@lijigang

ljg-x-download extracts media from x.com and twitter.com post links via yt-dlp, saving files to ~/Downloads. supports multiple url formats including t.co redirects.

ljg-think recursively deconstructs ideas by drilling vertically through explanatory layers until reaching irreducible axioms. it trades procedural rigor for poetic framing, making the intent clear but execution vague.

ljg-invest produces investment analysis reports centered on a single question: whether a project creates new order or merely rearranges existing structures. the core framework treats wealth as desire-illuminated order, with five structured sections evaluating flywheel dynamics, resilience, and market perception gaps.

ljg-skill-map scans installed skills and renders a categorized ascii visualization showing name, version, description and invocability. designed for operator inventory review.

ljg-qa extracts argumentative structure from source material by deriving sharp q-a chains that expose authorial reasoning rather than summarizing or listing facts. reader walks the logic chain, each answer anchors understanding without spoiling the next question.

ljg-rank decomposes domains into their minimal independent generators, using Deutsch's epistemological criteria (reach and hard-to-vary) to identify explanations that cannot be altered without collapsing predictive power.

ljg-present renders org-mode outlines as full-screen presentation slides with bold typography and color themes (black/red/yellow/cyber). preserves source structure without editing, auto-hyphenates by character count, maps hierarchy to page types via rules.

ljg-learn deconstructs concepts through eight dimensional analysis (history, dialectics, phenomenology, linguistics, formalization, and others) to distill insight. procedure is skeletal and metaphorical rather than executable.

ljg-plain is a rewriting skill that simplifies content for a 12-year-old audience. it enforces oral naturalness, zero jargon, concrete language, and short sentences via red-line constraints, with optional ascii-based tooling (analogy, narrative, diagrams). form follows content.

ljg-paper is a framework for extracting actionable insights from academic papers written in chinese. it prescribes an org-mode template and nine-step workflow emphasizing narrative clarity over academic rigor, with heavy emphasis on title distillation and example-driven explanation.

Book reader that reconstructs a book as x -> f -> f(x): the problem it addresses, the author's central answer, and how that answer changes judgment or action.…

把 ~/.agents/skills/ljg-* 里所有更新过的 skills 同步到 github repo (ljg-skills)，先推 master 分支（org-mode 输出风格），再切 md 分支（markdown 输出风格）做基础 markdown 化后推。Use when user says…

Reading companion agent. Accompanies user through any text (books, articles, essays, papers, news) with translation, structural annotation, deep questioning,…

Word flow: deep-dive word analysis + infograph card in one go. Takes one or more English words, runs ljg-word (generates deep semantics analysis) then ljg-card…

论文倒读法：给一篇论文，递归找出它批判和改进的前序论文（最多5层），再找它之后的最新进展，从源头正向讲述问题演化史。以问题为轴，费曼式讲解每篇论文看到的问题和解法创新。Use when user shares a paper and wants to understand its intellectual…

Relationship analyst combining structural diagnostics (5-layer framework) with psychoanalytic depth (transference, unconscious patterns, resistance). Guides…

Paper workflow: read papers + cast 取景框 library cards in one go. Takes one or more arxiv links, paper URLs, PDFs, or paper names. For each paper, runs ljg-paper…

Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user asks to explain/master a specific…

写作引擎。像手术刀剖开一个观点，一层层剥到底。1000-1500 字。

一个议题，一场圆桌：主持人请来 3-5 位真实人物，定义开场，逐轮交锋， 每轮收一张 ASCII 结构图，用户用指令控节奏（可/止/深入此节/引入新人物）， 散场后全文存入 org 笔记。Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to…

Content caster (铸). Transforms content into PNG visuals. Seven molds: -l (default) long reading card, -i infograph, -m multi-card reading cards (1080x1440), -v…

Deep travel research workflow for museums and ancient architecture. Input a city name, auto-generates structured knowledge document (org-mode) + portable…