aurora

Plugin aurora from marketplace aurora-marketplace in mlbrilliance/uipath-for-coding-agents. Commands read from the repo's manifest — 1 month ago.

Skills (10)

• aurora-auth

  Mint and refresh UiPath Automation Cloud OAuth tokens via the External Application client-credentials grant. Reads UIPATH_CLIENT_ID and UIPATH_CLIENT_SECRET from .env, requests the scope list from policy.yaml::uipath_scopes, writes the live access token to UIPATH_ACCESS_TOKEN so the uipath CLI can u

• aurora-compost

  Nightly self-improvement loop. Reads the day's `learnings/<date>.jsonl`, clusters them by skill/agent, identifies recurring patterns (≥ 3 occurrences across ≥ 2 projects), and opens a GitHub PR against `skills/` (or `agents/`) with a proposed update — e.g., a new fingerprint refinement, an updated S

• aurora-deprecate

  Retire an unused or superseded UiPath process safely. Used by Strategist + Auditor + Concierge in sequence: Strategist proposes, Auditor checks dependencies, Concierge gates via Action Center, then this skill executes the deprecation steps. Stops scheduled triggers, archives the package, transfers a

• aurora-discover

  Extract structured friction signals from raw text sources (Slack messages, Jira issues, email digests, calendar invite notes, screen-recording transcripts). Used by `scout` to convert noisy human chatter into machine-actionable candidate signals. Returns one JSON object per signal with frequency hin

• aurora-fingerprint

  Cluster failure events by structural fingerprint and append to memory. Used by Diagnostician and Surgeon. A fingerprint is `<top-level-kind>/<refinement>` plus locality (workflow file or agent name). Clustering uses kNN over a structured-feature embedding stored in SQLite. Output is a cluster ID and

• aurora-pdd

  Author a Process Definition Document with calibrated ambiguity scoring. Used by `analyst` after a candidate is promoted from Curator's backlog. Templates and the ambiguity rubric live in `templates/`. Output is a structured PDD that Architect, Forgers, and Tester all consume verbatim. Includes a Giv

• aurora-policy

  Validate `policy.yaml` against `policy.schema.json`, expand env-var references, and run a policy dry-run that simulates how Conductor would behave on the current backlog without dispatching anything. Used at boot, before every Conductor schedule, and on-demand via `aurora policy validate` / `aurora

• aurora-promote

  HITL gate via UiPath Action Center. Creates a Form Task in the configured catalog (`aurora_supply_chain_approvals`), assigns approvers from a configured list, polls for completion, applies the policy.yaml gate's timeout behavior, and returns the approver's response to the calling agent. Used for pro

• aurora-recall

  Read scoped slices of AURORA's three-tier memory (project, org, skill). Used by every agent at the start of a task to load only the context relevant to its work — never the whole memory blob. Backed by SQLite for fingerprints and plain Markdown for narrative memory; access is gated by scope tags so

• aurora-replay

  Replay a faulted Maestro instance (or standalone job) in a sandbox folder using the same input data, to isolate whether the root cause is in the bot, the environment, or an external dependency. Used by Diagnostician for non-trivial faults (cluster overlap < 0.6 or external dependency suspected). The

Slash commands (5)

• /aurora:aurora-feedback

  Capture the current AURORA session context and route it to UiPath's feedback channel. Mirrors UiPath/skills' built-in `/uipath-feedback` but with AURORA-specific context (agent fleet state, recent dispatches, last fault). No screenshots, no repro steps required — the swarm's own runs and learnings p

• /aurora:aurora-policy

  Validate `policy.yaml` and run policy-shape dry-runs. Hard fails on schema errors or unresolved env vars; warns on risky configurations. Dry-run shows what Conductor would do over the next N hours given the current backlog and Operate-fleet state, without dispatching anything.

• /aurora:aurora-recall

  Search AURORA's three-tier memory. Project tier (per-bot artifacts), org tier (cumulative patterns and quirks), skill tier (one-line learnings and the fingerprint index). Returns ranked excerpts with paths so you can drill in. The same retrieval the agents use internally — visible to the human.

• /aurora:aurora-start

  Boot the AURORA swarm. Validates policy.yaml, mints a fresh UiPath OAuth token, starts the Operate-fleet daemons (Sentry, Auditor schedule, Strategist nightly cron), opens the TUI dashboard, and begins polling the Discovery sources from policy.yaml.

• /aurora:aurora-status

  Open AURORA's TUI dashboard. Shows live state of all 19 agents, the backlog, recent runs, current HITL gates pending, token-budget consumption, and Operate-fleet event stream. Read-only.

