Open source alternatives to agent-platform-troubleshooting
24 open source AI Skills apps to use instead, best rated first.
Top picks
- G
github-ops
Getgithub-ops is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It manages a GitHub repository with a focus on community health, CI reliability and the experience of contributors. It covers triaging issues by classify
Open source
- O
opensource-pipeline
Getopensource-pipeline is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It prepares a private project for safe public release through a three-stage pipeline. The fork stage strips secrets from a copy. The sanitise st
Open source
- A
andrej-karpathy-skills
Getandrej-karpathy-skills is a single CLAUDE.md file from the multica-ai project that is meant to improve how Claude Code behaves on coding tasks. It is derived from Andrej Karpathy's public observations about LLM coding pitfalls. The file dis
Open source
- M
microsoft/markitdown
Getmarkitdown-mcp is the MCP server package for MarkItDown, Microsoft's tool for converting many file formats to Markdown for language models. It is a lightweight server that runs over stdio, Streamable HTTP or SSE, and exposes one tool, conve
Open source
- O
od-contribute
Getod-contribute is an agent skill in the OpenDesign project that provides a guided, one-click contribution flow to the OpenDesign repository, written so that people without a coding background can send a real pull request. It is locked to the
Open source
- G
github-deep-research
Getgithub-deep-research is an agent skill from the DeerFlow project that researches a single GitHub repository in several rounds and writes a report in Markdown. It is for requests that need more than a README summary, such as a comprehensive
Open source
More AI Skills apps
modelcontextprotocol/server-memory
Knowledge graph-based persistent memory for maintaining context
netdata/netdata#Netdata
Discovery, exploration, reporting and root cause analysis over Netdata metrics
Learn Claude Code
by shareAI-lab - A really interesting analysis of how coding agents like Claude
MCP Toolbox for Databases
MCP Toolbox for Databases enables your agent to connect to your database
About agent-platform-troubleshooting
agent-platform-troubleshooting
Troubleshoots Google Cloud Gemini Enterprise Agent Platform issues
Agent Platform troubleshooting is an agent skill for diagnosing problems in Google Cloud's Gemini Enterprise Agent Platform. It covers Agent Gateway, the Agent Registry for agents, MCP servers and endpoints, Agent Identity, policies, authorization delegated through Identity-Aware Proxy, service extensions and Model Armor. Before it responds, the skill runs a pre-flight checklist of rules that match the kind of problem you describe, and when a rule matches it follows that rule's directive. It works only from the reference files in its own references folder, which hold a field manual, a list of known issues, and an agent registry guide with workspace-specific fixes. The skill says these files are the sole source of truth for the session, so it does not search for other playbooks. This keeps its advice tied to the documented fixes, though it means the skill is only as complete as those references. It is useful for platform administrators and developers who see an agent fail to reach a model, get blocked by a policy, or lose access through identity or proxy settings. It is published by Google on skills.sh under the google skills repository, with about 4.4K installs, and the listing shows Gen Agent Trust Hub, Socket and Snyk all passing.
- Price
- Free
- Made by
- Category
- AI Skills
- Website
- github.com/google/skills/agent-platform-troubleshooting