migrate-max-v2-to-v3
Use when migrating a MAX model from the V2 graph API (max.nn, TensorValue, explicit Graph construction) to ModuleV3 (max.experimental.nn, Tensor, F.lazy() +…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-20 00:13
Agents & models
24,176 results
agentic-data-scientist
Adaptive multi-agent framework for automated data science tasks with planning, execution, and validation
claude-md-architect
CLAUDE.md file generation and optimization for Claude Code projects. Capabilities: initialize project instructions, analyze codebase context, optimize existing…
justin-sun-perspective
Justin Sun's thinking framework and way of expression. Based on 21,829 tweets (14,418 EN + 7,411 ZH), 1 autobiography "This World Is Both Cruel and Tender," 155-episode audio course "The Road to Financial Freedom Revolution" (~18 hours), 40+ in-depth interviews and investigative reports, 2 core long-form Chinese interviews (Huazong 86 minutes + LatePost 76 minutes), 2 English in-depth podcasts (Bankless...
agent-advisor
Unified entry point for AI-agent work on AWS: evaluate and pick a runtime, generate a full migration plan (for existing workloads), and build an executable POC…
X Chat
Read, summarize, or send encrypted X Chat (XChat) DMs via the X plugin MCP plus local chatxdk / xchat_lite.py. Use when the user mentions X Chat, xchat,…
omni-ai-optimizer
Optimize your Omni Analytics model for Blobby, the Omni Agent — configure ai_context, ai_fields, synonyms, sample_queries, and AI-specific topic extensions.…
laohan-skillcreator
Create, audit, fix, and optimize Agent Skills. Use when the user wants to create a new Skill, check Skill quality, restore the original version or correct clear errors, compare old and new results, or update the upstream methods this Skill draws on. Trigger words: "create skill" "write a skill" "modify skill" "optimize skill" "score a skill" "skill checkup" "revi…
secrets-manager
AWS Secrets Manager for secure secret storage and rotation. Use when storing credentials, configuring automatic rotation, managing secret versions, retrieving…
azure-data-share
Expert knowledge for Azure Data Share development including troubleshooting, decision making, security, configuration, and deployment. Use when estimating Data…
ralph-loop
Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover…
hermes-labyrinth-observability
Hermes Labyrinth observability plugin for monitoring autonomous agent journeys, crossings, and execution traces
dual-stacking
Dual Stacking enrollment operations on Stacks — earn BTC-denominated rewards (paid in sBTC) by holding sBTC. Check enrollment status and APR data, enroll with…
erc8004
ERC-8004 identity, reputation, and validation — register identities, retrieve identity info by agent ID, query reputation scores, submit peer feedback, and…
opportunity-tool-selection
Decide which tool mode to use for opportunity workflows: normal web search, browser automation, MCP/API access, local files, or chat-only reasoning.
wangjianshuo-perspective
Wang Jianshuo's thinking framework and expression style. Based on 7 in-depth research studies (approximately 1 million words of English blogs + approximately 1.09 million Chinese characters of Chinese blogs, 2002–2022, all primary sources), 7 core mental models, 10 decision-making heuristics, and a complete bilingual expression…
wjs-promoting-skills
Use when the user wants to set up automated daily promotion / marketing for their Claude Code skills — researching how top skills are promoted on marketplaces…
caveman
Compress and simplify prompts to preserve meaning while reducing use of context
ln-840-benchmark-compare
Use when benchmarking hex-line MCP against Claude built-in tools with scenario manifests, activation checks, and diff-based correctness.
skill-load-tips
Diagnoses and refactors existing SKILL.md files whose references or assets are ignored by agents. Applies Required Reading Routers, hard STOP directives,…
plan-implementation
Execute detailed implementation plans systematically. Breaks down planned tasks into actionable steps with progress tracking and milestone management.
hermes-agent-guide
Comprehensive Chinese guide for Hermes Agent framework covering installation, architecture, memory systems, skills, tools, multi-agent orchestration, and…
tuzi-update-claude-md
Analyze issues found in code review feedback or during development, extract general rules, and update CLAUDE.md and the detailed rules documentation. Use when the user says "update rules", "add coding rules", "update claude md", or when a coding pattern that needs to be recorded is discovered.
openclaw
Comprehensive guide for installing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI agent gateway. Use when the user…