WenyuChiou
@WenyuChiou
Public Skills
knowledge-base
by WenyuChiou
"Research Hub pipeline for academic literature management. Searches papers (arXiv, Semantic Scholar, CrossRef, PubMed), saves to Zotero with collection assignment, creates Obsidian notes with auto-generated summaries, rebuilds hub index, and uploads to NotebookLM. Use when the user mentions Research Hub, finding papers, literature search, Obsidian notes, knowledge base, NotebookLM, paper management, citation graph, research gaps, or says '幫我放到Research Hub'."
gemini-delegate
by WenyuChiou
"Delegate CJK/Chinese content tasks to Gemini CLI. Use this skill for writing Chinese reports, Threads posts (美洲更新), comments, translations, and any task requiring native-quality Traditional Chinese output. Gemini handles the content generation while Claude plans, reviews, and integrates."
agent-task-splitter
by WenyuChiou
Use when the user asks to split a goal across Claude, Codex, or Gemini (gemini requests are rerouted - lane deprecated); 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).
agent-acceptance-gate
by WenyuChiou
Use when a multi-agent round needs a pre-merge gate, pre-commit check, verification before push, or a PASS/FAIL decision after reconciliation.
agent-output-reconciler
by WenyuChiou
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.
agent-context-budget
by WenyuChiou
Use when multi-agent work risks context overflow, memory growth, noisy logs, oversized handoffs, cross-session continuation, or parallel Codex and Gemini execution.
agent-plan-act-reflect
by WenyuChiou
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.
agent-debate
by WenyuChiou
Use when a consequential decision needs adversarial review, opposing agent arguments, a second opinion via debate, or explicit trade-off analysis before implementation.
agent-shared-memory
by WenyuChiou
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.