WenyuChiou

Operate research-hub workflows for literature discovery, source ingest into Zotero/Obsidian/NotebookLM, dashboard inspection, and vault maintenance. Use when the user asks to find papers and organize them, build a knowledge base, ingest a folder of PDFs, upload to NotebookLM, generate research briefs, inspect clusters, or maintain a research vault. NOT for auditing or cleaning up an existing Zotero library — that's `zotero-library-curator` (read-only audit) plus `zotero-skills` (for CRUD).

After research-hub ingests a cluster of cited papers, fill the per-paper Key Findings + Methodology + Relevance sections in BOTH Obsidian markdown and the Zotero child note. Use when the user says "fill the TODO Key Findings/Methodology blocks left by research-hub auto", "I just ran auto and don't know what these papers are about", or "summarize the papers in cluster X". Invokes a supported LLM CLI on each paper's abstract. NOT for summarizing the user's own manuscript draft — that's `paper-memory-builder`. NOT for cluster-level briefs — that's `research-hub notebooklm generate`. This skill is per-cited-paper only. If the user says "extract claims from these papers", disambiguate before acting: their own manuscript draft → `paper-memory-builder`; a cross-paper comparison matrix → `literature-triage-matrix`; per-cited-paper Key Findings → this skill.

Research-domain router that writes `.coord/multi_ai_plan.md` when a single round of work will need two or more delegates AND the work touches research-hub artifacts (`.research/`, `.paper/`, Zotero/Obsidian/NotebookLM pipelines). For a single delegate, use `codex-delegate` or `gemini-delegate` directly — do not invoke this skill. For generic non-research multi-agent decomposition (pure code refactor, generic translation, no research-hub artifact), use `agent-collab-workspace:agent-task-splitter` instead (different artifact `.coord/plan.yml`, different scope). The router decides task splitting, dependency ordering, and reconciliation; the leaves execute.

Audit and curate a Zotero library — find duplicate DOIs, orphan items missing required tags, propose collection rebinds, identify bloated or under-used collections, generate tag hygiene reports, emit preview-only cleanup plans. Use when the user asks to "audit Zotero", "find duplicates", "tag hygiene report", "which collections are bloated or under-used", or "propose a Zotero cleanup plan". Defers all CRUD operations to the standalone `zotero-skills` skill or `research-hub zotero` CLI. Includes a backup-first reminder before any apply/CRUD handoff suggestion.

Use research-hub to operate Zotero, Obsidian, and NotebookLM research workflows through CLI, MCP, REST, and dashboard. Trigger when the user asks to find papers, ingest sources, organize a literature review, build Obsidian research notes, upload sources to NotebookLM, inspect clusters, generate AI briefs, or maintain a research vault.

Convert a paper draft + figures + Zotero metadata into reusable .paper/claims.yml and .paper/figures.yml files so the academic-writing-skills skill can do writing, revision, and audit passes without re-reading the manuscript every time. Use when the user asks to "build paper memory", "extract claims from this manuscript", "extract claims, supporting evidence, and figure key numbers", or "prepare this paper for AI-assisted writing". NOT for summarizing cited papers in a literature cluster — that's `paper-summarize`. This skill is for the user's own manuscript draft only.

Guide a researcher through 5 Socratic segments — research question sharpening, expected mechanism, identifiability check, validation plan, risk register — and produce `.research/design_brief.md`. Use when the user asks to "frame this research question", "design my study", "help me think through what model to build", "sharpen my hypothesis", "is my research question sharp enough to be falsifiable?", or "before I start coding, walk me through the design". Runs AFTER a topic is chosen — it designs the study for a given question; to decide whether a research gap is worth pursuing at all (open / a contribution / feasible), use `gap-to-topic`. Does NOT write the model spec; does NOT invent the research question — guides the human to articulate them.

Inspect a research repository and write a compact `.research/` workspace manifest (project_manifest.yml, experiment_matrix.yml, data_dictionary.yml) so future AI sessions can orient themselves without rescanning the whole repo. Use when the user asks to "compress this project context", "create a research manifest", or "save the project context for future agents".

Use when the user asks to split a goal across Claude, Codex, or Gemini; plan a multi-agent run; break work into parallel agent tasks; or decompose a large task that needs bounded context handoffs. This is the **generic** multi-agent task splitter — writes `.coord/plan.yml` (a DAG) plus per-agent task files. NOT for research-domain routing that touches `.research/`, `.paper/`, or Zotero/Obsidian/NotebookLM ingest pipelines — for those, use `research-hub-multi-ai` instead (different artifact `.coord/multi_ai_plan.md`, research-hub-aware reconciliation).

Use when a multi-agent round needs a pre-merge gate, pre-commit check, verification before push, or a PASS/FAIL decision after reconciliation.

Use when multi-agent work risks context overflow, memory growth, noisy logs, oversized handoffs, cross-session continuation, or parallel Codex and Gemini execution.

Use when multiple agents have completed a round and the user asks to reconcile outputs, compare Codex and Gemini, synthesize run results, identify conflicts, or decide what should be retried.

Use when a task needs single-agent self-correction across multiple iterations — write plan, execute, critique own output, revise plan, re-execute, until convergence or budget exhausted. Different from `agent-debate` (which is 2 agents arguing pro vs con); this is 1 agent looping over its own work.

Use when a consequential decision needs adversarial review, opposing agent arguments, a second opinion via debate, or explicit trade-off analysis before implementation.

Use when the user asks to update shared memory, initialize multi-agent memory, summarize decisions so far, identify open questions, or prepare a fresh session primer.

