truefoundry-prompts
Manages TrueFoundry Prompt Registry. Covers listing, creating, updating, versioning, tagging, and using prompts through the AI Gateway. Agent authoring belongs…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-31 00:15
Agents & models
25,344 results
prompt-engineering
Comprehensive prompting techniques including chain-of-thought, few-shot, zero-shot, system prompts, persona design, and evaluation patterns
architect
Narrow open-ended problems into locked design direction, then converge verified evidence into one approach or an explicit no-build verdict.
ai-python-basics
Use for AI SDK for Python basics. Configure a model, make messages, stream, declare tools, build a basic agent.
ai-python-streaming-tools
Use for AI SDK for Python async-generator tools, streaming tool output, subagent tools, PartialToolCallResult events, and custom tool aggregation.
arkcli-custommodel
arkcli custom model repository management: import custom models from TOS, query/filter custom models, view details, rename, delete, query available quantization modes, quantize ready models. Any management, deployment preparation that mentions a custom model ID (`cm-*`), or boundary determination requests to use `cm-*` for direct conversation/inference/testing effects must use this...
production-planner
Architecture planning for production systems — guides system design with scalability, reliability, security, and operational concerns from day one. Use this…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
add-feishu
Add Feishu (Lark) as a channel. Uses WebSocket long connection — no public URL or ngrok needed. Works alongside WhatsApp, Telegram, Slack, or as a standalone…
model-failover
Automatic LLM provider failover with fallback chains, inspired by OpenClaw/ZeroClaw model configuration.
fable-5-best-practice
Route Claude tiers, effort, and subagents for Fable-led work, and handle Fable-specific prompting, long-running execution, API behavior, refusals, and fallback.
hands-3d-pose
High-quality 3D hand pose estimation for egocentric videos from ECCV 2024 (ap229997/hands). Provides 3D joint keypoints and skeleton visualization projected to…
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified…
realtime_protocol_guidance_prompts
Generates short, imperative guidance prompts for the next experimental step from current video frame and protocol context. Output is optimized for voice…
transformers
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use…
skill-maker
Create and edit Claude Code skills with TDD methodology. Use when creating or editing skills. Test with subagents before deployment, iterate until bulletproof.
mindsdb-mcp-skill
MindsDB MCP server interaction skill, supporting natural language querying and operation of 200+ enterprise-level data sources. Core features include: 1) database connection and querying; 2) NL2SQL natural language to SQL; 3) RAG knowledge base construction and intelligent Q&A; 4) data analysis and visualization; 5) AI predictive model creation; 6)…
enhance-prompt
Use skill if you are enhancing a prompt before sending it to an LLM or coding agent — adds narrative structure, thinking-steering, failure pre-emption, halt…
optimize-agentic-mcp
Use skill if you are auditing an existing MCP server for agent-readiness, designing a new MCP server before any code, or deciding framework, security, and…
mcp-server-building
Building MCP (Model Context Protocol) servers for Claude extensibility. Use when creating MCP servers, building custom Claude tools, extending Claude with…
bash-ops
Defensive Bash scripting for production automation, CI scripts, and agent-facing tools. Triggers on: bash, shell script, defensive bash, bash strict mode, set…
cast-subagents
Use when suggesting exactly one Codex subagent lineup before work begins for multi-lane tasks: branch/PR review across bugs, security, tests, maintainability,…
elite-longterm-memory
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again.…