model-pruning
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50%…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-28 00:17
Agents & models
24,968 results
moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense…
speculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6×…
dcf-valuation
Activate this skill when the user is assessing whether a stock is "cheap," agonizing over whether to make buy or sell decisions based on PE/PB, or trying to precisely calculate a company's value using the DCF formula. Core judgment signals: the user mentions "valuation," "how many times PE," "DCF model," "calculate how much it's worth," or is agonizing over "can I buy at this price." This skill restores valuation from mathematical calculation to business judgment—using "discounting future cash flows" as a way of thinking rather than...
awesome-skills-purge
Removes installed agent skills from every AI agent on the machine (Claude Code, Codex, Gemini CLI, Cursor...) behind a keep list, an archive and a confirmation…
stock-info-explorer
A Yahoo Finance (yfinance) powered financial analysis tool. Get real-time quotes, generate high-resolution charts with moving averages + indicators…
project-manager
Agent team role for project delivery management using PRINCE2 principles. Use when the user asks to plan project stages, manage risks, track progress, write…
mcp-code-execution
Scaffold the code execution pattern for MCP-based agents. Use when agents call many MCP tools, intermediate data exceeds context, you need loops, or PII must…
mcp-management
Install and configure MCP servers for Claude Code. Use when adding/enabling servers, updating .mcp.json, managing OAuth remote servers, or troubleshooting…
unbrowse
Attributed purpose/status summary: Two complete third-party records link the exact lekt9/unbrowse-openclaw repository. One describes the plugin connecting Unbrowse CLI to OpenClaw;the other documents Unbrowse website-to-API and structured-data extraction. Only the common web-data integration purpose is summarized,distinguishing plugin and underlying CLI. The old Skill,plugin command and CLI install mapping remain unverified;automatic execution,authentication handling and performance statements are not treated as test results.
compaction-prompts
Configures Letta agent compaction settings and custom summarization prompts. Use when a user asks to change an agent's compaction prompt, improve summaries…
protolink
In the AI assistant within the IDE, help users directly complete ProtoLink project preview, iterative preview, viewing local iterations, creating/updating/publishing iterations, obtaining online links, publishing configuration diagnostics, and the ProtoLink CLI / Skill suite…
cc-notebooklm
Claude Code connects to NotebookLM MCP. Loads when you say "connect NotebookLM".
style-guide
Analyze a codebase to extract its conventions, patterns, and style. Spawns specialized analyzer agents that each focus on one aspect (structure, naming,…
mint-api
Integrate Mint's production API into applications and agent workflows. Use for Mint API authentication, service-specific generation, operation polling, Preview…
aeo-optimizer
Optimize an article for Answer Engine Optimization (AEO) so AI engines like ChatGPT, Perplexity, and Claude can extract, quote, and cite it. Use when asked to…
partner-skill-name
Describe what this skill does and when an AI agent should use it. Be specific — this field determines whether Claude loads this skill. Bad: "Analytics tool for…
configuring-zsh
Configure and troubleshoot Zsh shell. Use when editing .zshenv, .zprofile, .zshrc, .zlogin, or .zlogout, setting up powerlevel10k prompt, configuring oh-my-zsh…
confidence
Rates confidence that the current work fully solves the stated requirement. Supports plan validation, code review, and analysis (root-cause, refactor,…
component-audit
Deep audit of a component library: inventory, usage, duplication, complexity, coverage gaps. Triggers: audit my components, unused components, what components…
pp-doordash
Printing Press CLI for Doordash. DoorDash GraphQL operation spec curated from sniffed traffic and ashah360/doordash-mcp query files. This...
case-justification
Draft case justification sections for interview-based sociology articles. Guides cluster selection, component coverage, and calibration based on analysis of 32…
methods-writer
Draft publication-ready Methods sections for interview-based sociology articles. Guides pathway selection, component coverage, and calibration based on…
agent-harness
Use when making a repo agent-ready, verifying harness consistency, checking for documentation drift, bootstrapping harness infrastructure (AGENTS.md as index,…