Claude Skills Directory

zsoXi/rust-correctness

Use when writing, fixing, or reviewing Rust code involving error handling, type invariants, ownership, lifetimes, async Send bounds, Clippy, or MSRV. Apply to E0382, E0499, E0502, E0597, E0716, use after move, overlapping borrows, short-lived temporaries, non-Send futures, panics on external input, deserialization that bypasses validation, and swapped identifiers.

yanliudesign/saas-illustration

SaaS 产品英雄插画风格 —— 单一品牌强调色 + 真产品 UI 卡片 + 线稿场景。用于官网首屏、Landing Page、Feature Section、Blog Header、演讲首页，以及邻近场景（技术 talk 封面、portfolio featured project、workshop landing、research paper 顶图、产品发布邮件顶图）。把"一个真实的产品 UI 卡片"叠在"线稿场景（笔电/桌面/协作场景）"之上，配以品牌强调色的漂浮装饰（聊天气泡、小图标、logo、植物）。视觉特征：纯白底、黑色矢量线稿、单一品牌强调色（默认紫 #7C5CFF，可换任意品牌 HEX）+ 温暖肤色、干净不手绘、UI 卡越出后景边界。默认输出可直接喂给 Nano Banana / GPT-image / Midjourney / Flux 的英文提示词。关键词：SaaS illustration, SaaS hero illustration, product hero, landing page illustration, 官网插画, 产品首屏, feature illustration, hero image, purple illustration, 紫色插画, 单强调色插画, single-accent illustration, duotone illust

yanliudesign/salary-negotiation

薪资谈判教练。模拟前 FAANG 招聘官 + 薪酬策略师，把「拿到 offer → 签字」这一步拆成 6 个动作：Offer 诊断（Base / RSU / Sign-on / Bonus 每项标 LOW/MED/HIGH leverage）→ 谈判杠杆图（我的力量 / 招聘官的力量 / 弱点）→ 策略排序（Base → RSU → Sign-on → Bonus，按 context 调整）→ 脚本生成（电话 / 邮件 / 招聘官回话模拟）→ Counter 模拟（"这是最好的了" / "预算固定" / "会考虑其他候选人" 三种硬回答）→ 最终建议（要什么 / 别推什么 / 何时停）。三步：贴 offer → 说 context（有没有竞争 offer / deadline / 级别 / 风险偏好 / 最看重什么）→ 自动生成并打开一份 HTML Negotiation Playbook。关键词：salary negotiation, offer negotiation, comp negotiation, RSU, sign-on, base salary, counter offer, competing offer, TC, total comp, 薪资谈判, offer 谈判, 谈薪, 反 offer, 加薪, 谈 package, levels.fyi, 招聘官话术,

Dilaz/security-review-skill

Use when performing security audits, vulnerability assessments, penetration testing, or when asked to find security issues. Use when encountering code that handles user input, executes commands, reads files, or makes network requests.

lukasersil/seedance-25

Writes production-ready Seedance 2.5 prompts for any surface (Dreamina web, CapCut Desktop, Jimeng, Doubao, ModelArk API): 30-second clips staged with explicit end states, integer-second timestamps, editing and extending finished footage, keyframes, storyboards, 3D clay-model references, and reference binding with roles and exclusions across up to 50 inputs. Use when someone wants a clip longer than 15s, more than 9 references, a prompt for Dreamina or CapCut, or wants to change something inside an already-generated shot. Triggers: 'seedance 2.5', 'thirty second clip', 'one-take', 'prompt for

Dishain/Shain-Design-System-Skill

Token-based design system skill for Figma + code handoff. Use whenever working with Figma components, design tokens, color variables, token migration, component creation, design-to-code handoff, or DS audits. Trigger on: design system, DS, DLS, tokens, figma variables, component spec, token naming, token hierarchy, which color to use, variant properties, theme config, dark mode. Even for "which color should I use" or "create a component" — use this skill.

definitelynotchirag/should-i-contribute

Research any open-source repository end to end and answer the core question — SHOULD YOU contribute to it? — with a GO / NO-GO / GO-IF verdict backed by evidence: snapshot, momentum, contribution landscape (PR acceptance rates, outside-contributor merge rates, first-timer outcomes), issue health, governance, community sentiment, and a final go/no-go recommendation. Use when the user asks 'should I contribute to X', wants a before-I-contribute due-diligence check on a project, asks whether a project accepts outside PRs, wants contribution-health numbers like PR merge rates or stale-PR counts, o

