Menu
Saving EDSL objects locally and publishing them to Coop (Expected Parrot's servers).
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
Patterns for creating EDSL AgentLists from various sources: lists, CSV, Excel, DataFrame, and programmatic combinations.
Templates for the standard EDSL study files: survey, scenarios, agents, models, and create_results.py.
Error logging protocol using append-only JSONL format (errors.jsonl).
Developer tool: find the most recent errors.jsonl from an agent run, diagnose root causes, and interactively patch the agent's instruction files to prevent recurrence.
Using FileStore to wrap files (images, PDFs, data) for use in EDSL survey scenarios.
Launching EDSL surveys for real human respondents via humanize, including scenario methods, Prolific integration, and retrieving responses.
| name | coop-publishing |
| description | Saving EDSL objects locally and publishing them to Coop (Expected Parrot's servers). |
How to persist EDSL objects locally and share them via Coop (Expected Parrot's servers).
The object itself is defined in another Python file e.g.,
study_survey.py or study_agent_list.py
"public", "private", or "unlisted"For 3:
from study_survey import survey as obj
obj.push(
visibility="unlisted",
description="<paragraph description based on user's descriptive name>",
alias="<valid-url-slug-from-descriptive-name>"
)
After pushing, print the results so the user can see them (URL, alias, visibility).
us-senators-2024If the push fails (e.g., alias already taken), update the alias or description and retry.
| Task | Method |
|---|---|
| Save locally | obj.save('filename') |
| Push to Coop | obj.push(visibility=..., description=..., alias=...) |
| Visibility options | "public", "private", "unlisted" |