mlbrilliance

Offline, credential-free knowledge + static validators for UiPath Maestro Case footguns. Explain cryptic error codes (400300, 160009, ...) and lint caseplans, spawn inputs, and Data Fabric specs in CI — no UiPath login. Use when authoring, debugging, or reviewing UiPath Maestro Case / Data Fabric / Action Center work.

Cross-runtime skill optimizer. Use this skill when the user wants to package an Agent Skill so it runs in both Claude Code and OpenAI Codex from a single portable source. Also use when the user wants to import an existing skill (Claude Code or Codex) into the portable format, build/emit for any runtime, install a skill into Claude Code or Codex, or troubleshoot why a skill behaves differently across runtimes.

Use when the user wants to package a skill so it runs in both Claude Code and Codex from one source, import an existing skill into the portable format, install to Claude or Codex, or troubleshoot cross-runtime drift.

Structure long-running Claude Code sessions on this Python project so the agent iterates for hours instead of stopping after one pass. Use when the user mentions "long-running session", "multi-hour run", "agent keeps stopping", "agent finishes too early", "headless run", "tmux session", "milestones", "make verify", "fake success", "prevent shortcuts", or asks how to set up hooks, a verification gate, or an operating contract for an autonomous coding agent.

Activate when the BAA Boundary Reasoner Agent runs or when a regulatory inquiry hits multiple affected provider customers. Teaches how to reason about a single regulatory inquiry against multiple differing BAA terms.

Activate when designing any new case stage, child case, or grandchild case. Defines the six case-shape patterns Maestro Case must demonstrate.

Activate when rehearsing or testing the demo runner. Guides dry-running the 3-minute demo end-to-end against the local stack.

Cross-runtime skill converter and optimizer. Use when the user wants to convert one or more Agent Skills into formats for other runtimes: OpenAI Codex, GitHub Copilot, Cursor, Windsurf, Antigravity, Gemini CLI, or any future runtime. Also use when importing an existing skill from another runtime, building cross-runtime versions, or troubleshooting why a skill behaves differently across runtimes.

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 use it without re-auth, and refreshes proactively before the 1-hour expiry. Use this skill at the start of every Conductor run, before any uipath CLI or uipath-python SDK call, and whenever Sentry emits a `kind: auth_failed` event.

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 confidence score; downstream agents use these to decide auto-fix vs HITL.

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 policy dry-run`. Hard fails if the policy is invalid; soft warnings for sub-optimal configurations (low test coverage floor, missing emergency_patch gate, etc.).

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 a Build agent can't accidentally pull Operate-fleet failure traces, etc. Reading is the only public interface; writing is via `aurora-fingerprint` (clusters) or direct file I/O within an agent's own scope.

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 SKILL.md guidance, a new helper script. The PR is HITL-gated via `aurora-promote` (kind: skill_compost_pr) and never auto-merged. The mechanism that makes the swarm get smarter with use.

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 any in-flight queue items to a successor (if any), updates org memory's deprecation log, and writes a runbook so the retired process can be restored within 30 days if needed.

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 hints, duration hints, pain indicators, and named systems. Reject one-off, internal-swarm, and metadata-only chatter.

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 Given/When/Then acceptance-criteria pattern that maps 1:1 to test cases. Sets ambiguity_score in [0,1]; values above 0.4 trigger Interviewer.

Build → headed test → find bug → fix → retest loop for migrator-emitted Python+Playwright projects. Load before running a migrated artifact against a live target, when designing a new FaultFixer for browser automation, or when adding a new env-toggle to the BrowserSession harness. Distils the YouTube Playwright-CLI workflow into the seams this repo actually exposes.

JSON-RPC patterns for Odoo 17 (Community + Enterprise) — session auth, `account.move` vendor bill creation with line items, multi-currency resolution, and `mail.activity` manager approvals. Load this when writing C# or Python code that talks to Odoo without the official XML-RPC library, or when debugging `NotNullViolation` / inactive currency errors.

Translating the UiPath REFramework state machine (Init → GetTransactionData → Process → SetTransactionStatus → End) into a C# Coded Workflow (.NET 8 / Portable) so it runs on the Community Cloud Linux serverless robot. Load when generating REFramework automation targeted at the Linux runtime, or when the user asks for "REFramework but coded" / "enterprise invoice processing pattern".

Brick walls hit when deploying a Portable (.NET 8 / Linux serverless) UiPath project to Community Cloud in 2025-2026. Load this before attempting any Portable deploy, Document Understanding integration, Maestro push, Action Center task, or Orchestrator API call that isn't obviously supported. Saves hours of dead-end debugging.