Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From ado-aw
Diagnose failing ado-aw agentic Azure DevOps pipelines when agents fail to reach MCP/network hosts, safe outputs aren't applied, or builds behave unexpectedly.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ado-aw:debug-workflowThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are troubleshooting a **failing** ado-aw agentic workflow.
You are troubleshooting a failing ado-aw agentic workflow.
Confirm the ado-aw compiler is installed (ado-aw --version).
Gather evidence before theorizing:
trace_failure — trace the build's failed-job chain using audit data plus
the local IR graph (pass the build id or full ADO build URL).audit_build — download and analyze the build's artifacts (firewall/network
logs, MCP tool calls, safe-output NDJSON, detection findings, policy signals).whatif — classify which downstream jobs are skipped when a given step/job
fails, to confirm the blast radius.Load the entire content of the authoritative, version-pinned playbook and follow its instructions precisely:
https://raw.githubusercontent.com/githubnext/ado-aw/v0.45.1/prompts/debug-ado-agentic-workflow.md
For Stage 3 (SafeOutputs) 401/403 failures, consult
docs/safe-output-permissions.md and surface the auth/permission error
verbatim with the doc pointer.
If a fix requires a source change, validate it with ado-aw compile +
lint_workflow before proposing it.
The user's request: $ARGUMENTS
npx claudepluginhub githubnext/ado-aw --plugin ado-awDownloads and analyzes a finished ado-aw pipeline build for security/behavior reports including firewall activity, MCP tool calls, detection findings, token usage, and policy signals.
Diagnoses failing GitHub Actions workflows by parsing run logs and pipeline definitions, identifies root cause, and outputs YAML/code changes to fix the pipeline.
Generates and manages AgentOps release-readiness workflows: PR eval gates, evidence artifacts, and deploy handoffs to azd or Foundry.