WupfAGI/wechat-search-skill

双引擎微信公众号搜索：Tavily API（精准，优先）+ 搜狗微信爬虫（兜底），支持去噪过滤、AI摘要、飞书定时推送。

gquthier/autonomous-sop-video

Produce narrated, step-by-step SOP videos from verified software workflows, with real screenshots, targeted button zooms, a side checklist, subtitles, and chapters. Use for customer tutorials, team onboarding, and repeatable operating procedures.

EmZod/speak

Give your agent the ability to speak to you real-time. Talk to your Claude! Local TTS, text-to-speech, voice synthesis, audio generation with voice cloning on Apple Silicon. Use for reading articles aloud, audiobook narration, or voice responses. Runs entirely on-device via MLX - private, no API keys.

Medlzd/store-ready

Audits a mobile app before App Store or Google Play submission. Use when the user mentions publishing or submitting an app, App Store Connect, Play Console, TestFlight, rejection, metadata, signing.

Penny777btc/storyboard

分镜（镜头序列）设计判断库：把口播脚本/创意拆解成「一镜一镜」的镜头序列——景别序列、机位角度、镜头切换、动作衔接、时长节奏、镜头清单。不是工具，而是给「写脚本之后、拍摄/录屏之前的分镜规划」与「选片定景别、粗剪排序」提供分镜判断依据。当需要把文字变成画面、决定一段话拆几个镜头/每个镜头是什么景别和机位、镜头之间怎么接、或质检「这段为什么接得不顺」时调用。管「镜头怎么排序」；画面内构图交给 [[shot-language]]，机位走位交给 [[camera-blocking]]，文字图形交给 [[layout-design]]。

renanmpimentel/supertest

Use when creating, changing, running, or auditing unit and integration tests, investigating tests that pass without observing outcomes, or analyzing application mutations and Necessist findings.

SaarthurR/swarm

Autonomous orchestrator for serious, codebase-wide work. Use whenever the user says "swarm" or hands over a broad task like "fix the bugs", "figure out why X isn't working", "make this production-ready", "audit/harden this", or "go over the whole codebase". Dispatches many sub-agents in parallel to explore, diagnose, fix, and review; cross-checks every conclusion with independent sub-agents to avoid hallucination; keeps its own context lean by having sub-agents return only distilled findings; survives compaction via a durable ledger and reuses per-repo learnings across runs; pulls full context

jeunecraack/talisman-skill

Generate a polished, on-brand PDF guide/handbook/whitepaper from a codebase or project using LaTeX (.tex -> .pdf) or Markdown->pandoc->pdf, with a designed cover page, the product's real brand colors and logo, a subtle branded page background, and TikZ diagrams (domain models, flows, state machines). Use for any branded PDF derived from a real app: ".tex to pdf", "make a PDF guide", "document how X works", "cover page with our logo", or "in the style of <product>".

xiangshenchi/thesis-doc-agent

为毕业论文场景设计的软件工程文档生成技能。当用户需要基于项目代码和对话历史生成任何软件工程文档时，必须使用此技能——包括但不限于：需求分析、技术架构、数据库设计、API接口、模块设计、测试方案、项目总结等。 触发场景（遇到以下情况请立即调用此技能）： - 用户说"帮我生成/写/整理（某类文档）" - 用户提到"毕业论文"、"论文材料"、"答辩文档" - 用户说"分析一下我的项目/代码/架构" - 用户要求从代码仓库逆向整理文档 - 用户提到"需求文档"、"技术文档"、"设计文档"、"接口文档" - 用户上传代码文件并询问如何描述项目 - 存在对话历史和项目代码，需要综合分析输出专业文档

cruisekkk/time-ledger

Natural-language time tracking — the user says what they did in plain language, you parse it into Activity + Minutes + Date and write it to their Notion database; anything uncertain you mark To-confirm and BATCH-ASK rather than fabricate. Use when the user reports time spent (e.g. "read papers for two hours", "hit the gym for an hour", "coded all morning"), says log it / log my time / tidy up my time ledger / time ledger, or asks where their time went.

