1Password CLI
Practical secret access layer for agents and scripts that need secure credential injection without hardcoding.
Skills
The supporting stack is often what determines whether a model is usable in real work. This directory makes that layer easier to compare.
Normalized skill registry
Official sources, install method, deployment model, permission posture, provider support, and works-with relationships are first-class fields so this can evolve into a real registry and routing layer later.
| Name | Best for | Works with | Install method | Trust signals | View details |
|---|---|---|---|---|---|
1Password CLI Secrets · security Score 88 Practical secret access layer for agents and scripts that need secure credential injection without hardcoding. | Agent automationCoding | Any provider agent runtimes · CI jobs · local developer machines | manual · hybrid Moderate · Supported hosts: CLI / local scripts Permission: high | 1Password CLI docs ↗ Last verified: Apr 8, 2026 | View details |
Codex CLI Coding agent · coding Score 88 Terminal-native coding agent workflow for implementing features, refactors, and technical reviews from a real repo. | CodingAgent automation | OpenAI OpenAI models · Git repos · terminal-first dev workflows | npm · local Moderate · Supported hosts: CLI / Repo workspace Permission: high | Codex CLI repo ↗ Last verified: Apr 8, 2026 | View details |
Playwright Browser automation · browser Score 88 Reliable browser automation layer for agent actions, QA checks, scraping flows, and human-in-the-loop web tasks. | Agent automationResearch | Any provider any model · web-actuation stacks · QA automation | npm · local Moderate · Supported hosts: Node apps / Python apps Permission: high | Playwright docs ↗ Last verified: Apr 8, 2026 | View details |
Claude Code Coding agent · coding Score 87 Strong coding and refactor assistant with especially high-quality explanations and calm change planning. | Coding | Anthropic Anthropic models · repo refactors · review-oriented workflows | npm · local Moderate · Supported hosts: CLI / Repo workspace Permission: high | Claude Code docs ↗ Last verified: Apr 8, 2026 | View details |
OpenAI Whisper Speech to text · extraction Score 87 Battle-tested transcription layer for meetings, podcasts, multilingual notes, and voice-driven workflows. | ResearchAgent automation | OpenAI · Local runtime audio pipelines · meeting notes · local transcription stacks | pip · local Easy · Supported hosts: CLI / Python apps Permission: low | OpenAI Whisper repo ↗ Last verified: Apr 8, 2026 | View details |
LangGraph Agent orchestration · workflow Score 86 Graph-based runtime for durable agent workflows, branching logic, and stateful multi-step execution. | Agent automationResearch | OpenAI · Anthropic · Google · Meta OpenAI · Anthropic · Google | pip · hybrid Advanced · Supported hosts: Python apps / Node apps Permission: medium | LangGraph docs ↗ Last verified: Apr 8, 2026 | View details |
n8n Automation · workflow Score 86 Popular workflow builder for gluing APIs, LLM calls, and back-office tasks into practical automations. | Agent automation | OpenAI · Anthropic · Google · Cohere SaaS connectors · LLM APIs · ops workflows | hosted · hybrid Easy · Supported hosts: Hosted app / Self-hosted Permission: high | n8n docs ↗ Last verified: Apr 8, 2026 | View details |
SerpApi Research search · search Score 85 Search data API that helps agents gather current web signals with consistent, parseable results. | ResearchAgent automation | Any provider research agents · market scans · evidence gathering | hosted · hosted Easy · Supported hosts: API backends / automation tools Permission: low | SerpApi docs ↗ Last verified: Apr 8, 2026 | View details |
Zapier AI Actions Automation · workflow Score 84 Fast path to business automation through prebuilt actions across SaaS tools and operational systems. | Agent automation | OpenAI · Anthropic · Google · Any provider SaaS-heavy businesses · no-code ops teams · AI action layers | hosted · hosted Easy · Supported hosts: Hosted app / SaaS integrations Permission: high | Zapier AI Actions official ↗ Last verified: Apr 8, 2026 | View details |
E2B Sandbox Execution runtime · connector Score 82 Ephemeral execution environment for agent-generated code, notebooks, and dynamic analysis tasks. | CodingAgent automation | Any provider generated-code flows · analysis notebooks · agent sandboxes | hosted · hosted Moderate · Supported hosts: cloud runtime / agent backends Permission: high | E2B Sandbox docs ↗ Last verified: Apr 8, 2026 | View details |
Obsidian Memory Vault Knowledge memory · memory Score 82 Personal knowledge layer that turns agent memory into editable markdown instead of opaque hidden state. | ResearchAgent automation | Any provider assistant continuity · markdown-based memory · human review loops | manual · local Easy · Supported hosts: desktop app / local markdown repos Permission: medium | Obsidian Memory Vault docs ↗ Last verified: Apr 8, 2026 | View details |
Weaviate Vector retrieval · connector Score 82 Vector database and retrieval layer for grounding answers, semantic search, and memory-augmented agents. | ResearchAgent automation | OpenAI · Anthropic · Google · Meta · Any provider RAG systems · memory-heavy agents · semantic search | hosted · hybrid Advanced · Supported hosts: Cloud / Self-hosted Permission: medium | Weaviate docs ↗ Last verified: Apr 8, 2026 | View details |
MCP Toolbox Tool protocol · mcp Score 81 A practical toolbox around the Model Context Protocol for exposing actions, files, and resources to compatible agents. | Agent automationCoding | OpenAI · Anthropic · Any provider OpenAI-compatible agents · Anthropic-compatible agents · tool servers | manual · hybrid Advanced · Supported hosts: desktop agents / local runtimes Permission: high | MCP Toolbox docs ↗ Last verified: Apr 8, 2026 | View details |
Practical secret access layer for agents and scripts that need secure credential injection without hardcoding.
Terminal-native coding agent workflow for implementing features, refactors, and technical reviews from a real repo.
Reliable browser automation layer for agent actions, QA checks, scraping flows, and human-in-the-loop web tasks.
Strong coding and refactor assistant with especially high-quality explanations and calm change planning.
Battle-tested transcription layer for meetings, podcasts, multilingual notes, and voice-driven workflows.
Graph-based runtime for durable agent workflows, branching logic, and stateful multi-step execution.
Popular workflow builder for gluing APIs, LLM calls, and back-office tasks into practical automations.
Search data API that helps agents gather current web signals with consistent, parseable results.
Fast path to business automation through prebuilt actions across SaaS tools and operational systems.
Ephemeral execution environment for agent-generated code, notebooks, and dynamic analysis tasks.
Personal knowledge layer that turns agent memory into editable markdown instead of opaque hidden state.
Vector database and retrieval layer for grounding answers, semantic search, and memory-augmented agents.
A practical toolbox around the Model Context Protocol for exposing actions, files, and resources to compatible agents.