Research

Use when assembling the AEA Data and Code Availability deposit for an AER, AER:Insights, or AEJ acceptance, writing the README, or auditing a replication package before the AEA Data Editor review. Implements the current AEA policy, including the February 2026 Data and Code Availability Policy.

Use when responding to a Revise & Resubmit decision from AER, AER:Insights, or an AEJ, and a point-by-point response letter plus aligned manuscript revisions are needed. Handles triage, the concede / clarify / push-back decision, and the response-letter format that editors actually read.

Use when drafting or rewriting the introduction of an economics manuscript targeted at AER, AER:Insights, or an AEJ, or when compressing an abstract to the mandatory 100-word limit. Implements the Keith Head / Bellemare five-paragraph formula and AER-specific formatting conventions.

Use when selecting, implementing, or stress-testing the causal identification strategy for an empirical economics manuscript — difference-in-differences (including staggered designs), instrumental variables (including weak-IV-robust inference), regression discontinuity, synthetic control, or shift-share / Bartik. Apply before writing the introduction or results.

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

Given a set of changed or affected spec nodes, perform BFS forward-impact propagation through the CEG to identify all downstream documents that may need updating. Also surface any CoDD `conventions:` / `must_review` alerts attached to the changed node or its immediate parents. Results are classified into Green / Amber / Gray bands.

Extract gap-indicating sentences and phrases from papers/reviews. Identifies linguistic markers of research gaps (e.g., "remains unclear", "has not been explored", "limited understanding").

Generate solutions targeting specific coverage gaps — detect gaps, generate failure-driven solutions, and design factor-level experiments.

Classify identified gaps using Miles 7-type taxonomy and AHRQ 4-reason framework. Determines gap type (theoretical, methodological, empirical, etc.) and root cause of gap existence.

Gap Analysis Campaign — identify, classify, validate, and prioritize research gaps via systematic evidence mapping. 5 strategies (gap-identification, gap-classification, gap-validation, gap-prioritization, gap-synthesis), 3 tactics, 12 subagent SOPs.

Aggregate probability judgments across perspectives using Real-Time Delphi or prediction market mechanisms.

Project solution effects using Future Reality Tree logic

Build biological system functional model. Map energy, matter, and information flows.

Map technical functions to biological functions, find organisms solving equivalent problems. Deep functional matching across domains.

Remove components while preserving function via TRIZ trimming methodology. Simplify systems by redistributing functions.

Redistribute functions across different components

Build substance-field functional model of a system, annotating useful, harmful, insufficient, and excessive interactions.

TRIZ function analysis: function-level recombination and redistribution

FMEA Step 3: Decompose artifact into function tree — identify what each component is supposed to do before analyzing how it can fail.

Produce a complete ordering of all candidates using PROMETHEE I/II, ELECTRE III, or MAVT methods.

Tactic: 选择最适合的 RQ 框架并系统应用

SOP: 根据研究类型匹配最适合的 RQ 框架

Strategy: 选择 RQ 框架（PICO/SPIDER/SPICE/ECLIPSE）并系统应用