andrehuang

Map a subfield by discovering, organizing, and cross-linking research papers into a persistent, wiki-integrated lit workspace. TRIGGER when the user wants to build a literature review, survey a subfield, do a paper search, find related work, or map what exists on a topic. Also triggers on "find me papers on...", "what papers exist about...", "related work for...", "literature search", "paper survey", or any ML/social-science conference/venue name. Maintains per-topic memory-bank.md, mind-graph.md, and references.bib under wiki/queries/<topic>/. Chains to /paper-read for per-paper summaries and deep-read ingestion; chains to /research-companion for idea triangulation. Adapted from bchao1/paper-finder to fit the Researcher Pack's wiki model.

Read, discuss, and optionally ingest a research paper. TRIGGER when the user wants to read a paper, discuss a paper, ingest a paper into the wiki, or analyze a research document. Provides a 5-phase workflow: Load → Analyze → Discuss → Ingest → Follow-up. Chains to wiki, mental-gym, and research-companion.

Strategic research companion — brainstorm, evaluate, and decide on research directions. TRIGGER when the user wants to brainstorm research, evaluate research ideas, do project triage, or explore a problem space. ALSO TRIGGER when the user proposes a research idea mid-session, shares a hunch, or uses phrasings like "what if…", "I'm thinking…", "maybe we could…", "here's an idea…", "should we try X?", "wouldn't it be interesting if…" — mid-session proposals default to triage mode (pass `triage` or `quick` as the first argument for a fast, single-agent critique; pass `full` or a bare problem space for the 6-phase flow). Orchestrates brainstormer, idea-critic, and research-strategist agents through a 6-phase pipeline: Seed → Diverge → Evaluate → Deepen → Frame → Decide. Includes Carlini's conclusion-first test.

Start a structured research session with a briefing and guided workflow. TRIGGER when the user is starting a work session, wants to know what to work on, or says "research session" / "what should I work on" / "catch me up." Reads research state, presents a briefing, and chains to appropriate sub-skills (paper-read, research-companion, academic, mental-gym).

General-purpose multi-agent orchestrator. TRIGGER when: (1) the task is complex or multi-step — research, analysis, review, planning, debugging, refactoring, or any work that benefits from multiple expert perspectives; (2) the user asks for parallel review or multi-angle analysis; (3) brainstorming, ideation, or creative exploration is requested; (4) the task spans multiple files, domains, or concerns. Coordinates specialist agents in parallel, synthesizes findings, and drives iterative improvement. For academic writing specifically, prefer the /academic skill if available.

>-

Strategic research companion — brainstorm, evaluate, and decide on research directions. TRIGGER when the user wants to brainstorm research, evaluate research ideas, do project triage, or explore a problem space. Orchestrates brainstormer, idea-critic, and research-strategist agents through a 6-phase pipeline: Seed → Diverge → Evaluate → Deepen → Frame → Decide. Includes Carlini's conclusion-first test.

Strategic research companion for Codex. Use when the user wants to brainstorm research directions, evaluate ideas, assess project strategy, or run a structured ideation session from vague topic to pursue/park/kill decision.

Strategic research companion — brainstorm, evaluate, and decide on research directions. TRIGGER when the user wants to brainstorm research, evaluate research ideas, do project triage, or explore a problem space. Orchestrates brainstormer, idea-critic, and research-strategist agents through a 6-phase pipeline: Seed → Diverge → Evaluate → Deepen → Frame → Decide. Includes Carlini's conclusion-first test.

Session continuity — save structured task state so the next conversation picks up where you left off. TRIGGER when the user says /handoff, "save progress", "let's pause here", "wrap up", or is ending a complex multi-step session. Also trigger when resuming: "pick up where I left off", "check handoffs", "what was I working on".

>-

Academic writing multi-agent orchestrator. TRIGGER when: user is editing .tex files, reviewing thesis/paper chapters, drafting academic content, checking writing quality, or analyzing research positioning. Coordinates specialist agents in parallel for review, research, drafting, polishing, figure work, bibliography auditing, and literature surveys.

Echo prediction intelligence for Polymarket. Analyzes prediction markets using Map-Reduce multi-agent research (parallel subagents for polling, institutional, base rates, economic, and timeline analysis), domain-specific rubrics, and structured output with evidence classification, counterfactual fragility, and monitoring recommendations. Inspired by UniPat AI's Echo system.

Produce a scholarly, annotated, bilingual HTML "critical edition" translation of an academic text (journal article, book chapter, essay), chapter by chapter. Use this skill whenever the user wants to translate a research paper, academic article, scholarly book, or long intellectual text into another language — especially Chinese — and wants it as a polished reading document rather than a bare translation. Trigger this for any request like "translate this paper / article / chapter", "做成中英对照 / 带注释的译本", "翻译这篇论文并做成 HTML", or when the user uploads a scholarly PDF and asks for a translation, even if they don't explicitly say "HTML" or "skill". Handles unified terminology, key-term annotation with original-language glosses, translator's notes (校注) for proper nouns and historical context, faithful figure extraction from PDFs, native rebuilding of important tables, and reading navigation (table of contents, hover footnotes). Default target language is Chinese; adapt for others.