managed-agents

managed-agents is an LLM app frameworks & APIs skill for AI agents, published by SaschaHeyer in the gen-ai-livestream repository on GitHub. Skillspace rates managed-agents D (68/100) and it passed the safety scan; the rating is based on static analysis only.

Use this skill when running Gemini API Managed Agents through the Interactions API, especially background execution (background=True, poll and reconnect by interaction id), attaching remote MCP servers as tools, custom function calling with the requires_action flow, and reusing a server side sandbox across turns with environment_id. Covers the antigravity managed agent, the client.interactions SDK surface, and the agent vs model gotcha. SDKs and tools used, google-genai Python SDK (client.interactions), Python 3.10+, Gemini API key.

Grade
D
Quality
68 / 100
Safety
Passed
GitHub stars
187

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubSaschaHeyer/gen-ai-livestream

Our review

Architecture
85 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in LLM app frameworks & APIs

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.