Skill Claude CodeCodex
Always invoke for .xaml or .cs workflow files. UiPath RPA — create, edit, build, run, debug .cs coded workflows and .xaml workflows. UI automation with Object Repository selectors, test case authoring, Integration Service connector calls. Live desktop/browser UI exploration and control. Deploy via…
Agent
Auto-discover UiPath project structure, dependencies, and conventions; write .claude/rules/project-context.md + AGENTS.md, return the context document for Claude Code/Autopilot. Spawn before workflow authoring or when user asks to refresh project context / regenerate AGENTS.md. Skips empty and freshly-scaffolded…
Skill Claude CodeCodex
Always invoke for .uipx files. UiPath Solution lifecycle via the uip solution CLI: init/restore/pack/publish/deploy/activate/upload, projects add|import|remove, resources refresh|add|remove|edit. Also DIAGNOSE solution-lifecycle failures: pack/publish/deploy/activate errors, stale or missing bindings…
Skill Claude CodeCodex
UiPath Action Center human-in-the-loop tasks via uip tasks: list, assign, complete, plus task catalogs, comments, labels, metadata, and task data (get/save). For authoring HITL nodes in flows/agents→uipath-human-in-the-loop. For Orchestrator→uipath-platform, codedapp→uipath-coded-apps. Skip Document Understanding.
Skill Claude CodeCodex
UiPath Test Manager — manage test projects, cases, sets, executions; generate reports; package and run external Playwright test suites. For Orchestrator→uipath-platform. For Studio/RPA test automation authoring→uipath-rpa.
Skill Claude CodeCodex
UiPath causal investigation across every product, runtime, and activity package. Use when the primary outcome is an explanation, diagnosis, or root cause for undesirable existing behavior: faults, hangs, regressions, slowdowns, access loss, unexpected state changes, wrong or empty results, silent no-ops, or raw…
Agent
Covers low-code agent runtime and authoring errors. Primary investigation surface: uip traces spans get --output json or uip traces spans get --job-key --output json; local reproduction uses uip agent debug only with explicit user approval because it uploads and executes the agent.
Plugin Claude Code
Test whether your Claude Code skills actually trigger, and benchmark AI coding agents against your own tasks.
Command Claude Code
Review the codebase across critical quality axes.
Command Claude Code
Workflow-based 8-axis codebase review — per-axis sub-workflows, adversarial verify, deterministic scoring + rendering.
Command Claude Code
Run a multi-model code review on uncommitted changes or a described set of files.
Command Claude Code
Create a structured, phased implementation plan for a feature or change in the codereval codebase, executable from a fresh session by /coder-eval-implement-plan.
Command Claude Code
Implement an approved codereval plan phase by phase with risk-scaled per-phase review, then a final code review.
Command Claude Code
Generate per-task review.json (summary + tags) for a completed run.
Instructions file
Instructions for UiPath/coder_eval, covering claude.md - ai assistant guide, project overview, directory structure, key architectural patterns and success criteria (15 types).
Agent
Run Google Antigravity (Gemini) as the agent under evaluation in Coder Eval — installation, authentication, model and skill configuration, and how its telemetry maps to sandboxed, weighted scoring.
Agent
Configure and run the default Claude Code agent in Coder Eval — the full agent-config surface, direct vs. Bedrock authentication, permission modes, sandbox isolation, skills/plugins, early stop, and token telemetry.
Agent
Run OpenAI Codex as the agent under evaluation in Coder Eval — installation, authentication, task configuration, and how Codex telemetry maps to sandboxed, weighted scoring.
Agent
One task file, run on any harness, must be the same task. runlimits.maxturns was the field that broke that promise hardest: Claude Code enforced it, and Codex and Antigravity accepted it and never read it, so maxturns: 6 ran capped on one backend and unbounded on the other two.
Agent
Run OpenCode, the open-source terminal coding agent, as the agent under evaluation in Coder Eval — installation, provider authentication, model selection, and how its event stream maps to sandboxed, weighted scoring.
Plugin Claude Code
Test whether your Claude Code skills actually trigger, and benchmark any coding agent — author, run, and analyze the eval suite that proves it, locally or as a CI gate.
Skill Claude CodeCodex
Analyze a finished coder-eval run and write analysis.md — cluster failures into systemic patterns and recommend fixes. Use when the user wants to know why a run failed, what regressed or got worse since a previous run, what to fix, or what a run says about their tasks.
Skill Claude CodeCodex
Generate and run a coder-eval activation suite for a Claude Code skill. Use when the user asks whether a skill triggers, wants to test skill activation, or worries a skill has silently stopped firing.
Skill Claude CodeCodex
Generate a GitHub Actions workflow that runs a coder-eval suite as a CI gate or on a schedule, using the published composite action — with the agent runtime, credentials, JUnit output and a score floor wired correctly.