Research

Fetch, organize, and analyze LangSmith traces for debugging and evaluation. Use when you need to: query traces/runs by project, metadata, status, or time window; download traces to JSON; organize outcomes into passed/failed/error buckets; analyze token/message/tool-call patterns; compare passed vs failed behavior; or investigate benchmark and production failures.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls

Diagnoses dbt Cloud/platform job failures by analyzing run logs, querying the Admin API, reviewing git history, and investigating data issues. Use when a dbt Cloud/platform job fails and you need to diagnose the root cause, especially when error messages are unclear or when intermittent failures occur. Do not use for local dbt development errors.

Interactive debugging companion for Hive agents - identifies runtime issues and proposes solutions

Verify claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that MUST use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Triggers on "fact check", "verify claims", "check against primary sources", or when backlog items are marked UNVERIFIED.

What will competitors do? — Competitive method progress prediction and time window analysis

Predict competitor progress, publications, and strategic moves

Analyze competitor IP portfolios — comparative patent portfolio reports with strategy inference. Budget: 120 patent families, 15 claim parses, 40 web searches.

Tactic: 多假设管理——生成竞争假设，设计区分性预测，构建结构化比较矩阵

SOP: 为同一现象生成机制上不同的竞争假设

Strategy: 为同一现象构建多个竞争假设

Execute a pairwise comparison between two candidates, producing a judgment with winner, confidence, and reasoning.

Design fair comparison experiments against baselines and competing methods

Strategy: 构建对比性研究问题 — A vs B 的系统化比较

Compare feasibility across multiple candidates using multi-dimensional radar and weighted feasibility index.

Synthesize all combinatorial creativity outputs

Combinatorial Creativity Campaign — produce emergent concepts via concept blending, multi-level bisociation, and function combination (Fauconnier-Turner)

Evaluate new combinations for feasibility and novelty

Strategy for multi-judge ranking aggregation using Condorcet, Schulze, Borda, Kemeny-Young, and Copeland methods to produce consensus rankings from diverse perspectives.

Full crystallization strategy for users who have no research direction at all. Covers actor profiling, landscape reconnaissance, direction narrowing, obstacle analysis, goal decomposition, and north-star synthesis. Use when the user's first message reveals zero specificity about what they want to research.

Strategy for auditing preference consistency using Consistency Ratio, cycle enumeration, and mElo to detect and resolve intransitivities.

Identify natural opinion clusters from collected judgments and characterize each cluster.

Apply Goldratt's 8 Categories of Legitimate Reservation to validate causal claims. Tests clarity, existence, sufficiency, and logical integrity.

Strategy: Lewis Possible Worlds — find the minimal change to reality that would flip the conclusion, measuring how close the nearest world where the conclusion fails.