Docs & Writing

family3253 Bundle

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

archibate Bundle

Work with PDF files — read or extract text/tables, merge/split, rotate, watermark, fill forms, encrypt/decrypt, extract images, OCR scanned PDFs, or create new PDFs.

archibate Bundle

Create, read, edit, or manipulate Word documents (.docx). Triggers: 'Word doc', '.docx', or requests for reports, memos, letters, or templates with formatting (TOC, headings, page numbers, letterheads). Also extracting content, inserting images, find-and-replace, or tracked changes/comments in .docx files.

archibate Bundle

Create, read, edit, or manipulate PowerPoint files (.pptx). Triggers: 'deck', 'slides', 'presentation', or any .pptx filename — including creating pitch decks, extracting text, combining/splitting files, or editing templates, layouts, speaker notes, and comments.

archibate Skill

Structured workflow for co-authoring documentation, proposals, technical specs, or decision docs — context gathering, iterative refinement, reader testing.

lqf0624 Bundle

Paper reproduction skill for computer systems, networking, and AI research. Use when the user provides a paper PDF, appendix, or repository and wants Codex to reconstruct the method, extract claims and experiments, identify missing details, plan a faithful reproduction, and judge whether the paper is reproducible, partially reproducible, blocked, or contradicted.

motormetrics Skill

Maintain README files with setup instructions, features, tech stack, and usage examples. Use when updating project documentation, adding new features, improving onboarding, or creating READMEs for new packages.

shotaiuchi Skill

AI生成コードのレビュー時に「全体の流れだけを把握するため」のスキミング用ビューを生成するスキル。 指定ファイル群・PR差分・ブランチ差分を入力に、クラス/関数のシグネチャ、既存コメント、 上位レベルの制御フロー、副作用呼び出しだけを残した圧縮ビューをMarkdownで出力する。 他の自作関数を呼ばない「末端関数」の中身は自然言語の1行要約に置き換え、 要約である旨を明示する。コメントが欠落している箇所はレビュー指摘候補として記録する。 「レビュー用に流れだけ見たい」「全体像を掴みたい」「末端の実装は読み飛ばしたい」 「このPRのロジックだけざっと把握したい」等の依頼で使用する。

tuliosousapro Skill

Updates the llms.txt file to reflect changes in documentation. Use when editing repository details or specifications. For creating from scratch, see create-llms.

owo-x-project Skill

Use when updating README.md, CLAUDE.md, directory INDEX.md files, requirement documents, or checking consistency between documentation and implementation.

jangviktor-web Skill

上传1-10份券商研报PDF → 提取核心观点、盈利预测和评级，多份时生成观点分歧矩阵。 触发词："研报摘要"、"研报要点"、"快速阅读研报"、"研报对比"、"帮我看看这几份研报"、 "卖方观点汇总"、"券商观点"、"机构怎么看"、"研报速读"、"各家评级"。

jangviktor-web Skill

输入公司名称和材料 → 撰写券商体例的公司深度研究报告，覆盖行业、商业模式、财务、估值全框架。 触发词："深度报告"、"公司深度"、"首次覆盖"、"帮我写一篇深度"、"公司研究报告"、 "写一篇研报"、"公司分析"、"首覆报告"、"个股深度"。

third774 Skill

Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation. Use when running /init, onboarding to a new codebase, bootstrapping project documentation, or regenerating stale AGENTS.md files.

kreuzberg-dev Skill

Use when fetching a live URL and converting it to Markdown. Covers --url, custom user agents, preprocessing for noisy pages, and the --json ConversionResult shape.

the-fish-salmon Bundle

Ingest a local PDF (or a folder of PDFs) into the Obsidian vault -- extracts DOI/title, resolves metadata via Semantic Scholar, writes 30_Literature/CITEKEY.md.

the-fish-salmon Bundle

Resolve a paper from a DOI, arXiv id, URL, or Author-Year-keyword into the Obsidian vault. Fetches metadata, downloads PDF, writes 30_Literature/CITEKEY.md.

jackal9384 Bundle

写作系统的唯一落盘入口。任何技能不得自行将内容写入本地文件系统——必须经此技能校验通过后统一落盘。校验范围覆盖所有输出类型：正文文本（CPS.json 标点 + Core 结构规范）、JSON 文件（语法/模式/引用一致性）、结构化 Markdown（字段完整性/跨文件引用）。不通过项自动修正至合格后写入。不经校验直接写入视为流程违规。

photostructure Bundle

Set up, assess, or improve stable Rust projects for idiomatic safe code, maintainability, strict but usable rustc/Clippy/rustfmt policy, Cargo workspace and feature design, MSRV/edition/toolchain management, testing and CI, unsafe/FFI boundaries, documentation, crates.io packaging, and release hygiene. Use when asked to create or review a Rust project or Cargo.toml, make a Rust codebase easier to maintain, configure strict lints, reduce or govern unsafe code, add Miri/fuzz/sanitizer checks, structure a workspace, prepare or dry-run a crate publish, or establish Rust release and dependency policy. In assessment mode, produces an applicability-aware Met / Gap / Not applicable / Needs verification baseline rather than claiming bugs or unsoundness.

