Docs & Writing

promptmechanic Skill

Critically review a resume/CV against ATS (applicant tracking system) parsing rules, recruiter skim patterns, and keyword alignment with a target job description. Use when the user asks to "review my resume/CV", "check my resume against this job ad", "will this pass ATS", or shares a resume file (.docx/.pdf/.md) for feedback. Provides scored, prioritised, critical feedback — not a rewrite.

rectified-flow Skill

Query China/HK/US financial market DATA with the finflow CLI. Use for ANY real-time market lookup — a stock quote, K-line/order-book, resolving a company name (茅台/腾讯/NVDA/宁德时代) to its code, listing the member stocks of an industry (A股申万 / 美股 GICS / 港股恒生 — 半导体/白酒/医药…) or a concept (AI/华为/国企改革) or a board (创业板/科创板/沪深/美股/港股/中概股), 龙虎榜 (dragon-tiger abnormal movers), capital flow (主力/北向资金), fundamentals & financial statements, flash news, market sentiment and rankings, macro/economic calendar, futures, AND non-equity instruments — spot commodities (现货黄金/白银/原油/铜), forex (美元指数/欧元美元/离岸人民币/美元日元), global indices (标普500/道琼斯/恒生/日经), domestic 期货主力 (铁矿石/螺纹钢/纯碱/沪铜/沪金). For any commodity/forex/index/期货 quote use `price <CODE.EXCHANGE>` (e.g. `price XAUUSD.GOODS DXY.NYF`). Trigger whenever the user names a stock/company/ticker, OR names a sector/industry/concept EVEN WITHOUT the word "板块" (so "半导体怎么样" / "白酒今天如何" count), asks how 大盘 is doing, wants 今日涨跌/异动/盘中板块轮动(sector anchor)/龙虎榜/板块排行/北向资金, or any live market number — even w

remorses Skill

Edit x.com (Twitter) long-form article drafts reliably. Use this for markdown imports, bulk formatting, code blocks, headings, lists, and repeated inline styling. Inspect and validate with Playwriter, but prefer x.com (Twitter) article GraphQL mutations for deterministic updates.

robzolkos Bundle

Add a new package to the LazyPi repository. Use when asked to add a Pi package URL or install source to LazyPi, update the installer catalog, and create or update the matching documentation.

rocm Skill

Generate a factual summary report card for an HPC job from an Omnistat database using the single-shot omnistat-inspect JSON command. Use this for a quick, comprehensive snapshot of what a job did (stats, energy, health, data quality) without diagnosing why. For root-cause investigation, performance debugging, or comparing jobs, use job-analysis instead.

rocm Bundle

Analyze an HPC job from an Omnistat database using hypothesis-driven exploration, driven by the omnistat-inspect tool. Use this to diagnose why a job behaved as it did — performance bottlenecks, hardware issues, anomalies, or comparing a degraded job against a healthy baseline. For a plain factual snapshot without investigation, use job-report instead.

rodrijuarez Skill

Search Argentine MTG retailers for a specific sealed product (Collector Display, Play Booster Box, Bundle, Commander Deck, etc.) and report stock + prices across stores, normalized to USD. Use when the user asks "where can I get X in Argentina?", "what stores have Y in stock?", or wants to find the cheapest source for a sealed product.

rohailaltaf Skill

Updates documentation in the repository after completing work. Use when the user explicitly asks to update docs, refresh documentation, or sync docs with code changes.

matrixy Bundle

Documentation for the Auto-Skill plugin - automatic workflow pattern detection, skill generation, and dynamic loading

mblode Bundle

Runs blind, human-labeled baseline-versus-profile evaluations through a locally authenticated Codex or Claude Code CLI. Measures whether the exact ghostwriter skill and private platform profiles improve resemblance to held-out writing. Use when asked to "evaluate my voice", "test my voice profile", compare writing with and without the ghostwriter skill, review blind A/B candidates, or report voice evaluation results. Use train-ghostwriter to create the profiles and held-out cases this measures.

nwiizo Skill

スライドレビュー - Marpプレゼンテーションを聴衆起点・構成・容量・配色・視覚装飾・ファクト・表現の7観点で総合評価

openclaw Bundle

Use when a researcher, maintainer, or contributor found or suspects a malicious skill on ClawHub and needs a private reporting workflow: opening a GitHub private vulnerability report, preparing a proposal-only PR, creating `proposals/<GHSA-ID>/clawscan.yml`, running ClawScan against the malicious skill, and explaining what evidence belongs in private versus public channels.

