提示词

提示词工程与模板

显示 313-336 / 共 4537 个技能
Orchestra-Research

sglang

Orchestra-Research

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

数据处理 1.2万 9个月前
Orchestra-Research

awq-quantization

Orchestra-Research

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

MLOps 1.2万 9个月前
Orchestra-Research

fine-tuning-with-trl

Orchestra-Research

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

CI/CD 1.2万 9个月前
Orchestra-Research

nanogpt

Orchestra-Research

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

数据处理 1.2万 9个月前
Orchestra-Research

gguf-quantization

Orchestra-Research

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

CLI 工具 1.2万 9个月前
Orchestra-Research

rwkv-architecture

Orchestra-Research

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

MLOps 1.2万 9个月前
getsentry

prompt-optimizer

getsentry

Create, optimize, and iteratively refine agent prompts and system prompts. Use when asked to "improve a prompt", "optimize a system prompt", "rewrite an agent prompt", "tune prompt wording", "make this prompt more reliable", or "adapt a prompt for OpenAI, Claude, or Gemini". Handles model-specific prompt guidance, prompt markers/tags, eval design, and meta optimization loops for new and existing prompts.

代码生成 954 4个月前
tursodatabase

index-knowledge

tursodatabase

Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation.

自动化 2.4万 7个月前
snyk

doc-coauthoring

snyk

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

代码生成 2958 7个月前
snyk

skill-creator

snyk

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

代码生成 2958 7个月前
glebis

agency-docs-updater

glebis

End-to-end pipeline for publishing Claude Code lab meetings. Automatically finds/creates Fathom transcript, downloads video, uploads to YouTube, generates fact-checked Russian summary, creates MDX documentation, and pushes to agency-docs for Vercel deployment. Single invocation replaces 5+ manual steps.

CLI 工具 363 7个月前
majiayu000

claude-ecosystem

majiayu000

"Claude Code ecosystem expertise. Modules: CLI tool (setup, slash commands, MCP servers, hooks, plugins, CI/CD), extensibility (agents, skills, output styles creation), CLAUDE.md (project instructions, optimization). Actions: configure, troubleshoot, create, deploy, integrate, optimize Claude Code. Keywords: Claude Code, Anthropic, CLI tool, slash command, MCP server, Agent Skill, hook, plugin, CI/CD, enterprise, CLAUDE.md, agentic coding, agent, skill, output-style, SKILL.md, subagent, Task tool, project instructions, token optimization. Use when: learning Claude Code features, configuring settings, creating skills/agents/hooks, setting up MCP servers, troubleshooting issues, CI/CD integration, initializing or optimizing CLAUDE.md files."

智能体 580 7个月前
majiayu000

Build Your Google ADK Skill

majiayu000

"Create your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chapter"

智能体 580 7个月前
majiayu000

prompt-architect

majiayu000

"Create and enhance prompts, system instructions, and principle files. Capabilities: transform verbose prompts, add patterns/heuristics, optimize token usage, structure CLAUDE.md principles, improve agent/persona definitions, apply prompt engineering techniques (CoT, few-shot, ReAct). Actions: create, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, system prompt, CLAUDE.md, principle files, instruction optimization, agent prompt, persona prompt, token efficiency, prompt structure, workflow prompts, rules, constraints, few-shot, chain-of-thought, soul, tensions, dialectic. Use when: creating new prompts, enhancing principle files, improving system instructions, optimizing CLAUDE.md, restructuring verbose prompts, adding patterns to workflows, defining agent behaviors."

智能体 580 7个月前
majiayu000

claude-ecosystem-promoter

majiayu000

Marketing and promotion specialist for Claude ecosystem technology - MCP servers, skills, plugins, and agents. Expert in community engagement, registry submissions, content marketing, and developer relations. Activate on 'promote MCP', 'share skill', 'market plugin', 'launch agent', 'developer marketing', 'MCP registry'. NOT for creating MCPs/skills (use agent-creator), general marketing (use content-marketer), or SEO optimization (use seo-visibility-expert).

Git 与版本控制 580 7个月前
majiayu000

Build Your Pipecat Skill

majiayu000

"Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter"

CI/CD 580 7个月前
majiayu000

Build Your Pipecat Skill

majiayu000

"Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter"

CI/CD 580 7个月前
majiayu000

Build Your LiveKit Agents Skill

majiayu000

"Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter"

智能体 580 7个月前
majiayu000

model-selection

majiayu000

Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.

MLOps 580 7个月前
majiayu000

claude-skill-registry

majiayu000

The most comprehensive Claude Code skills registry Web Search: https://skills-registry-web.vercel.app

CLI 工具 580 6个月前
majiayu000

Build Your Google ADK Skill

majiayu000

"Create your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chapter"

智能体 580 7个月前
majiayu000

model-selection

majiayu000

Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.

MLOps 580 7个月前
mitsuhiko

tmux

mitsuhiko

"Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output."

认证鉴权 2939 8个月前
CharlesWiltgen

axiom-foundation-models-diag

CharlesWiltgen

Use when debugging Foundation Models issues — context exceeded, guardrail violations, slow generation, availability problems, unsupported language, or unexpected output. Systematic diagnostics with production crisis defense.

认证鉴权 1139 7个月前