tmuskal Skill

Generate a scorecard from a completed LongMemEval run - computes overall accuracy + per-question-type accuracy and writes scorecard.json

zhuxining Bundle

面向公募基金的单基金综合诊断能力。适用于用户提出“这只基金怎么样”“适不适合继续持有”“风险和收益特征如何”等泛化问题时，返回结构化的Markdown诊断报告。每次仅分析一只基金，不处理多基金对比与量化建模。触发核心条件：用户问法为概括性诊断，未要求具体指标公式计算或回测建模。

zhuxining Bundle

面向沪深京A股的单票综合诊断能力。适用于用户提出“这只股票整体怎么样”“是否值得继续持有/加仓/减仓”“当前风险和机会如何”等泛化问题时，返回结构化的Markdown诊断报告。每次仅分析一只股票，不处理港股/美股及多标的对比。触发核心条件：用户问法为概括性诊断，未指定某个单一技术指标或财务指标（如MACD、RSI、ROE等）做精确计算。

zhuxining Bundle

依托东方财富数据库，为指定行业生成深度研究报告。 当用户问题中出现可识别的行业/产业/领域主体，且意图属于行业认知、产业剖析或撰写研究报告时，应触发本 Skill。 常见表述如「XX 行业研究」「XX 行业报告」「帮我分析 XX 行业」「XX 产业深度研究」「XX 领域市场分析」等。 即使用户未明说「报告」，只要以某一行业为核心、要求系统性或深度的研究/分析，同样适用。

microsoft Skill

Process PDF files including text extraction, rotation, and merging. USE FOR: "extract PDF text", "rotate PDF", "merge PDFs", "split PDF pages", "convert PDF to text". DO NOT USE FOR: creating PDFs from scratch (use document-creator), editing PDF forms (use form-filler).

lobehub Bundle

End-to-end verification and self-evidence for a delivery in any repository, with or without a preconfigured verify plan. Discover an existing plan when one was handed to this run; otherwise author checks and publish a standalone acceptance. Pick the proving surface (CLI / web / desktop / iOS Simulator), drive the real product, capture visually confirmed evidence, and publish a round with the lh CLI. Triggers on 'verify the task', 'collect evidence', 'prove it works', 'upload evidence', 'verify plan', 'requiredEvidence', 'local test', 'manual test', 'test report', 'test with cli', 'test in electron', 'test desktop', or any local end-to-end verification task. Needs no ambient ids, and never depends on running inside a LobeHub conversation.

s1lverelixir Skill

Report this session's output tokens and CO2 by running the repo's committed EcoLogits port, plus the modelled CO2/$ saved vs a no-Honey baseline - always labelled with the bench stamp it came from. Use when asked how much Honey saved, the session's carbon/token footprint, or to expand the statusline badge into a full breakdown.

s1lverelixir Skill

Harvest every `honey:` comment in the codebase into a debt ledger, so the deliberate shortcuts Lever 1 leaves behind get tracked instead of rotting into "later means never". Flags markers with no revisit trigger - those are the ones that go permanent silently. Use when the user says "honey debt", "/honey-debt", "what did honey defer", "list the shortcuts", or "what did we mark to do later". One-shot report; changes nothing.

s1lverelixir Skill

Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session. Stores only the stable, expensive-to-rediscover, not-in-the-code context - architecture + why, build/test/run commands, decisions and dead-ends - as human-readable markdown, versioned with the code so it can't silently rot. Use when asked to set up project memory/context, stop agents re-grepping the codebase, scaffold or refresh a PROJECT.md / CLAUDE.md memory section, or cut cold-start rediscovery cost. Prose context only - never code, config, or data.

shotaiuchi Skill

ユーザーの質問に「回答のみ」を返す読み取り専用Q&Aスキル。 PR/ブランチ/コミット履歴、仕様・ドキュメントとの整合性、実装の妥当性や設計判断について、 「〜はどうなってる？」「〜で合ってる？」「〜の理由は？」「このPRの変更意図は？」 「このブランチは何のため？」「この実装で問題ない？」「仕様と矛盾してない？」 等の質問に対して、コード・git履歴・ドキュメントを調査して回答する。 ユーザーから明示的に指示されない限り、ファイル編集・コミット・PR操作など一切の変更を行わない。 セッション終了時または明示要求時に、Q&Aテーブルと詳細レポートを単一のMarkdownファイルに出力する。

bitsocialnet Bundle

Retrieve library documentation with Context7 when the current task needs version-specific API guidance or a concrete documentation lookup.

gabonio Bundle

Read-only pressure test for a specification, plan, architecture, implementation, current diff, or readiness claim. Use only when explicitly requested to run an adversarial review, challenge assumptions, find hidden flaws, pressure-test decisions, or argue against readiness. Report three or four evidence-aware findings per pass without inventing objections.

jazzenchen Skill

Start a VibeAround Preview for either a running local web server or a Markdown file. Use after starting a dev server, after creating or updating Markdown, or when the user asks to preview a browsable artifact.

jazzenchen Skill

Start a VibeAround Preview for either a running local web server or a Markdown file. Use after starting a dev server, after creating or updating Markdown, or when the user asks to preview a browsable artifact.

jiahongc Skill

Return a compact full report for one major-US credit card, covering fees, offer, earnings, redemption, credits, travel benefits, protections, mechanics, eligibility, and strategy. Use when the user wants the whole card picture.

open-mercato Skill

Implement a specification (or specific phases of a spec) using coordinated subagents. Handles multi-phase spec implementation with unit tests, integration tests, documentation, and code-review compliance. Use when the user says "implement spec", "implement the spec", "implement phases", "build from spec", or "code the spec". Tracks progress by updating the spec with implementation status.

smallnest Skill

Edit PDFs with natural-language instructions using the nano-pdf CLI.

smallnest Skill

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.