PlutoLei

Set up Hermes Agent Feishu/Lark gateway from CLI, including dependency install, TERM=dumb interactive setup, QR/manual credential flow, gateway restart, and daily cron delivery verification. Use when configuring Hermes with Feishu/Lark or troubleshooting Feishu setup.

Operate Claw Email mailboxes via mail-cli. Use for reading, searching, sending, and managing claw.163.com mailboxes and newsletter sub-mailboxes.

Verify a ClawEmail mail-cli setup, test end-to-end send/read flow, and distinguish between mail-cli readiness, OpenClaw email-channel enablement, and Hermes skill integration.

Create polished Feishu/Lark docx reading versions for scheduled digests with real outline headings, wiki archive links, and verification. Use when a digest/newsletter/wiki cron must produce a Feishu doc, not just a message or markdown dump.

Set up a separate project-specific daily “Lens” push via Hermes cron that complements, rather than duplicates, an existing business-intelligence or newsletter digest bot. Use when the user wants a second daily push for a company/project theme with its own wiki area, schedule, and editorial boundaries.

Produce concise Chinese digests of the current Hugging Face Daily Papers weekly page. Use when asked to summarize/trend top papers from huggingface.co/papers/week/current or the Weekly tab on Hugging Face Papers.

Ingest AI newsletters from ClawEmail into a local wiki, extract reusable workflows, and produce bilingual daily digests. Use when operating a newsletter-driven second-brain setup with mail-cli, Hermes, and markdown notes.

Use when user needs academic diagrams, methodology figures, statistical plots, or presentation slides from text descriptions or data files. Also use for evaluating generated figures against references.

Use when user wants to create a full slide deck or presentation using PaperBanana image generation, OR modify/regenerate an existing PaperBanana slide deck. Triggers on "make slides", "create presentation", "PPT", "slide deck", "regenerate slides", "update slides", "paperbanana slides". Also triggers when user has an existing slide-deck directory with outline.md and wants to regenerate images or make changes. This is the PRIMARY slide deck skill — always prefer over baoyu-slide-deck.

Search academic papers across multiple sources at once (OpenAlex, Semantic Scholar, arXiv/Valyu, Perplexity) from a single request, then cross-validate and cross-align the results into one cited synthesis report. Use this whenever the user wants to find papers / literature / prior work / studies on a topic and would benefit from MORE THAN ONE source — i.e. they want it comprehensive, corroborated, triangulated, or cross-checked, or they say things like "多源搜论文", "交叉搜论文", "跨源检索", "find papers on X across sources", "what does the literature say about X", "search arxiv and openalex for X", or ask which findings are agreed-upon vs contested. Strongly prefer this over any single source skill (openalex-paper-search / arxiv-search / perplexity-search / research-lookup) when the goal is a literature scan rather than fetching one specific known paper. The dedup/consensus/coverage alignment is the whole point — don't hand-roll it with one source.

Use when 需要多文件代码实现并要求异源模型（Claude + Codex）交叉审查，或架构方案需要对抗性质询验证。适用于大型编码任务的端到端协作，不适用于单文件小修改或纯数据处理。