Catalogue of architecturally useful Orchestra orchestrations already registered in this workspace that should be reused (via the `Orchestration` step type or the data-plane `invoke_orchestration` MCP tool) instead of being re-implemented inline. Use this skill when authoring a new orchestration that needs to publish ActionView entries, generate other orchestrations from natural-language descriptions, or run an ephemeral self-healing task. Pair it with `writing-orchestrations` (schema reference) and `mcp-catalog` (MCP wiring).
Authoritative catalog of MCP servers actually configured and working in this Orchestra workspace. Use this skill whenever you author or generate an orchestration so every `mcps:` entry references a real MCP. Distinguishes pre-registered MCPs (in orchestra.mcp.json, no top-level declaration needed) from inline-only MCPs (must be declared in the orchestration's top-level `mcps:` block).
Creates and validates Orchestra orchestration files (JSON/YAML) that define DAGs of steps (Prompt, Command, Script, Http, Transform, Approval, Orchestration) with triggers, hooks, MCPs, subagents, loops, typed inputs, human-in-the-loop pauses, and template expressions. Use when authoring new orchestrations, generating orchestration files from descriptions, reviewing existing orchestrations for correctness, or debugging orchestration issues.
Responds to PR comments using the PowerReview MCP server. Reads incoming comments on the user's PRs, creates draft replies and proposed code fixes. Use when asked to respond to PR feedback, fix issues raised in review comments, or address reviewer concerns.
Reviews pull requests using the PowerReview MCP server. Reads PR metadata, diffs, and comment threads, then creates draft review comments. Use when asked to review a pull request, provide code review feedback, or analyze PR changes.
Creates an ActionView entry of type 'pr-comment-response' summarizing how AI agents responded to incoming PR comments. Shows each reviewer comment paired with the AI's draft reply, draft operation, and/or proposed code fix, with per-response approve/delete/reject actions and safe entry-level actions. Use after the AI agent has finished processing incoming comments on a PR.
Creates an ActionView entry of type 'pr-review-summary' from PowerReview draft comments/replies and consolidated review data. Produces a structured JSON entry with PR metadata, per-draft details (reviewer name, file/thread, severity, code diff when available), per-draft approve/delete actions, and entry-level bulk actions (approve all, submit, vote, delete all). Use after all PR reviewers have finished creating their draft comments or follow-up replies and the consolidated review is available.
Use when reviewing a Pull Request and you want to apply the liabadi reviewing perspective, covering Resource Providers, RPAAS, UserRP ARM, Azure deployment and RP semantics, orchestration correctness, and observability.