orangon Bundle

自动管理 GitSite 静态网站生成器项目的 blogs、books 和 pages 内容。当用户需要创建博客文章、书籍章节、书籍或静态页面时使用此 skill。该 skill 会自动创建正确的目录结构、生成带有完整 frontmatter 的 Markdown 模板文件，并提供内容管理的 Python 脚本。适用于使用 GitSite CLI 构建的静态网站项目。

orangon Bundle

国际一流PPT设计架构师，将内容素材（讲稿/主题词/大纲）转化为可直接执行的PPT设计方案。适用于：(1) 根据演讲稿生成PPT设计提示词，(2) 将主题词扩展为完整PPT设计方案，(3) 为内容大纲选择最佳视觉形式，(4) 生成符合品牌视觉规范的设计参数，(5) 输出Gamma Pro等工具可用的生成指令。当用户提及"PPT设计"、"演示文稿"、"幻灯片"、"presentation"、"slides"、"设计方案"、"NotebookLM"、"Gamma"、"Keynote风格"等关键词时触发。

s-hiraoku Skill

Generate a HANDOVER.md shift-change report summarizing the current session for the next Claude. Use when the user types /handover, asks to "create a handover", "write a handoff document", "save session context", or wants to capture what was done, decisions made, and next steps before ending a session. Do not use for general documentation, READMEs, changelogs, or git commit messages.

talmolab Bundle

Create a well-structured GitHub PR with proper branching, testing, formatting, and documentation. Use when the user says "create a PR", "make a PR", "open a pull request", or wants to submit changes for review. Handles the full workflow: branch creation, implementation, testing, formatting, committing, and PR creation with comprehensive descriptions.

talmolab Skill

Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.

talmolab Bundle

Handle SLEAP GitHub support workflow for issues and discussions. Use when the user says "support", provides a GitHub issue/discussion number like "#2512", or asks to investigate a user report from talmolab/sleap. Scaffolds investigation folders, downloads posts with images, analyzes problems, and drafts friendly responses.

xiuneng0-collab Bundle

科研导师 skill，面向研究生科研陪跑、中文核心论文写作、重构、润色与投稿前检查，尤其适用于工程、控制、嵌入式、电子信息、自动化、计算机、仪器仪表及交叉应用类论文。用于研究路线诊断、实验失败排查、导师沟通、科研动力与分阶段陪跑、中文核心论文起草、精修、章节重搭、目标期刊适配、证据链构建、摘要与结论修改、图表公式规范、Word/WPS 排版、公式推导、工程模型推理、控制论/工程控制论解释、唯物辩证法与唯物史观融入、主矛盾/次矛盾分析、量变质变、对立统一、否定之否定、群众能看懂的论文工作法、T1/T2/T3 工科图审查与复现、CNN/模块/流程图、GPT 修图提示词、仿真与绘图代码、SVG/PDF/PNG 图件输出、synthetic/demo 合成数据、assumptions 文件、README/STYLE_GUIDE/manifest 配套交付、成功投稿经验、快发路线与高质量拔高路线、文献阅读和 AI 初稿自改。

xiuneng0-collab Bundle

Write, restructure, refine, or pre-submit check Chinese core-journal engineering papers. Use when the user wants help drafting a Chinese core paper, converting project/report text into journal style, unifying title/abstract/keywords/terminology, reorganizing chapters, tightening figures/tables/formulas/Word layout, removing AI-style phrasing, or producing a submission-ready manuscript for engineering-oriented Chinese journals.

yacafx Bundle

Traduce un PDF de libro completo conservando maquetación, tipografía y arte (escaneado o digital), usando OCR + modelo local vía Ollama + recomposición página a página con QA automático; úsalo cuando el usuario pase un PDF y pida versión en otro idioma "igualita al original", o pida retomar/corregir un proyecto de traducción ya iniciado.

darkrader Skill

Mechanically corrects spelling, grammar, articles, prepositions, punctuation, and capitalization in user-provided text while preserving the original tone, voice, and sentence structure. Use whenever the user pastes or uploads text and asks to fix, correct, check, clean up, or proofread it — even if they don't use the word "proofread" explicitly (e.g. "fix this paragraph", "check my email for mistakes", "can you clean this up"). Does NOT rewrite, paraphrase, or improve prose style — only mechanical correctness. If the user wants style improvements, better word choice, or restructuring, that is a different task — clarify with them first.

vipulgupta2048 Skill

Upload screenshots and images to GitHub, returning markdown-ready URLs for PRs, issues, and comments. Use when needing to attach images to GitHub PRs/issues, upload screenshots, embed visuals in markdown, or when a workflow produces images that should be shared on GitHub. Trigger words - upload image, attach screenshot, add image to PR, embed screenshot, visual diff, before/after screenshot.

