Public Maestro research workflow SOP skills for compute, data, and experiments.
Use for RA Compute CPU/GPU research execution: submitting, monitoring, diagnosing, cancelling, resuming, optimizing, or downloading compute jobs; mecon CLI setup; CPU resource profiles; GPU tier choice; long empirical scripts; structural/JAX estimation; bootstrap sweeps; large Parquet first-pass analysis; failed, stalled, timed_out, or cancelling runs.
SOP for discovering, inspecting, querying, citing, and downloading RA Data datasets through mecon data. Use when the user asks about datasets, catalog search, metadata, citation, samples, Parquet/CSV download, DuckDB queries, signed query URLs, dataset description, schema, coverage, source attribution, or RA Data CLI usage.
SOP for managing online research experiments through mecon exp. Use when the user asks to initialize, create, edit, inspect, preview, publish, pause, close, export, or delete an experiment; asks about participant sessions, experiment status, live URL, preview URL, dashboard, response export, or experiment lifecycle operations.
Public plugin shell for Maestro research workflows.
This repository intentionally contains only host-plugin metadata and public agent SOP skills. It does not contain the RA Compute CLI, Python runtime, worker code, deployment workflow, tests, or implementation references.
Current public plugin version: 0.7.2.
Included skills:
ra-compute: CPU/GPU and long-running research job SOP.ra-data: dataset discovery, inspection, query, citation, and download SOP.ra-experiments: online experiment lifecycle and export SOP.mecon is the CLI used by these workflows; it is not the organizing concept of
the skills. The skills are organized by user task and research object.
For RA Compute CPU/GPU jobs, install maestro-economics>=0.7.2 and use:
mecon resources
mecon submit . --resource cpu-4c-16gb
mecon submit . --resource l4
The private implementation lives with RA Suite. Do not add runtime or worker code back to this repository.
.claude-plugin/.codex-plugin/.github/workflows/public-shell-boundary.ymlskills/ra-compute/SKILL.mdskills/ra-data/SKILL.mdskills/ra-experiments/SKILL.mdOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub maestro-ai-stack/maestro-economics --plugin maestro-economicsProduction MCP memory layer for Claude Code: workspace-scoped search, entity inspection, claim grounding, change discovery, and grounded drafting through Maestro Nerve.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.