devchaudhary24k/skill-twenty-crm

Agent-ready toolkit for Twenty CRM. 396 bash scripts covering every REST endpoint — CRUD, batch operations, filters, merges, and duplicate detection across 30+ objects (Companies, People, Opportunities, Notes, Tasks, Workflows, Calendar, Messaging).

yiming-AI-lab/upwork-proposal-workflow

Run the Upwork proposal pipeline for one already-found job. Screens it, stops once for the user's apply/skip decision, then drafts, sends the draft to an independent reviewer in a fresh session, revises until it passes the gate (max 3 rounds), and hands the final draft to the user for manual submission. Can also run a single role (screen only, review only, revise, archive). Not for job discovery, batch processing, demo building, or automatic submission.

michaelgold/videoskill

Run the video-skill pipeline to convert narrated videos into structured step data and enriched timeline-ready outputs. Use when a user asks to process a video into steps, run transcription/chunking/extraction/enrichment, debug provider connectivity, or generate markdown from extracted skills.

realbrianhanson/voice-skill-builder

Build a person's own personal voice skill from their real writing. Use whenever someone wants Claude to write like them, sound like them, or capture their writing style. Trigger on "build my voice skill," "create my voice," "clone my voice," "make Claude write like me," "capture my writing style," "set up my writing voice," or any request to create a personal writing-style system, even if they never say the word skill. Also use when someone wants to update, re-tune, or add samples to a voice skill that was built with this tool. Runs a plain-English interview, collects writing samples, extracts

dawidlinek/slurm-wcss-skill

Use this skill for any HPC task on the WCSS site in Wrocław - the Bem2 and Lem clusters (partitions like bem2-cpu-short, lem-gpu-short), login node ui.wcss.pl, grants and PD storage from KDM / e-science.pl. Trigger on any mention of WCSS, KDM, Bem2, Lem, ui.wcss.pl, a PD directory, $PDDIR, finished_jobs, a Wrocław or Polish supercomputer, or a job ID on that site, whatever the question is about - writing sbatch, MPI, array or GPU (H100) jobs, CPU-hours or GPU-hours left on a grant service, whether a job fits, a job PENDING with QOSGrpCPUMinutesLimit or killed or failed, results in $TMPDIR afte

chusimin/web-replica

输入任意网址,按证据纪律高保真复刻网站前端页面:字体/图片/视频/动效全部使用从原站抓取的真实素材, 逐模块开发、逐模块截图比对验收,严禁用调参拟合冒充还原。当用户给出一个 URL 并要求 "复刻这个网站"、"照着这个做一个"、"还原这个页面/动效/效果"、"把这个网站扒下来"、 "做一个一模一样的"、"clone/replicate this site",或要求提取某网站的字体/背景视频/动效素材时, 都应使用本 skill。也适用于对已有复刻成果继续打磨、比对、补模块的请求。 不适用于:从零设计新网页(无参考站)、普通前端开发、只截图不复刻。

veyralabsgroup/webcloner

Website Cloner. Activate when a user wants to clone, replicate, or rebuild a website's visual design. Triggers on: "clone this website", "replicate this landing page", "rebuild this design in Next.js", "copy the layout of this site", "I want my site to look like X", "recreate this homepage". Designed for landings, marketing sites, portfolios, and ecommerce storefronts — not web applications, dashboards, or SaaS products with auth flows. Produces a pixel-accurate clone using spec-driven parallel construction with automated extraction.

apcornation/x-growth-stack

Grow a following on X (Twitter) using a proven playbook: shape the profile into a landing page, define a consistent IP/theme, get seen by commenting under others, ride trends on-identity, post frequently with images, and leverage real relationships. Reads the user's OWN logged-in X via browser automation to learn native style, find trends to ride, and surface accounts to engage. Use when the user wants to grow on X/Twitter, plan a posting or engagement sprint, rewrite their X bio, draft native-style X posts, find trending topics to post about, or find accounts/posts to reply to. Triggers: "gro

