Research

Turns a raw Qualtrics conjoint export into an analysis-ready long-format dataset — export settings and metadata rows, identifying which Qualtrics implementation produced the file, reshaping wide to long by hand or with cjoint read.qualtrics and cjdata reshape_conjoint, mapping the choice variable onto profiles, ratings and secondary DVs, attribute-level translation and factor ordering, pilot data-quality diagnostics, and subgroup merges. Use when the user has a conjoint CSV and asks how to cl...

Audits the citation layer of a manuscript — in-text and reference-list parity, fabricated or nonexistent sources, DOIs that resolve to a different work, style and completeness against APA 7 or a named journal style, and whether each cited work actually supports the claim attached to it. Verifies against Crossref, OpenAlex, DataCite, and Semantic Scholar, drives LaTeX audits off the keys actually cited, and marks anything it cannot check as NOT CHECKED rather than guessing. Use when the user a...

Consult an independent, read-only GPT-6 Astra advisor before committing to a substantive interpretation, approach, or final result. Not for routine work, implementation, or file edits. Defaults to gpt-6-astra at xhigh for demanding reviews.

Structures research papers in IMRaD format (Introduction, Methods, Results, and Discussion) or social sciences format with section-by-section guidance, producing a complete paper framework. Use when the user asks to structure a research paper, write an academic paper, organize a study for publication, or create an IMRaD paper. Do NOT use for literature reviews (use literature-review), abstracts only (use abstract-writing), or editing an existing paper (use academic-paper-review).

Writes thematic literature reviews that synthesize sources into argument-driven narratives rather than sequential summaries. Identifies patterns, gaps, and contradictions across existing research. Use when the user asks to write a literature review, survey existing research, synthesize sources, or map the scholarly landscape on a topic. Do NOT use for single-paper summaries, annotated bibliographies, or research paper structure (use research-paper-structure for full papers).

Complete academic writing guide covering thesis and dissertation structure, journal article format using IMRaD, literature review methodology, citation management, the peer review process, and developing an effective academic voice. Use when the user asks about academic writer, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of academic writer or requires a different specialized skill.

Reviews academic papers for methodological rigor, argument structure, evidence quality, and scholarly conventions. Produces structured peer-review-style feedback with specific, actionable recommendations. Use when the user asks for feedback on an academic paper, manuscript review, or scholarly critique of a research document. Do NOT use for proofreading academic text (use proofreading), writing a paper from scratch (use research-paper-structure), or responding to peer review comments (use pee...

Constructs rigorous academic arguments with clear claims, evidence, warrants, counterarguments, and rebuttals. Produces logically structured argumentative writing for academic contexts. Use when the user asks to write an argumentative essay, build an academic argument, construct a logical case, or develop a position paper with scholarly evidence. Do NOT use for thesis statements only (use thesis-statement), persuasive business writing (use business skills), or personal opinion pieces (use cre...

Evaluates source credibility and relevance using the CRAAP test (Currency, Relevance, Authority, Accuracy, Purpose) and SIFT method for learners assessing research sources. Produces a completed evaluation with credibility ratings -- not a tutorial on critical thinking. Use when a learner asks to evaluate a source, check if a source is credible, assess research quality, or determine if a source is suitable for academic work. Do NOT use for finding sources (use `literature-search`), for citatio...

Compares research methodologies and helps learners select the most appropriate method for their research question. Produces a methodology comparison with rationale for selection -- not a textbook chapter on research methods. Use when a learner asks to choose a research method, compare qualitative vs quantitative approaches, select a research design, or justify their methodology choice. Do NOT use for developing a research question (use `research-question`), for data collection instrument desi...

Research methodology guidance covering literature review strategies, source evaluation using the CRAAP test, citation management, research question formulation, methodology selection (qualitative, quantitative, mixed methods), academic writing structure, and plagiarism avoidance. Use when the user asks about research advisor, or needs help with research methodology guidance covering literature review strategies, source evaluation using the craap test, citation management, research question fo...

Synthesizes and connects concepts across multiple sets of notes for learners, identifying patterns, contradictions, and relationships between sources. Produces an integrative summary that goes beyond individual note sets. Use when a learner asks to connect ideas across notes, synthesize multiple readings, find patterns across study materials, or integrate notes from different lectures or sources. Do NOT use for single-source note taking (use `cornell-notes`), for concept mapping of one topic ...

Creates annotated bibliography entries with summary, evaluation, and relevance notes for learners compiling research sources. Produces complete annotated entries -- not a guide on what annotated bibliographies are. Use when a learner asks to create an annotated bibliography, write source annotations, summarize and evaluate sources for a research project. Do NOT use for finding sources (use `literature-search`), for evaluating single sources (use `source-evaluation`), or for citation formattin...

Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change. Use for evidence-backed coaching proposals, never hot-swaps.

Produce and structure slow-query performance reports for PostHog's production ClickHouse (US and EU). Use when asked for a slow query report, query performance analysis over the last N days, per-team query cost, OOM or timeout investigation, cluster cost/memory regressions, or materialization candidates. Covers the modern `query_log_archive` source (typed `lc_*` columns, multi-day retention), how to categorize and attribute slow queries, root-cause patterns (unmaterialized JSONExtract, high-c...

Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by cross-referencing autocapture events on the same page, and can create a saved heatmap the user opens in PostHog, then summarizes the behavior and proposes improvements.\nTRIGGER when: user asks what a heatmap shows, why people aren't clicking something, where users rage-click, how far they scroll, what to change on a page based on heat...

Signals scout for PostHog surveys. Watches active surveys for score regressions, response- volume drops, abandonment spikes, and targeting drift, and aggregates open-text responses into recurring themes.

Signals scout for observability gaps — significant event volumes with no insight, dashboard, or alert coverage. Recommends new insights, dashboards, or alerts as the product evolves.

Signals scout for PostHog logs. Watches for emerging and rate-shifted message patterns, volume bursts, severity-distribution shifts, service silence, and trace-correlated bursts.

Cross-product Signals scout. Looks for cross-product correlations and explores the surfaces the per-product specialist scouts don't cover.

Signals scout for Content Security Policy violations. Watches `$csp_violation` events for blocked-URL clusters, per-directive bursts, post-deploy regressions, and suspicious third- party domains.

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature flag, and what the next step should be. Pulls aggregated metrics, sample exception events, segment breakdowns, linked replays, and synthesizes a hypothesis-grade summary in one pass.

Extract a written voice profile from your own prior papers, then use it to keep new drafts sounding like you. Reads a corpus one document at a time via subagents, produces a reusable profile on disk (lexicon, sentence rhythm, how you open and close, hedging habits, deliberate quirks), and audits a draft against it. Use when the user says "make this sound like me", "match my voice", "profile my writing", "why does this draft not sound like my papers", or before drafting prose that will carry t...

Prove that the file you are about to send, publish, or hand off IS the thing you mean — before it leaves your hands. Rebuild from source, check integrity, diff the derived artifact against its source, and require the recipient to echo what they received. Use before sending a paper/PDF for review, shipping a release or replication package, handing files to a coauthor or collaborator, uploading anything to an external reviewer or model, or publishing. Prevents an entire review/QA cycle from bei...