Turn raw WAGF audit traces (household_governance_audit.csv + raw/*.jsonl) into paper-ready governance metrics — IBR, EHE, rejection taxonomy, retry outcomes, model-condition comparisons. Use when the user says "analyze these traces", "compute governance metrics", "summarize rejection and retry outcomes", or hands over a results directory and asks "what does this say".

Walk a researcher (PhD, collaborator, lab-mate) through building their first single-agent WAGF domain — from "I have a research question + maybe an external model" to "I have a working WAGF experiment producing audit traces." Conducts a structured S0-S7 interview, invokes `broker.tools.scaffold_domain` at S4, guides 4 surgical edits in S5, and runs `broker.tools.validate_prompt` after every change. Hands off to `wagf-coupling-designer` for any coupling work and to `wagf-experiment-designer` / `abm-reproducibility-checker` once the domain runs green. Use when the user says "I want to build a WAGF model for <my domain>", "help me set up a new domain", "I'm new to WAGF and have a research question", or "scaffold a domain from scratch".

Verify the contract between WAGF/ABM agents and an external model (flood, hydrology, irrigation, seismic, catastrophe) — units, time steps, state mutation direction, feedback-loop double-counting. Use when the user says "check ABM-model coupling", "audit feedback loop", "verify units between WAGF and X model", or asks to confirm an external-model integration is safe.

Walk a researcher through designing the LLM↔external-model interface — decision flow IN, observation flow OUT — for a single-agent WAGF domain. Emits a coupling contract, a working mock adapter, and a pattern-specific real-model adapter scaffold so the WAGF side can be built and smoke-tested BEFORE the real model is wired in. Use when the user says "I want to couple my LLM agents to <my simulator>", "help me design the WAGF↔X interface", "scaffold the external model adapter", "draft a coupling contract", "I have a Python / R / CSV-based model and want WAGF to drive it". Sister skill to `model-coupling-contract-checker` (which AUDITS existing contracts; this one DESIGNS new ones).

Verify another researcher can reproduce a WAGF experiment — manifests, seeds, configs, runnable commands, data provenance vs git blame, figure-script outputs match references. Use when the user says "audit reproducibility", "prepare for submission", "check this experiment folder", or any time a results directory needs a pre-publication integrity sweep.

First-time WAGF setup walkthrough — environment check, smoke test, first experiment, and handoff to the four lifecycle skills. Use when the user says "I just cloned WAGF", "set up WAGF", "first WAGF run", "I'm new to this", "where do I start with WAGF", or opens a Claude Code session in a freshly-cloned WAGF repo without a clear task.

Turn a WAGF research question into a reproducible experiment matrix (model × governance × seed × metric × artefact path). Use when the user says "design an experiment", "plan an ablation", "compare strict vs disabled", "set up cross-model evaluation", or wants a runnable matrix written to .research/.

When the user is building a tool-calling agent and gets stuck — "為什麼 LLM 不呼叫我的 tool", "我這 schema 哪裡寫壞", "tool 被呼叫但 args 不對", "ReAct loop 跑不停", "the LLM won't call my tool", "help me design a function schema", "debug this tool-use behavior". Walks them through a 4-branch diagnostic + 5-step schema design walkthrough, with references to bad/good schema A/B and SDK-diff cheatsheet. Do NOT use for: pure LangChain / LangGraph / CrewAI framework questions (route to Stage 4 frameworks), MCP server building (route to cookbook 2), production agent observability (route to Stage 7).

Delegates implementation-heavy or repetitive coding work (batch edits, boilerplate, multi-file refactors with clear patterns, test scaffolding) from Claude to OpenAI Codex CLI. Use when token cost outweighs judgment cost. Trigger phrases include "delegate to codex", "let codex do this", "batch refactor across files", "scaffold tests for". Avoid for architecture, security review, or root-cause debugging.

Delegates large-context reading, bilingual or Chinese (CJK / 中文 / zh-TW) drafting, cross-file synthesis, and second-opinion review to Google Gemini CLI. Use when input exceeds Claude's working budget, when the user writes in Chinese, when terminology must align across long documents, or when a reviewer pass is needed. Trigger phrases include "summarize this in Chinese", "second-opinion review", "long-context synthesis", "draft this in zh-TW". Avoid for bulk code generation or security-sensitive coding.

Full CRUD operations on Zotero library — search, add, update, delete items with notes, tags, collections, and PDF attachments. Uses dual-API architecture (local API for fast reads, Web API for writes). Use this skill whenever the user mentions Zotero, references, citations, literature management, reading notes, or wants to organize academic papers — even if they don't explicitly say 'Zotero'.

End-to-end academic manuscript workflow for drafting, revision, reviewer response, figure-text consistency, claim-evidence audits, and pre-submission checks. Use this skill whenever a user asks for manuscript sections, paper revision, rebuttal letters, journal compliance, overclaim detection, GPT-style prose cleanup, figure captions, or evidence-backed academic writing. It is especially useful for multi-section papers where context, claims, figures, and reviewer comments must stay consistent across revisions. When `.paper/claims.yml` and `.paper/figures.yml` exist (produced by the `paper-memory-builder` skill), use them as ground truth instead of re-reading the manuscript; if they are absent and the task is multi-section / claim-evidence / reviewer-response work, suggest running `paper-memory-builder` first to build the memory layer.

Sweep up ALL session artifacts left behind by Claude Code: stale git worktrees, dangling git refs, and orphaned worktree directories. Use this skill whenever the user mentions slow performance, low disk space, too many worktrees, cleanup, maintenance, freeing space, or wants to reduce clutter from Claude Code sessions. Also triggers for 'my computer is slow', 'running out of space', 'clean up after Claude', or any mention of worktree or session accumulation. Especially relevant for heavy Claude Code users who spawn many code tasks — each task creates a full git worktree copy that persists after the session ends.