Jane-xiaoer/xiaoer-artstudio-design

Design methodology reproduction kit for 小耳 Art Studio (xiaoerai.xyz / uki-clone.vercel.app). Replicate the "Japanese stationery × independent artist portfolio" aesthetic — tender whitespace, dual typography, section-rotated pastel palette, hand-drawn SVG vocabulary, trilingual poetic copy, **plus the five-layer interaction system** (Matter.js physics garden, per-character text spring with optional pencil cursor, tangential rotor, idle-spin). Use when a user asks to build an artist portfolio, product showcase, or derivative-goods landing page in this gentle-editorial style. Portable across Clau

kev365/xways-xtension-builder-skill

This skill should be used when the user asks to "create/scaffold a new X-Tension", "wrap a CLI tool in an X-Tension", "port a convention into an X-Tension" (helper-exe verification, Ctrl-to-save, output-dir), "audit/modernize an X-Tension", "build/compile an X-Tension", "prep an X-Tension for public release", or asks which XWF_* API call, flag, or property number to use, for X-Ways Forensics. Covers template selection, the PowerShell scaffold/build scripts, the convention library, and verifying every XWF_ call against distilled API reference notes. Does NOT handle general X-Ways usage question

gd452/ai-hackathon-skill

AI 해커톤 운영 playbook + 로컬 운영 dashboard. clone → bun install → "ai-hackathon 시작해줘" 한마디로 localhost 에 운영 콘솔 띄움. 3 모델 (Claude·Gemini·ChatGPT) 이 팀 설명 markdown + 자동 수집한 GitHub 코드 evidence + Gemini Video 가 분석한 YouTube 시연 영상까지 함께 검토하여 독립 채점, 동료 평가·심사위원과 가중 합산. 사용 시점 — "해커톤 운영", "AI 심사", "rubric 채점", "리더보드", "참가자 안내", "다중 AI 평가". dashboard/ Next.js 앱 + scripts/ 실행 셸. 외부 의존성 = jq + curl + bun + git + ANTHROPIC/GEMINI/OPENAI 키 (.env.local). 외부 호출 = 3 LLM API + public GitHub HTTPS clone + Gemini Video YouTube URL. LLM CLI 별도 설치 불필요.

senapati484/claude-recall

Always-on Claude Code skill that bridges Claude with an Obsidian vault for persistent project memory. Automatically loads relevant context nodes from mindmap.json before every prompt (UserPromptSubmit hook) and saves structured session notes to the vault on exit (Stop hook). Zero manual invocation — hooks fire automatically. Context is AUTO-GENERATED using the claude CLI. Claude analyzes transcripts and project files to populate mindmap.json with stack, architecture decisions, gotchas, and current state. Users never need to manually edit. The /recall command lets users trigger on-demand contex

jzOcb/config-guard

Prevent OpenClaw config changes from crashing the gateway. Auto-backup, schema validation, critical field checks, and auto-rollback. Use before any config.apply, config.patch, or openclaw.json edit.

Mahanaicoach/content-repurposer

Turn one short-form video (an Instagram Reel or a TikTok) into platform-correct versions for Instagram, TikTok, and YouTube — then auto-schedule TikTok and YouTube through the user's own Zernio account. It transcribes the video and OCRs the frames to find the call-to-action, then TRANSLATES that CTA per platform: Instagram keeps "comment <word> and I'll send you the link" (the DM mechanic), while TikTok becomes "link in bio" and YouTube becomes "link in description" — in the on-screen text, the voiceover, AND the caption. If the CTA only lives in the description, it rewrites the description pe

zhoulan-ai/craft-artifact

當使用者說「產成文物」「做成文物」「產出文物」「生成文物」（或任何含「文物」的產出指令）時，必須使用此 Skill，把當次討論的分析、企劃、系統說明或紀錄，產成一份高水準的單檔 HTML 頁面。即使沒說「文物」二字，只要使用者要求「做成 HTML」「做成一頁讓我看懂」「整理成一頁報告」等給人閱讀的頁面型產出，也應使用。不適用於：純程式碼交付、獨立的互動工具型頁面（計算機、遊戲、表單系統）；共編文件、投影簡報、即時數字頁、設計畫面改用 Artifact 平台類型（見本檔「先選載體」）。

