diagnose-flow Skill
Deep autonomous diagnosis of a failed flow run. Provide environment, flow, and run IDs. Use when the user asks to diagnose or deeply investigate a specific failed flow run. Published by microsoft in power-platform-skills.
What is diagnose-flow Skill?
Deep autonomous diagnosis of a failed flow run. Provide environment, flow, and run IDs. Use when the user asks to diagnose or deeply investigate a specific failed flow run. Published by microsoft in power-platform-skills. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Data analysis
- Data analysis use cases
Technical details
- Install or run with Copy skill directory
When to use diagnose-flow Skill
- Use it for data analysis.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/power-platform-skills
- Skill file: plugins/power-automate/skills/diagnose-flow/SKILL.md
What it does
Deep autonomous diagnosis of a failed flow run. Provide environment, flow, and run IDs. Use when the user asks to diagnose or deeply investigate a specific failed flow run.
Skill instructions
Deep Flow Diagnostic Agent You are an autonomous diagnostic agent. Given environment, flow, and run IDs, perform a comprehensive failure analysis. Input Parse $ARGUMENTS for: environment ID, flow ID, run ID. Tools This skill uses the FlowAgent MCP tools, referred to by bare name (clients surface them as mcpflowagent<tool in Claude Code or flowagent-<tool in Copilot CLI). If MCP tools aren't available, run /setup to wire the FlowAgent MCP server. Workflow 1. Triage with diagnoserun, then gather full context in parallel: - diagnoserun — classified failed/timed-out actions with a remediation each (start here) - getrundetails for overall run status - getrunactions for the full action-level execution trace - getflow for definition context - For a failed loop, getrunactionrepetitions on an action inside the loop (the container returns none) to find the failing iteration 2. Build execution graph: Map each action's runAfter dependencies. Identify parallel branches. 3. Identify failed actions:
Explore related resources
Frequently asked questions
What is diagnose-flow?
diagnose-flow is a open-source AI agent skill with Copy skill directory. Deep autonomous diagnosis of a failed flow run. Provide environment, flow, and run IDs. Use when the user asks to diagnose or deeply investigate a specific failed flow run.
Who is diagnose-flow best for?
diagnose-flow is best for reusing agent instructions, scripts, and references, data analysis workflows.
How do I install diagnose-flow?
Install or run diagnose-flow using Copy skill directory. Check diagnose-flow for the latest setup command.
Is diagnose-flow actively maintained?
diagnose-flow may need a closer maintenance check before production use.
Auto-fetched from GitHub.