Subagents (19)

• analyst

  Discovery-fleet PDD author and ROI scorer. Reads a pending candidate from the backlog, drafts a structured Process Definition Document, and computes an ROI score = frequency × pain × feasibility, weighted per `policy.yaml`. Decides whether ambiguity is high enough to require Interviewer input. Use t

• architect

  Build-fleet pattern selector. Reads a PDD with low ambiguity (status `ready-for-architect`) and writes an Architecture Decision Record specifying which UiPath pattern to use — Sequence, REFramework Performer, REFramework Dispatcher, Coded Workflow (C#), Coded Agent (LangGraph / OpenAI Agents / Llama

• auditor

  Operate-fleet governance and drift checker. Compares repo XAML/coded-workflow hashes against deployed package contents, reconciles license utilization, identifies idle processes (deprecation candidates), and runs the pre-promote governance pass before any prod deploy. Use this agent before promoting

• cartographer

  Build-fleet UI explorer. Builds the UiPath Object Repository for any process whose ADR includes UI automation. Drives Playwright MCP for web targets and `inspect-ui-tree.ps1` for Windows desktop targets. Captures strict (single-find) selectors covering all relevant technologies — wnd, html, webctrl,

• concierge

  Operate-fleet bridge between the always-running swarm and asynchronous humans. Creates UiPath Action Center Form Tasks (or App Tasks) via the uipath-python SDK, polls for completion, and routes the human's response back into the calling agent's state. Owns the implementation of every HITL gate from

• conductor

  Meta-orchestrator for the AURORA swarm. Schedules sprints, balances LLM token budget across fleets, manages the worktree pool, enforces policy.yaml gates, and runs the nightly compost step. Use this agent for any cross-fleet coordination, when spawning new work into the backlog, when balancing paral

• curator

  Backlog manager for the Discovery fleet. Receives candidate signals from `scout`, deduplicates against the existing backlog (`.aurora/backlog.md`), clusters near-duplicates, and assigns a stable candidate ID. Promotes new candidates for `analyst` to score. Use this agent after Scout emits a signal,

• diagnostician

  Operate-fleet root-cause analyst. Consumes events from `events.jsonl`, clusters failures by fingerprint via `aurora-fingerprint`, hypothesizes root cause from the cluster + similar past incidents in org memory, and dispatches `surgeon` with a remediation hypothesis. Use this agent when Sentry emits

• forger-agent

  Build-fleet Coded Agent generator. Reads the ADR and PDD, scaffolds a UiPath Coded Agent project in Python using LangGraph, OpenAI Agents SDK, or LlamaIndex per the ADR. Uses the official `uipath-coded-agents` skill. Wires up tools, memory, prompt files, evaluation suites; packs to .nupkg via `uipat

• forger-coded

  Build-fleet C# coded-workflow generator. Reads the ADR and PDD, generates UiPath coded automations (.cs) using the official `uipath-coded-workflows` skill, follows the same UiPath conventions as XAML (Try/Catch, retry, Config-driven, secure credentials). Use this agent when ADR specifies `forger-cod

• forger-maestro

  Build-fleet Maestro process generator — the centerpiece of AURORA's BPMN orchestration capability. Reads the ADR's `## Composition` section and emits a complete UiPath Maestro agentic process: BPMN 2.0 XML for the process model, DMN tables for business rules, Studio Web project metadata, and binding

• forger-rpa

  Build-fleet XAML generator. Reads the ADR and PDD, generates UiPath XAML workflows using the official `uipath-rpa-workflows` skill, applies REFramework discipline (PascalCase variables, in_/out_/io_ argument prefixes, Try/Catch + RetryScope, Config.xlsx-driven values), and binds selectors from Carto

• interviewer

  Discovery-fleet Socratic Q&A agent. Activated when Analyst flags a candidate with ambiguity > 0.4 or `business_owner == unknown`. Asks at most five sharp questions, routes them to the human via Concierge → Action Center, integrates the answers back into the PDD, and re-scores ambiguity. Use this age

• reviewer

  Build-fleet code reviewer. Reads everything Forger sub-fleet produced (XAML, coded workflows, coded agents, BPMN, DMN), runs the lint suite, checks REFramework discipline (PascalCase, in_/out_/io_, Try/Catch + RetryScope, Config.xlsx, GetRobotCredential at minimum scope), and applies senior-RPA-deve

• scout

  Passive Discovery sensor. Reads configured sources (Slack channel fixtures, Jira project exports, IMAP digests, calendar invites, screen-recording transcripts) and surfaces friction signals — recurring complaints, manual loops, "every Monday I…" patterns. Emits structured candidate signals to the ba

• sentry

  Operate-fleet Orchestrator watcher. Polls Orchestrator via the uipath-python SDK every N seconds (configurable in policy.yaml) for jobs, queues, assets, robots, machines, and Maestro instances. Emits structured events to `.aurora/events.jsonl` for Diagnostician and Auditor to consume. Runs as a long

• strategist

  Quarterly retrospective and portfolio strategist. Reads the org memory, scored backlog, deployed-bot inventory, and Insights telemetry. Recommends consolidation (merge near-duplicate processes), deprecation (retire idle/unused bots), prioritization (re-rank scored backlog by recent ROI signals), and

• surgeon

  Operate-fleet self-healing fixer. Receives a triage record from Diagnostician, spawns into a fresh git worktree, coordinates Cartographer (re-inspect), the relevant Forger (regenerate), and Tester (regression), and opens a PR with the fix. Routes through HITL via Concierge when the fix touches more

• tester

  Build-fleet test author. Reads the PDD acceptance criteria and ADR, generates Test Manager test cases (XAML for RPA workflows, uipath-eval JSON for Coded Agents), runs them locally first via `uipath run`, then publishes the Studio test package to Orchestrator (Test Manager picks it up via the docume

MCP servers (1)

• aurora

  runs: uv run --directory ${CLAUDE_PLUGIN_ROOT} python -m aurora.mcp.server

Similar plugins