Ensemble Curator — Data & AI agent for Claude Code
High-volume triage agent for external-AI-agent PRs (Codex, Jules, Hermes, Droid, Aider, etc.).
How to install Ensemble Curator
Installs to ~/.claude/agents/effortlessmetrics-perl-lsp-ensemble-curator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/EffortlessMetrics/perl-lsp/HEAD/.claude/agents/ensemble-curator.md -o ~/.claude/agents/effortlessmetrics-perl-lsp-ensemble-curator.md Restart Claude Code, or start a new session, for it to be picked up.
What Ensemble Curator does
name: ensemble-curator description: High-volume triage agent for external-AI-agent PRs (Codex, Jules, Hermes, Droid, Aider, etc.). Analyzes, consolidates, cross-pollinates, routes, closes-when-wrong. NOT a correctness gate — that stays with reviewer-deep. model: haiku color: purple isolation: worktree
You are the ensemble-curator for perl-lsp — a Rust LSP/DAP server whose inbound PR stream is ~70% external-AI-agent-generated (Codex 4-shot bursts, Jules single-prompt runs, Hermes plannin
Alternatives in Data & AI
- GitHub Issues Specialist — GitHub Issues and Pull Requests specialist optimized for AI-agent workflows 1.5k ★
- Comprehension Review — De-warmed cold comprehension-and-structure gate for design.md and track files: reads only the document, never 432 ★
- Review Code Correctness — A code review agent that checks analysis scripts for logical errors, incorrect function usage, wrong variable 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Triage Analyst
Root-cause analyst. Use when something is broken, erroring, hanging, silently doing nothing, or returning wron
Portfolio Inflight Collector
Read-only in-flight data collector dispatched by portfolio-inflight-triage: gathers open issues, open PRs (inc
AI PR Gate
Reviews bot-authored PRs for INV-91 compliance. Checks that the approved-by-human label is present and that th
External Data
Conditional review angle "external data" of the user's §6 gate — a feed, API or IPC boundary: reconnect, rate
Omn Context Agent.Agent
Context Agent of the AI Engineering Framework. Reconstructs current-state product, technical, and delivery con
Engine Design Review Architecture
Before a change you've asked for gets built, checks whether the plan is soundly designed — clean boundaries, a
Related Skills
Cluster Triage
Ensemble-curator step 6 — for a detected cluster, pick winner(s) by file-path, extract edge cases from losers,
Agent Skills Lint
Cross-agent skill validator and installer — Claude Code, Codex, OpenCode, Aider, Copilot, Cursor, Gemini, Droi
Audit Implementation
POST-IMPLEMENTATION AUDIT — analyzes what the implementing agent did wrong and why, proposes specific changes