inkeep/typescript-sdk
skills/typescript-sdk/SKILL.md
Use when creating, modifying, or testing AI Agents built with the Inkeep TypeScript SDK (@inkeep/agents-sdk).
$ install --global
skillsauthnpx skillsauth add inkeep/skills typescript-sdkInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 29, 2026, 8:18 AM163.1s50 files scanned
SKILL.md
- name:
- typescript-sdk
- description:
- Use when creating, modifying, or testing AI Agents built with the Inkeep TypeScript SDK (@inkeep/agents-sdk).
- license:
- MIT
- author:
- inkeep
- version:
- 1.0
Typescript Sdk
Overview
The TypeScript SDK provides a declarative way to define agents, sub-agents, tools, and their relationships.
Rules (49)
Read individual rule files for detailed explanations and code examples on particular tasks or topics:
| Title | Topic | Description | | --- | --- | --- | | Sub Agent Relationships Overview | typescript-sdk/agent-relationships | Transfer and delegation relationships between Sub Agents | | When to Use Transfers vs Delegation | typescript-sdk/agent-relationships | Guidelines for choosing between transfer and delegation relationships | | Types of Delegation Relationships | typescript-sdk/agent-relationships | Sub agent, external agent, and team agent delegation | | Configuring StopWhen | typescript-sdk/agent-settings | Control stopping conditions to prevent infinite loops in agents | | Sub Agent Parameters Reference | typescript-sdk/agent-settings | Complete parameter reference for subAgent() configuration | | CLI inkeep add Command | typescript-sdk/cli-reference | Pull a template project or MCP from the Inkeep Agents Cookbook | | CLI inkeep config Command | typescript-sdk/cli-reference | Manage Inkeep configuration values | | CLI Configuration File Structure | typescript-sdk/cli-reference | Structure of inkeep.config.ts and configuration priority | | CLI inkeep dev Command | typescript-sdk/cli-reference | Start the Inkeep dashboard server for visual agents orchestration | | CLI Environment Variables | typescript-sdk/cli-reference | Environment variables respected by the CLI and SDK | | CLI inkeep init Command | typescript-sdk/cli-reference | Initialize a new Inkeep configuration file in your project | | CLI inkeep list-agent Command | typescript-sdk/cli-reference | List all available agents for a specific project | | CLI inkeep login Command | typescript-sdk/cli-reference | Authenticate with a deployment using the device code flow | | CLI inkeep logout Command | typescript-sdk/cli-reference | Clear stored credentials for a profile | | CLI inkeep profile Command | typescript-sdk/cli-reference | Manage named CLI profiles for multiple remotes, credentials, and environments | | CLI inkeep pull Command | typescript-sdk/cli-reference | Pull project configuration from server and update local TypeScript files | | CLI inkeep push Command | typescript-sdk/cli-reference | Push agent configurations to your server | | CLI inkeep update Command | typescript-sdk/cli-reference | Update the Inkeep CLI to the latest version | | Runtime Limits Configuration | typescript-sdk/configure-runtime-limits | How to configure execution limits, timeouts, and constraints | | Runtime Configuration Variables | typescript-sdk/configure-runtime-limits | All available environment variables for configuring runtime limits | | Context Fetchers Overview | typescript-sdk/context-fetchers | How to use context fetchers to embed real-time data in agent prompts | | Credential Store Options | typescript-sdk/credentials/overview | Options for storing MCP server and external agent credentials | | Data Operation Types Reference | typescript-sdk/data-operations | All data operation event types and their payloads | | Data Operations Overview | typescript-sdk/data-operations | How to enable and use data operations for debugging and monitoring | | External Agents Overview | typescript-sdk/external-agents | How to configure and use external agents using the A2A protocol | | Passing Context via Headers | typescript-sdk/headers | How to pass dynamic context to agents via HTTP headers | | Using Headers in Agents | typescript-sdk/headers | How to use header values in prompts, context fetchers, and external tools | | Conversation Memory Overview | typescript-sdk/memory | How conversation history is managed and included in context windows | | Model Types Reference | typescript-sdk/models | When to use each model type in the configuration hierarchy | | Model Provider Options | typescript-sdk/models | Configuration options for different model providers | | Supported Models Reference | typescript-sdk/models | List of supported model providers and their API keys | | Defining Artifact Components | typescript-sdk/structured-outputs/artifact-components | How to define artifact components with preview fields for citations and sources | | Defining Data Components | typescript-sdk/structured-outputs/data-components | How to define data components using Zod schemas | | Status Updates Configuration | typescript-sdk/structured-outputs/status-updates | How to configure AI-powered status updates for agents | | Function Tools Execution Environment | typescript-sdk/tools/function-tools | Sandbox providers, runtime configuration, and security guarantees | | Function Tools Overview | typescript-sdk/tools/function-tools | Use cases and how to create function tools | | Environment-Aware MCP Servers | typescript-sdk/tools/mcp-tools | Configure MCP tools to switch based on environment (dev vs production) | | MCP Tool Authentication | typescript-sdk/tools/mcp-tools | Authentication methods for MCP servers including API keys, OAuth, and custom headers | | MCP Tool Overrides | typescript-sdk/tools/mcp-tools | Customize how individual MCP tools appear to agents | | Selecting MCP Tools | typescript-sdk/tools/mcp-tools | How to selectively enable tools from MCP servers | | Registering MCP Servers as Tools | typescript-sdk/tools/mcp-tools | How to register and configure MCP tools for your agents | | Tool Approvals Configuration | typescript-sdk/tools/tool-approvals | How to configure tools to require user approval before execution | | Responding to Tool Approval Requests | typescript-sdk/tools/tool-approvals | How to approve or deny tool execution requests | | Trigger Configuration Options | typescript-sdk/triggers/overview | Configuration options for triggers including authentication, schemas, and transforms | | Triggers Overview | typescript-sdk/triggers/overview | Creating webhook endpoints to invoke agents from external services | | Trigger Configuration Options | typescript-sdk/triggers/webhooks | Configuration options for triggers including authentication, schemas, and transforms | | Triggers Overview | typescript-sdk/triggers/webhooks | Creating webhook endpoints to invoke agents from external services | | Configuration Priority Hierarchy | typescript-sdk/workspace-configuration | How CLI flags, env vars, and config file values are resolved | | Workspace Configuration File | typescript-sdk/workspace-configuration | Structure and options for inkeep.config.ts |
Other Resources
For additional information, see:
- Full Documentation: https://docs.inkeep.com/ (llms.txt and llms-full.txt available are available!)
- GitHub Repo (Open Source): https://github.com/inkeep/agents
Related Skills
openclaw/openclaw-secret-scanning-maintainer
development
VerifiedTrustedCommunity
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
357,764SKILL.mdUpdated Apr 15, 2026
openclaw/openclaw-release-maintainer
development
VerifiedTrustedCommunity
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/openclaw-qa-testing
development
VerifiedTrustedCommunity
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/openclaw-parallels-smoke
development
VerifiedTrustedCommunity
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.
357,764SKILL.mdUpdated Apr 10, 2026