tavily-dynamic-search
Run programmatic Tavily search and extraction while filtering raw results outside the main agent context. Use for multi-step or high-volume research where…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Agents & models
25,520 results
n8n-mcp-tools-expert
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or…
reasonhub-snomed-semantic
Use SNOMED CT's semantic attribute relationships to answer clinical questions. Finds concepts by relationship attribute (finding site, causative agent,…
manpower
AI prompting skill level measurement and growth analysis. Analyzes user prompts from Claude Code session logs to calculate scores on 8 competency axes, and visualizes them with a radar chart and weekly growth trends. Triggers: /manpower, AI skill measurement, prompt analysis, AI competency, skill level,…
prompt-engineering
Use when you need to design effective LLM prompts. Intelligently selects optimal prompting methods (Chain of Thought, Few-Shot, Zero-Shot, ReAct, Tree of…
tinkering
Safe experimentation framework for AI agents. Creates isolated sandbox environments for trying new features, testing approaches, and exploring solutions…
rlm-cleanup-agent
Removes stale and orphaned entries from the RLM Summary Ledger. Use after files are deleted, renamed, or moved to keep the ledger in sync with the…
rlm-distill-agent
Distills uncached files into the Recursive Language Model(RLM) Summary cache Ledger. You (the agent) ARE the distillation engine. Read each file deeply, write…
create-skill
Guide for creating well-structured Claude Code skills with proper YAML frontmatter, focused descriptions, and supporting files. Use when the user wants to create a new skill, build a custom skill, extend Claude's capabilities, or mentions creating/designing/building skills.
gpt
Call GPT generation and OpenAI text embedding models through RunAPI using OpenAI-compatible clients. Use for chat, Responses, embeddings, streaming, tools,…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
excel-mcp
Excel MCP Server skill for Windows workbook automation. Use when an assistant needs rich MCP tools to create, inspect, modify, format, or analyze Excel files.…
excel-mcp-report-formatting
Apply optional presentation conventions when the user requests Excel report formatting or a new reader-facing report through Excel MCP tools. Use for readable…
promptlens
Scan local Codex, Claude Code, OpenCode, OpenClaw, Hermes Agent, or other JSONL/JSON AI tool histories and generate a Chinese/English word cloud of the user's…
setup-opencli
Set up OpenCLI on a new machine — let an AI agent control the user's everyday Chrome (with login state) through a Chrome extension bridge. Covers prerequisite checks, installing the CLI via npm, guiding the Chrome extension installation, opencli doctor verification, smoke testing, and common troubleshooting (extension Reconnecting, daemon…
atlas-contract
Goal-integrity skill. Use for backend/API/persistence, preserve/do-not-change, tests/validation, mocks, rework, multi-part requests. Emits Goal Contracts,…
coherence-engine
The LLM as consistency maintainer and orchestrator
needs
Dynamic motivations (Sims-style) — needs fluctuate and drive behavior
schema-mechanism
Drescher's computational theory of causal learning
scoring
Motto: Style counts. Context matters. Story trumps numbers.
simulation
Abstract base for runtime state — adventure, city-sim, ecosystem all inherit from this
hebrew-llm-eval-suite
Benchmark and compare LLMs on Hebrew reasoning, comprehension, sentiment, translation, and Israeli cultural knowledge. Wraps the HuggingFace Open Hebrew LLM…
check-agent-access
Audits all (or selected) Cortex Agents in a Snowflake account. For each agent the skill reads the live specification, extracts every dependency (semantic…
executing-plans
Structured approach for implementing architect-provided plans through controlled batch execution with review checkpoints - execute in batches (default 3…