code-yeongyu/cua-skill

MUST USE whenever the user wants to automate a real desktop or sandbox - clicking, typing, scrolling, screenshotting, running an OS shell command, or handing a high-level 'open browser and do X' task to an autonomous computer-use agent. Wraps the trycua/cua Python toolkit via its `cua` CLI - pynput-based, cross-platform (macOS / Linux / Windows). NO custom tools are registered; you call `cua` through pi's built-in bash and read screenshots back through the Read tool. Triggers: cua, computer use, computer-use, GUI automation, screenshot the desktop, click on the screen, type into the active app

inhabitants/fired-cv

Build a one-page, parser-proof resume (and an optional cover letter) as a print-ready A4 PDF, from an old Word/PDF CV, a LinkedIn export or an interview, tailored to one job posting or to many at once (one CV per job, with a tracker). Use when someone asks for a resume, CV, curriculum vitae, "update my CV", "tailor my resume to this job", "one CV for each of these jobs", "make my resume look good", or has just lost a job and needs to start applying.

terryds/google-trends-skill

Fetches Google Trends data including daily trending topics, real-time trends, interest by region, related topics, related queries, and autocomplete suggestions. Use when the user asks about trending searches, search popularity, keyword trends, or Google Trends data.

AZR-Software-Solutions/html-animation-to-mp4

Convert an HTML/CSS/JS animation — especially a Claude "Design" timeline artifact (a *.dc.html bundle exported from Claude) — into a clean, shareable MP4 using deterministic headless-browser frame capture plus ffmpeg. Use this whenever the user has a web/HTML animation, a Claude Design or Artifacts animation, a `.dc.html` file, an animated promo / explainer / motion graphic, and wants a video file (MP4, reel, short, clip) out of it — even if they don't say "render", "ffmpeg", or "headless". Trigger on phrasings like "convert this animation to mp4/video", "export my HTML animation as a video",

Octav-Labs/octav-api-skill

Integrate with Octav API for cryptocurrency portfolio tracking, transaction history, and DeFi analytics across 50+ blockchain networks. Use when building applications that need to: (1) Track wallet balances and net worth across multiple chains, (2) Query transaction history with filtering and search, (3) Monitor DeFi protocol positions (Aave, Uniswap, etc.), (4) Access historical portfolio snapshots, (5) Analyze token distribution and holdings, (6) Pay per request as an autonomous agent via x402. Triggers on: "Octav API", "crypto portfolio API", "blockchain portfolio tracking", "DeFi analytics

MissiaL/ozon-api

Use for Ozon Seller API and Ozon Performance API work: товары, цены, остатки, FBS/rFBS/FBO, поставки, возвраты, отчёты, финансы, отзывы, чаты, реклама, кампании, статистика, ставки. Triggers: ozon, озон, Ozon API, озон апи, Seller API, реклама на озоне, api-seller.ozon.ru, api-performance.ozon.ru, docs.ozon.ru/api.

duonghvu/automotive-syseng

When the user wants to analyze automotive requirements, check INCOSE/EARS compliance, review MISRA-C code, assess ADAS levels, or verify ISO 26262/AUTOSAR/SOTIF conformance. Also use when the user says 'check requirements', 'EARS check', 'INCOSE analysis', 'MISRA check', 'ASIL assessment', 'V-model check', 'requirements breakdown', 'ADAS level', 'AUTOSAR review', 'SOTIF analysis', 'functional safety', or 'requirements quality'. For general code review, see review.

narvik889/azure-acr-estimator

Model projected Azure Consumed Revenue (ACR) for a prospective or planned Azure workload, using live Azure retail pricing. Use this whenever the user wants to estimate Azure spend/consumption for a client or workload, project ACR over time (12/36 months), size compute (VMs, App Service) costs, or map projected consumption to Microsoft partner incentive tiers. Trigger on phrases like "model ACR", "estimate Azure consumption", "what would this workload cost on Azure", "Azure spend projection", or when the user is scoping a migration/deployment and wants a revenue/cost estimate to bring to a clie