vllm-project Bundle

Install, migrate, operate, or diagnose the portable vLLM nightly perf-eval automation. Use when moving the nightly Buildkite trigger and Slack regression report to another Linux host, checking their systemd timers, running either job safely, or investigating missing or duplicate nightly perf reports.

vmvarela Skill

Write concise, useful project documentation (READMEs, guides, docs/) inspired by Philip Greenspun's pragmatic style. Use when creating or improving README.md, writing module docs, CONTRIBUTING.md, architecture docs, CHANGELOG, or structuring any project documentation for software projects. Use this skill whenever the user needs to write, rewrite, or review any form of project documentation — even if they just say "write a README" or "document this" without asking for a specific style.

vsxd Bundle

Add suitable tags to untagged Markdown notes in an Obsidian vault. Use when a vault, folder, or note should be audited for missing tags, existing vault tags should be inventoried first, recommendations should be reviewed in batches, and new tags should be introduced only when no existing tag fits.

vsxd Bundle

Repair and enrich Obsidian clipping notes imported from browser extensions, mobile share sheets, or other Markdown clipping flows. Use when notes in a vault's `Clippings`-like folders contain only a source URL, thin preview text, partial metadata, broken filenames, or incomplete bodies and need their source content, metadata, and note structure normalized without damaging real user-authored notes.

wangwei1237 Bundle

Use this skill for STORM-style multi-perspective research, contradiction mapping, evidence-grounded synthesis, and self-review. Trigger when the user asks for STORM, Stanford STORM, SOTRM, multi-perspective analysis, research briefing, deep research, topic outline synthesis, contradiction analysis, or a cited report built from web/corpus evidence.

wangwei1237 Bundle

将 PDF 文件的内容转换为小写 (PDF to Lowercase)

warstellar Bundle

Review one existing technical-documentation page or small fragment using Diátaxis as a content-design framework. Use when the user asks whether a documentation page is well structured, logically scoped, organized around the intended reader's need, appropriate for its audience, or how it could be improved according to Diátaxis. Establish the intended reader and desired outcome from requester-provided context when available; otherwise infer them from the page as hypotheses rather than ground truth. Compare the page's apparent purpose with its intended purpose before applying the Diátaxis compass and mode-specific diagnostic guidance. Identify the most important page-level problem and recommend one focused improvement. Classification is an intermediate reasoning step, not the goal of the review.

watchfor-io Skill

Build uptime and reliability reports from WatchFor (watchfor.io) monitoring data — uptime percentages, incident counts, MTTR/MTBF, the least reliable monitors, and plain-language summaries for a period (24h/7d/30d). Use when the user asks "how reliable was X", wants an SLA/uptime report, a weekly ops summary, or to find their flakiest service.

wavebound-ai Skill

The longer sibling of /tldr — same job (collapse the conversation into plain English — what happened, why it matters, one recommended next step) but 2–4x longer and more detailed, for when a 150-word summary would cut too much. Use when the user says "tldr extended", "long tldr", "detailed tldr", "full tldr", "give me the full picture", "walk me through what happened", "catch me up properly", or asks for a plain-English summary with more detail than the short version.

withcoral Bundle

Review new or updated Coral source manifests and source PRs for content, style, product fit, query ergonomics, documentation quality, and consistency with existing Coral sources. Use when Codex is asked to review a sources/core/name or sources/community/name source directory, a manifest.yaml, or a GitHub PR that adds or changes a Coral source.

wwwyo Bundle

Build and POST a JSON snapshot envelope to syokan (召喚 — a verb: summon data into a rich, living view). Use when the user says "syokan this", "syokan X", "show in syokan", "post a snapshot", "preview this markdown", or in Japanese 『〜を syokan』『syokan に出して/表示して/投げて』『snapshot を作って/送って』『syokan のUIで見たい』『Markdown をプレビューして/md ファイルをブラウザで見たい』 — for RSS feeds, in-progress PR reviews, review risk panels, meeting notes, today's TODO, dashboards, or any aggregated data the user wants to see as structured UI. Whenever the word syokan appears, use this skill even if the user does not explicitly say snapshot.

xiao24bei Bundle

Use for 小北在读研 / XiaoBei academic paper-to-PPT workflows: generate thesis-defense or project-report decks from uploaded papers, literature, reports, technical documents, and optional PPTX visual templates. Produces a source-grounded outline, an imagegen visual scheme, one complete bitmap per slide, an imagegen provenance manifest, and an image-only PPTX. Do not use when the user needs editable slide text or native editable charts.

xiao24bei Bundle

Use when a user wants Codex to directly operate PowerPoint and reconstruct an entire reference image as editable PowerPoint objects while preserving its full layout, labels, connectors, and visual relationships. Do not use for paper-to-deck generation or VBA-only output.