documents Skills

Map an unfamiliar repository once and leave sparse AGENTS.md files: layout, commands, gates and traps. Use when onboardi...

Make a .pptx slide deck from a request or sources in a chosen design direction, gate it mechanically, then look at every...

Local document and PDF parsing with spatial text and bounding boxes. Use for extracting text from PDFs, DOCX, Office fil...

Local document and PDF parsing that returns spatial text with bounding boxes. Use for extracting text from PDFs, DOCX, O...

Export existing PDF, Zotero, or WoS records to Excel and CSV while preserving sources, evidence scope, and missing value...

Use during literature review or introduction drafting to extract gaps between current literature (AS-IS) and proposed co...

将 ppt_content.md 转换为完整的 .pptx 演示文稿。当用户已有 ppt_content.md 文件（由 literature-review-ppt-generator 生成）并要求生成 PPT、制作幻灯片、导出 pptx、...

为学术论文生成5分钟文献汇报PPT内容（2-3页）。当用户上传PDF论文并要求制作文献汇报、组会汇报、论文分享、paper presentation、读论文做PPT时触发。输出 paper_summary.md（论文总结）和 ppt_con...

새 주제의 선행 연구를 찾고 가장 가까운 논문과의 차이를 정리할 때, 신규성 관문을 위해 학회와 프리프린트를 전수 대조할 때, 또는 결과가 이미 알려진 정리와 같은지 확인할 때 사용. "관련 연구 찾아", "선행 연...

Create and maintain structured design documentation that drives development. Use for new projects, design decisions, gro...

把长期项目的文档当成一个小系统来维护，防止文档腐烂——四份各司其职的脊柱文件（CLAUDE.md 共享章程 / CLAUDE_MAP.md 地图 / PROJECT_STATUS.md 健康仪表盘 / PROJECT_LOG.md 流水账）...

Paper reader for non-academics. Takes a paper and extracts its ideas for personal use. Focuses on understanding, not aca...

Reading companion agent. Accompanies user through any text (books, articles, essays, papers, news) with translation, str...

Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user...

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

Company formation and LLC setup by country — costs, timelines, requirements, and tax notes. Use when the user asks about...

Hunt vulnerabilities in LLM-powered applications — direct/indirect prompt injection, system prompt extraction, ASCII smu...

A technique skill uses the same engine as genre skills. Use it whenever a task is tagged LLM, NPC

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementa...

Build external-knowledge wikis.

Karpathy 风格 LLM Wiki / markdown knowledge base 工作流。用于 ingest、query、lint 持久化知识库；先做 orientation，再按 analysis -> generation...

Bootstrap and maintain an LLM-generated wiki knowledge base in a project, following the llm-wiki pattern (persistent, co...

Search, ingest, create, and maintain notes in a topic-specific personal wiki (raw sources + cited wiki pages), following...

Audits any domain's AI-readiness by using curl to directly probe robots.txt, llms.txt, and llms-full.txt, then scores ea...

Generate a spec-compliant llms.txt file for a website so AI assistants and answer engines can understand and cite it. In...

Creates 2 backend docs (api_spec.md, database_schema.md). L3 Worker invoked CONDITIONALLY when hasBackend or hasDatabase...

Creates test documentation (testing-strategy.md + tests/README.md). Establishes testing philosophy and Story-Level Test...

Creates .pi/skills from procedural doc sections with proper structure and transformation

Defines measurable architecture drivers and constraints before system design; edits architecture docs only.

Use when an evaluation run needs review-driven documentation updates and a structured documentation summary.

Reviews a concrete implementation plan for missing decisions, feasibility and risk before execution; read-only.

Coordinates documentation audit across structure, semantic content, fact-checking, and code comments. Use when auditing...

Checks hierarchy, links, SSOT, compression, requirements compliance, freshness, legacy cleanup. Use when auditing docume...

Drafts or publishes authorized, fact-checked GitHub Discussions announcements; does not create releases.

Creates a project baseline of architecture drivers and constraints. Use before design or planning; not for target design...

Loads documents fully into the main agent's context so the agent can answer questions, summarize, or work with that cont...

local-discovery — Find local events, venues, and activities — ad-hoc web discovery when the user asks 'what's happening'...

Ground agent answers in local library documentation (pydoc, go doc, vendored READMEs, help() in REPLs) rather than routi...

本地 Python 第三方工具集成的 AI 辅助工作流。当用户需要以下操作时激活：(1) 获取股票、基金、期货、宏观等金融数据（akshare/tushare）；(2) 创建或编辑 Word、Excel、PowerPoint 文件（pyth...

Repo-level docs router: classify documentation requests, propose paths and filenames, and keep indexes in sync.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and hum...

Public repo identity – use in README and published repos. For your identity, use local-identity (gitignored) or copy fro...

Compute the LogAUC metric — provided by torchmetrics. Use when the user has predictions and ground-truth and needs to co...

超长文档生成工具，支持项目文档、商业文案、技术规格书。触发词：生成文档、写方案、技术规格书。

Plan, outline and write a long-form X or LinkedIn article in the author's voice from their notes and real examples, then...

Patterns for individual long-form content pieces. Case studies, whitepapers, research reports, definitive guides, manife...

Generates comprehensive blog post drafts with proper structure. Use when the user asks to write a full article, create b...

Use when work on one subject runs over many sessions and iterations, with verifiers and the person judging as it goes, a...