Menu
Daily OrCAID multi-agent delegation — run commit0/self_improve/paperbench tasks, evaluate output, deliver results. Schedule: 09:00 AM.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
arXiv paper discovery — select top 3 significant papers, research via subagents, ingest to wiki, deliver report.
Daily raw file ingestion pipeline — process files from raw/ into structured wiki knowledge, verify frontmatter and links, archive to Clippings/. Schedule: 06:30 AM.
Daily Zettelkasten insight generation — run CLI insight engine, create wiki pages for confidence>=0.7 insights, integrate to wiki. Schedule: 06:00 AM.
Daily global news curator — RSS discovery, significance filtering, clippings archive + synthesis wiki delivery, deliver headlines report. Schedule: 07:30 AM.
Wiki synthesis agent operational sheet — cross-domain bridges, concept advancement, evidence evaluation
Daily wiki quality audit anchored in wiki-indexing-theory.md — HITS authority scoring, GAAC cluster validation, tag taxonomy compliance, reciprocal link enforcement. Schedule: 08:50 AM.
| name | orcaid |
| description | Daily OrCAID multi-agent delegation — run commit0/self_improve/paperbench tasks, evaluate output, deliver results. Schedule: 09:00 AM. |
| tags | ["orcaid","self-improve","commit0","paperbench","paper2code","daily"] |
| triggers | [{"cron":"0 9 * * *"},{"manual":"delegate_task"}] |
| updated | "2026-05-25T00:00:00.000Z" |
| created_by | agent |
Run the OrCAID multi-agent delegation framework. Three task types: commit0 (stub implementation), self_improve (self-refactor), paperbench (paper reproduction). Choose the right mechanism for the job.
references/task-types.md — commit0 / self_improve / paperbench detailsreferences/execution-mechanisms.md — ACTIVE vs PASSIVE mechanismstemplates/run-report.md — run report formatMechanism 1 — ACTIVE: orcaid.cli → produces new outcomes
Mechanism 2 — PASSIVE: run_evolution.py --domain orcaid → computes metrics from memory (no new outcomes)
Mechanism 3 — PASSIVE: run_evolution.py --domain paper2code → evaluates Paper2Code outputs
| Task | Use When | Docker Image |
|---|---|---|
commit0 | Fix missing stubs in repo | wentingzhao/minitorch:v0 |
self_improve | Refactor/improve OrCAID itself | python:3.12-slim |
paperbench | Reproduce scientific paper | ghcr.io/openhands/agent-server:latest-python |
uv run python — NOT bare python~/.hermes/orchestrator-memory/ (NOT ~/.orcaid/)export ORCAID_RETRY_POLICY=kl