expectedparrot

Read the paper and decide which issue spotters to use, removing irrelevant ones and optionally adding custom ones

Run EDSL-parallelized issue finding across all sections of a katz-registered manuscript

Bootstrap a full paper review using katz

Send paper figures to vision-capable models for feedback on clarity, design, and presentation

Review open katz issues, investigate them against the manuscript and code, and record findings

Read the paper and file issues for problems found in the manuscript

Review the paper's repository — code, data, and analysis scripts — against manuscript claims

Collaboratively create GitHub issues from review findings

Patterns for creating EDSL AgentLists from various sources: lists, CSV, Excel, DataFrame, and programmatic combinations.

Saving EDSL objects locally and publishing them to Coop (Expected Parrot's servers).

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.

Gather and synthesize academic literature for a research question, then use findings to inform study design and analysis.

Generate a qualitative interview guide as an EDSL Survey with QuestionInterview, based on Geiecke & Jaravel (2026) methodology

Publish a completed study to GitHub - creates a repo with the analysis report as README.md, all charts, data, and a reproducibility footer linking to Expected Parrot

Generate a comprehensive, self-contained analysis report for a conjoint (choice-based) study with executive summary, methodology, part-worth utilities, segment analysis, and limitations

Design, execute, and analyze conjoint analysis studies - guides through attribute/level definition, experimental design, EDSL survey generation, and part-worth utility estimation

Quality standards and guidelines for generating analysis reports across all report-producing skills

Write a detailed referee report for an academic paper in economics or a related discipline

Create AgentLists from web searches, descriptions, local files, or programmatic generation

Analyze EDSL Results objects - load by UUID or file path, export survey documentation, and generate analysis reports

Analyze EDSL Results objects - load by UUID or file path, export survey documentation, and generate analysis reports

Answer questions about a generated analysis report - reads report artifacts, performs additional analysis if needed, and saves the answer with metadata

Design complete surveys from free text requirements - generates a Python script with Survey, ScenarioList, and AgentList definitions

Design a detailed experimental plan from a research question - includes literature review, randomization plan, survey design, power analysis, and sample size recommendation

EDSL agent reference - AgentList operations, trait manipulation, templates, codebooks, and instructions

Save/load Surveys, Agents, and AgentLists locally, push/pull to Expected Parrot cloud, git versioning

EDSL survey reference - question types, templating, rules, memory, helpers, and visualization

Publish a completed study to GitHub - creates a repo with the analysis report as README.md, all charts, data, and a reproducibility footer linking to Expected Parrot

Phase 6 — Generate the REVIEW.md report by walking the append-only review tree. Optionally create GitHub Issues.

Add a custom issue spotter for the paper review. Describe what to look for and this will create the spotter file.

Phase 1 — Run the chunks x issue_spotters cross-product to find candidate issues. Uses edsl for parallel LLM review.

Phase 3 — Deduplicate confirmed issues by writing a dedup.json mapping file. No files are moved or modified.

Draft author responses for each confirmed issue. Writes response.json next to each issue (append-only).

One-shot holistic referee review of the full paper. Issues are written to .review/holistic/ as append-only issue.json files.

Phase 2 — Investigate candidate issues. Writes investigation.json next to each issue.json with evidence and a confirm/reject verdict.

Run a full paper review pipeline (append-only). Builds a .review/ tree where each phase writes new files, never modifying existing ones.

Performs qualitative coding and thematic analysis of text corpora using the bewley CLI and EDSL. Covers project setup, open coding, code refinement, annotation, memo-writing, and export. Use when the user wants to analyze text of any kind -- transcripts, speeches, reviews, articles, field notes, open-ended survey responses, social media posts, or any unstructured text data. Triggers on requests to code, tag, theme, categorize, or find patterns in text, including content analysis and discourse analysis.