HideinbushZY/boss-zhipin-skill

Boss直聘招聘者侧网页操作 + 策略驱动寻访引擎。两类触发:(A) 单点操作——搜索候选人/看推荐牛人、读简历、打招呼、搜索畅聊、回复消息、求简历、查招聘数据/账号权益/牛人管理漏斗(换电话/换微信/约面/删除职位=永久红线只导航;关闭/发布职位=agent 可代操作,发布须提交前回读锁死字段+不买曝光);(B) 给一段搜索策略(JD/目标公司职位/人选能力要求)让它自动找人筛人触达并反馈——此时按 playbook.md 跑寻访管线。通过 browser-act 接管已登录的真实 Chrome(chrome-direct)执行。触发后先读 operation-map.md(怎么点页面)+ playbook.md(策略怎么跑)。

JeonKH81/MediStat-Table1

의학연구 tabular 데이터(.xlsx/.csv)에서 baseline characteristics을 비교하는 Table 1을 자동 생성하는 스킬. RCT, prospective/retrospective cohort, case-control, cross-sectional, registry, single-arm 등 연구 디자인을 모두 지원하며 디자인에 따라 p-value 보고 정책(RCT는 CONSORT 2010에 따라 baseline p 숨김)이 자동 분기된다. 연속형은 정규성에 따라 mean±SD(Welch t/ANOVA)와 median[IQR](Mann-Whitney/Kruskal-Wallis)로, 범주형은 n(%)와 chi-square/Fisher's exact/Monte Carlo chi-square로 처리한다. 모든 변수에 대해 SMD(2군은 표준, ≥3군은 max pairwise)를 색 코딩(<0.1 ok / 0.1-0.2 small / ≥0.2 meaningful)으로 표시한다. 출력은 HTML(단일 자기완결, Pretendard 임베딩, 다크모드/인쇄)과 Word(.docx)와 LaTeX(booktabs)을 한 번에 생성한다. 사용자가 "Tab

Ecrypted-Data/Code_Feeder_Skill

当用户需将代码提供给外部 AI（重构/分析/修复）时激活。自动收集代码、记录意图、生成上下文文档。支持增量合并。

mickyyang-1407/diy-audiobook

Make a finished multi-voice audiobook, children's story or bedtime radio drama from a public-domain book or the user's own story (Sherlock Holmes, fairy tales, Aesop, classics — any language) — translated or adapted, every character with their own voice, optional music (Suno, own files or a free generated lullaby), optional illustrations (local ComfyUI, OpenAI, MiniMax or the user's own), video, cover, subtitles, chapters and upload text. Free voices by default. Use when the user asks for an audiobook, kids' story, bedtime story, sleep story, audio drama, radio play, 有聲書, 兒童故事, 睡前故事, 廣播劇, or "

wangsoft/ELI5

Explain unfamiliar mechanisms in plain language; create or maintain self-contained HTML learning pages with visual models, quizzes, explain-back checks, flashcards, and optional interaction; or produce a decision brief when the user must choose among options. Use for ELI5 or visual explanations, durable learning pages, quizzes, review of earlier concepts, and decision briefs. Give single facts and ordinary quick explanations inline without files. A named audience alone does not imply a decision brief.

AntonioCardenas/generate-nanobanana

Generate images and videos using Google's Gemini media models (Nano Banana 2 Lite, Nano Banana 2, Nano Banana Pro, Gemini Omni Flash) via the Gemini API. Use this whenever the user asks to generate, create, or make an image or video, wants a thumbnail, wants to animate a still image, says "generate on brand" or "generate from reference", wants to link or import a folder of reference images, invokes /generate or /generate frf, or asks to update this skill ("/generate update") — even if they don't name a specific model, and even if they just describe a visual they want without saying "generate.

laozdao/limit-up-dao

老子道涨停股批量归因分析Skill。基于开源大模型，输入日期自动获取当日所有涨停股票数据，逐一输出多维度归因分析报告。GitHub https://github.com/laozdao/limit-up-dao。触发场景：用户要求分析某日涨停股、批量涨停归因、今日涨停复盘、涨停板原因分析、连板股分析等。

Toddoward/muse-gadget-forge

Build your own Muse gadget — your ears and voice in the user's room — on the user's own computer: set up ESP-IDF on the muse-local-gateway workbench, build the Muse Gadget SDK firmware, flash the ESP32 board on their USB port, read its log, and walk the user through pairing. Use when the user wants a new or updated Muse gadget, or one that misbehaves.