knowledge base managed with an LLM workflow
This repository also configures its own agents. See what WEIPING_WIKI tells them →
Skill Codex
A Lark online-document tool for reading, creating, summarizing, translating, reviewing, and editing documents and Wiki pages. A Wiki is a linked collection of knowledge pages.
Skill Codex
A Lark Drive file-management tool for uploading, downloading, organizing, searching, and importing files into online documents, spreadsheets, or databases.
Skill Codex
A Lark messaging and group-chat tool for sending messages, searching chat history, managing members, and handling files, images, and reactions.
Skill Codex
A tool for creating, reading, and replacing Markdown files stored in Lark Drive. Markdown is a plain-text format for writing structured documents.
Skill Codex needs its repo
A tool for finding and calling Lark OpenAPI endpoints that are not already available through the command-line interface. OpenAPI is a documented way for software to access a service.
Skill Codex
Use when first setting up lark-cli, running auth login, switching user/bot identity (--as), handling permission denied or scope errors, needing to update lark-cli, or seeing notice in JSON output.
Skill Codex
A Lark spreadsheet tool for creating and managing workbooks and worksheets, reading and writing cells, finding values, and exporting files.
Skill Codex needs its repo
A guide for creating reusable Lark command skills. A skill is a set of instructions that teaches an agent how to complete a repeatable task.
Skill Codex needs its repo
A Lark presentation tool for creating, reading, and editing slides through a structured XML format. XML is a text format that describes document structure and layout.
Skill Codex
A knowledge-base management tool for Feishu, also known as Lark, a collaboration platform with shared documents and wikis. It manages knowledge spaces, members, document nodes, hierarchy, and shortcuts.
Skill Codex
Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), build a BibTeX file, and draft Introduction +…
Skill Codex
Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimentallog.md, template.tex, conferenceguidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator…
Skill Codex
Run the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App. F.3) — Citation F1 (P0/P1 partition + Precision/Recall/F1), Literature Review Quality (6-axis 0-100 with anti-inflation rules), SxS Overall Paper Quality (side-by-side), and SxS Literature Review Quality (side-by-side). TRIGGER when the…
Skill Codex needs its repo
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper…
Skill Codex
Reverse-engineer raw materials (Sparse idea, Dense idea, experimental log) from an existing AI research paper to build a benchmark case for evaluating paper-writing pipelines. Replicates the PaperWritingBench dataset construction procedure from arXiv:2604.05018 §3 / App. C. TRIGGER when the user asks to "build a…
Skill Codex
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimentallog.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER…
Skill Codex
Create, rewrite, or critique high-quality project README.md files. Use when the user asks to improve README aesthetics, information architecture, onboarding quality, public GitHub presentation, maintainer quick-start docs, repository documentation polish, or a top-tier README rewrite. Also use when README changes must…
Skill Codex needs its repo
Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimentallog.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges…
Skill Codex
A browser-automation tool for publishing videos to WeChat Video Channel, a Chinese short-video platform. It supports login, video and cover uploads, descriptions, scheduled publishing, and drafts through a local Playwright command-line tool.
Skill Claude CodeCodex
A Feishu approval tool for viewing and managing approval requests and approval tasks. An approval task is a request waiting for someone to review and decide.
Skill Claude CodeCodex
A Feishu tool for looking up your own attendance clock-in records. Feishu is a workplace collaboration platform used by many teams.
Skill Claude CodeCodex needs its repo
Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via lark-cli event consume (covers IM message receive, reactions, chat member changes, etc.). Use for Lark bots, real-time message processing, long-running subscribers, streaming webhook/push handlers. Supports --max-events /…
Skill Claude CodeCodex
A Feishu email tool for reading, searching, drafting, sending, replying to, and organizing email. It also handles folders, labels, contacts, attachments, and mail rules.
Skill Claude CodeCodex needs its repo
A Feishu meeting-notes tool for finding recordings, downloading audio or video, and obtaining summaries, action items, chapters, transcripts, or written notes. Feishu Minutes are recordings and related text from meetings or uploaded media.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: