Docs & Writing

moonlarry Bundle

Review paper text or PDFs from a final-check or reviewer perspective. Use when the user wants fatal logic checks on English LaTeX, or a harsh reviewer-style report on a full paper PDF with concrete rejection risks and revision advice.

moonlarry Skill

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"build PDF\", \"生成PDF\", or wants to compile LaTeX into a submission-ready PDF.

moonlarry Bundle

Translate and rewrite academic paper text across Chinese and English. Use when the user wants Chinese-to-English LaTeX translation, English-to-Chinese literal translation, or Chinese academic paragraph rewriting for Word-style manuscripts.

moonlarry Bundle

Perform high-intensity global polishing for Chinese academic writing in either Word-style plain text or Chinese LaTeX. Use when the user wants section-level or document-level rewriting with global logic checking, outline reconstruction, compression, sentence-level polishing, and a final reviewer-style pass, or when the user explicitly asks for a staged structure-to-logic-to-expression Chinese polish workflow with confirmation checkpoints.

nearform Bundle

Build an interlinked markdown knowledge graph of an unfamiliar codebase and explore it. Scans the project, extracts modules/functions/relationships, writes one-concept-per-note Obsidian/Quartz/Foam-compatible markdown with [[wikilinks]] and backlinks, maps architecture and domain, and offers a guided tour. Adaptively asks which capabilities you want — knowledge notes, a Quartz graph viewer, a query/explore interface, incremental re-analysis on commits — and provisions only those. Use when onboarding to a new project, reverse-engineering legacy or undocumented code, ramping a teammate, or answering 'how does this whole system fit together and where does X live?'. Trigger on 'understand this codebase', 'map this repo', 'onboard me to', or 'build a knowledge base of this project'.

owl-listener Skill

Report program impact to leadership.

renky1025 Bundle

将任意 PDF 文件高质量转换为 Markdown 格式。支持复杂布局、表格、公式、图片提取，自动处理大文件分页，提供多种输出模式。基于 OpenDataLoader PDF - Benchmark #1 准确率。使用方法: /pdf2md <pdf路径> [--output=<输出目录>] [--mode=fast|hybrid] [--extract-images=true|false] [--ocr-lang=<语言>]

renky1025 Bundle

快速构建本地知识库（Obsidian 双链图谱）。当用户输入目录 / 文档 / URL 并希望搭建或填充个人知识库、Obsidian vault、互链 markdown 笔记，或导出知识图谱数据时，使用此 skill。This skill should be used when the user wants to scaffold or populate a local personal knowledge base / Obsidian vault from files, folders, or web URLs — preserving text and images and producing interlinked ([[wikilink]]) markdown pages plus exportable graph data.

shader-slang Skill

Read and write Slang compiler documentation.

microsoft Skill

Use this when you have finished making code changes and you are ready to update the documentation based on those changes.

poorvith-mp Bundle

Handle government digital presales: policy interpretation, solution design and bid documentation. Use when responding to government RFPs, tenders, compliance matrices, or FAR rules.

rudrathegreat Skill

Write scientific Python documentation, docstrings, READMEs, and reference material.

sergio-bershadsky Bundle

This skill should be used when the user asks to "create a secondbrain", "scaffold knowledge base", "init documentation portal", "set up second brain", "create TDA project", or mentions wanting to build a personal knowledge management system with VitePress and microdatabases.

sergio-bershadsky Skill

This skill should be used when the user asks to "review page", "stamp as reviewed", "mark reviewed", "review documentation", "add review stamp", "mark page as checked", or mentions wanting to track who has reviewed a documentation page and when.

sergio-bershadsky Skill

This skill should be used when the user asks to "search secondbrain", "find in knowledge base", "look up documentation", "search notes/ADRs/tasks", "find related content", "semantic search", or mentions wanting to find specific content across their secondbrain using natural language.

serhiy-bzhezytskyy Skill

Before you put a NUMBER in front of a maintainer — "N tickets affected", "X% of cases", "this run is 13% slower" — establish what that same number would be if nothing were wrong, and report the ratio. Build the floor by comparing against something that SHOULD be identical: repeat the measurement (N≥5), or shuffle the one variable your claim depends on and keep everything else fixed. If the signal is under ~2x the floor, say so yourself before the reviewer does. Use when you are about to quote a count, a percentage, or a performance delta in an issue, PR description or mailing-list post. Trigger terms: benchmark, regression, faster, slower, N tickets, X percent, how many, count, delta, improvement, is this significant, noise, variance, baseline.

serhiy-bzhezytskyy Skill

Use when the repo you found a bug in is a fork or port of another project and you are asking whether the original still has the same bug — or whether to report it there too. A port inherits its parent's bugs, so a defect found downstream is probably still live upstream, and vice versa. Check it, then report in both houses with each artifact cross-referencing its counterpart. But re-derive every anchor against the OTHER repo's own origin/main: line numbers drift, subcommands get deprecated, issue numbers autolink to the wrong project, label sets differ, and one house requires a DCO sign-off the other doesn't. Never copy a claim across a fork. Trigger terms: fork, port, upstream, downstream, vendored, same code, inherited bug, does upstream have this, does the original have this, is this fixed upstream, report it upstream too, cross-reference.

serhiy-bzhezytskyy Skill

Use when a maintainer asks for something mechanical — rebase, squash, rename, drop a file, apply a suggestion — and you are about to write a comment about having done it. The verification you run before pushing is for you; it is not the reply. GitHub already shows the force-push, the new commit and the green check, so a comment restating them adds reading cost and nothing else. Worse, a report of your own thoroughness reads as seeking credit for the request itself. The rule: do the mechanical thing, say at most that it is done, and say nothing when the timeline already says it. Comment only when you carry something the diff cannot show. Trigger terms: rebase, squash, force-push, "can you rebase", "needs a rebase", applied the suggestion, addressed the comments, done, updated, pushed, "I have verified", test summary in a comment, replying to a review comment.

serhiy-bzhezytskyy Skill

Source comments explain what the DELIVERED code does, in the present tense — never the change history: no issue/PR numbers, no maintainer @handles, no "the previous code did X", no "confirmed by", no "aligned per". Change-narrative in source is a top AI tell, and it rots in the codebase; that context belongs in the PR body and commit message. Grep the diff's added comment lines before every push. Use before committing any code change to a repo you don't own. Trigger terms: code comment, "// previously", issue number in comment, @handle in source, over-explaining, AI smell, delivered documentation.

serhiy-bzhezytskyy Skill

Use when you are about to PROPOSE something to a young project or subproject — a design, a new capability, a discussion thread — and want to know why it is the way it is: who built it, what it was chosen over, what its authors already called incomplete, and which design arguments are still unresolved. Read the discussion arc that CREATED the repo before proposing to it. Its founding threads name the known-incomplete edges (so you don't report them as discoveries), the objections its own committers recorded (so you don't reopen them), and who actually cares about your area — none of which git history or CONTRIBUTING can tell you. For "does the ORIGINAL of this fork still have the same bug?" use port-the-report-upstream: that is code lineage, this is decision history. Trigger terms: new subproject, young repo, why does this exist, what did they already decide, project history, founding thread, VOTE thread, was this discussed before, prior discussion, before I propose, am I repeating something, is this wanted.

yc-software Skill

Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.

yoanbernabeu Skill

Repurpose Product Hunt launch content across channels. Use this skill to maximize the value of your launch assets by adapting them for blog posts, documentation, social media, and more.

cdeistopened Skill

Map any industry on the physical-to-digital spectrum and find opportunities at the 'scanned version' stage. Use when someone says 'where is my industry on digital transformation,' 'what's the native digital version of X,' 'how do I digitize my business,' 'find the scanned PDF equivalent in my field,' or 'physical to digital opportunities.' Identifies where industries are stuck at intermediate digitization.

yushui2022 Bundle

Run or resume the complete Standard mathematical-modeling workflow from contest files through reproducible evidence, adaptive formal writing, native-equation Word output, and final render QA. Use as the entry point for complete-paper requests.

jwynia Bundle

Create and manipulate PowerPoint PPTX files programmatically. Use when the user needs to generate presentations, modify PPTX templates, extract slide content, create thumbnail previews, or automate PowerPoint workflows. Supports both template-based generation (for branding compliance) and from-scratch creation. Keywords: PowerPoint, PPTX, presentation, slides, template, deck, slideshow, corporate, branding.

rcarmo Bundle

Search the web via SearXNG (or DuckDuckGo fallback) and optionally fetch result pages as raw Markdown content.

rcarmo Bundle

Build a deduped markdown digest from feeds.carmo.io (last N hours) and store links separately.

vanman2024 Bundle

Architecture Decision Records (ADR) templates, sequential numbering, decision documentation patterns, and decision history management. Use when creating ADRs, documenting architectural decisions, tracking decision rationale, managing decision lifecycle, superseding decisions, searching decision history, or when user mentions ADR, architecture decision, decision record, decision tracking, or decision documentation.

vanman2024 Skill

REST/GraphQL/tRPC API pattern library with validation, error handling, and documentation. Use when creating backend APIs.

oocx Bundle

Create comprehensive architecture documentation using the arc42 template structure (12 sections covering introduction, constraints, context, solution strategy, building blocks, runtime, deployment, concepts, decisions, quality, risks, and glossary).

oocx Skill

Regenerate test snapshot files after intentional markdown output changes. Use after modifying templates or rendering logic.

oocx Skill

Generate the comprehensive demo markdown artifacts from the current codebase. Use before UAT to ensure test artifacts reflect the latest code.

oocx Skill

Generate PNG screenshots for release notes using the repository's HtmlRenderer and ScreenshotGenerator tools. Use when asked to add screenshots to release notes or documentation.

stevesolun Bundle

Investigate questions using high-trust primary sources and traceable citations. Use when the user asks for research, current documentation or API facts, source verification, or evidence-backed comparison.

viewway Skill

````markdown

flyfission Bundle

Verifies the delivered artifact a consumer actually receives (a figure, chart, PDF, SVG, screenshot, compiled build, or deployed response) by regenerating it fresh and directly observing the output, not the source that produces it, and ends in one honest verdict. Use when the deliverable is a produced artifact and correctness lives in the rendered result. Do not use for a pure source or code diff with no separate produced output; use reviewing-code-quality instead.