp-prompt-builder
Interactive loop that builds and tunes an AI prompt for evaluating whether a company fits a client's ICP. Run after any list-building skill (disco-like,…
account-tiering
Use when defining ABM tiers, scoring logic, and coverage rules.
repo-map
Scan or query repository assets, relationships, coverage, and drift; not routine task-local file discovery.
kairos
KAIROS action routing skill for structured workflow execution. When loaded and a KAIROS MCP server is connected, this skill routes action intents through the…
china-lbo-model
Leveraged buyout model for A-share and China-market LBO scenarios. Adapts the standard LBO-model methodology for Chinese debt markets, CAS accounting, and…
china-skill-creator
Create new China-specific financial skills following the established patterns and conventions. Use this meta-skill to scaffold new china-* skills that…
web-browsing
Web research with automatic fallback mechanism. WebFetch → Browser MCP → User assistance via ai_interaction. Use when need to browse web.
track-tariff-trends
Retrieve a country's average applied tariff over time — the MFN rate on all products, or the rate it applies on goods from one partner and/or in one product…
chunking-strategies
Optimize document chunking for RAG performance and retrieval quality. Use this skill when splitting documents, choosing chunk sizes, implementing semantic…
latitude-telemetry
Add or review Latitude Telemetry for LLM apps and agent harnesses. Use for Latitude tracing, LLM observability, missing traces, OpenTelemetry/OTLP integration…
custom-agent-definitions
Write and configure custom agent definitions in Claude Code agents/ directory. Use when creating an agent .md file, defining a specialized agent, or…
health-check
Claude Code health check — scans plugins, settings, hooks, MCP, runtime state, usage telemetry, permissions, marketplace with optional fixes. Use when checking…
earshot
Listen with earshot whenever you must judge, choose, trim, verify or compare sound you cannot hear - picking a sound effect, music or ambience from candidates,…
messaging-agents
Send messages to other agents on your server. Use when you need to communicate with, query, or delegate tasks to another agent.