Recently Added
Fresh skills just added to the collection. Be the first to try them out!
wecom-cs-mano
by JZQiang
"企业微信智能客服 V4（全自动版）- mss截图 + PIL红点检测 + EasyOCR + DeepSeek AI + pynput打字，全自包含无需外部API视觉模型"
fbs-bookwriter-lrz
by sawakso
"福帮手出品 高质量长文档手稿工具链：书籍、手册、白皮书、行业指南、长篇报道、深度专题；支持联网查证（宿主允许时启用，离线自动降级）、S/P/C/B 分层审校、中文排版与 MD/HTML 交付。触发词：福帮手、福帮手写书skill、福帮手写书、写书、出书、写长篇、写手册、写白皮书、写行业指南、协作写书、定大纲、写章节、封面、插图、排版构建、导出、去AI味、质量自检、图文书、写报道、写深度稿、写特稿、写专题、写调查报道、写长文、拆书改写、海外本地化改写、爆款结构改写、激活原料、原料盘点、整理素材、续写、继续写、接着写、补写、扩写"
Constraint Enumeration Protocol
by Droptops
It remains decision-useful rather than merely verbose.
zzz-one-dragon-player
by OneDragon-Anything
绝区零一条龙自动游戏助手 - 让 AI Agent 配合一条龙自动完成游戏日常
pdf-anonymize
by jamesconsultingllc
True-redacts PII from PDF, Word (.docx), and Excel (.xlsx) documents before sharing. PDFs have glyphs physically removed and replacement text re-laid; DOCX patches run slices to preserve formatting; XLSX replaces cells, comments, headers, defined names, and properties. Handles names, addresses, account numbers, credit scores, and merchants/stores/phones/cities on transaction lines. Works on ASCII PDFs and modern bank statements with CID-encoded subsetted fonts (BoA, Chase). Single file or directory (with --recursive). Output cannot be recovered via Ctrl+F, pdftotext, or another AI. Trigger on "anonymize/redact/sanitize/de-identify this PDF/Word/Excel", "scrub PII", "remove my name/address", "share this safely" — even when the user just attaches a file and asks to strip identifying info. DO NOT USE FOR visual watermarking, legacy .doc/.xls, or .pptx. Do NOT use nano-pdf — it re-renders pages via image AI and corrupts financial text.
wiki-operations
by nikker1974
"操作 Markdown wiki 知识库。双段式页面格式 + entities.json 实体索引 + 日志维护，让 AI Agent 拥有长期记忆。"
notebooklm-connector
by Jiang-Yude
公開版 NotebookLM 連接器技能包。讓 Claude Code 與 Codex CLI 透過 MCP 直接對自己的 Google NotebookLM 內容做問答查詢，並可選用 ExportKit 把 NotebookLM 內容匯出回本地、用 nlm CLI 管理 sources。當使用者說「連 NotebookLM」「在 Claude Code 用 NotebookLM」「在 Codex 問 NotebookLM」「裝 notebooklm-connector」「設定 NotebookLM MCP」時觸發。第一次使用先跑安裝腳本，再依 references/mcp-setup.md 把 MCP 設定加到 Claude Code 或 Codex 的設定檔。授權：MIT。
autoresearch-v2
by AndrewK404
Turns the Claude Code main thread into an event-driven coordinator for autonomous optimization. Use when the user asks to autonomously improve something measurable: optimize a file by a metric, run experiments on code, iteratively reduce loss / latency / bundle size, raise pass rate, improve a prompt eval score, "run experiments on this", "make this faster/smaller/better autonomously", "find a better version", "keep iterating until I stop you". Works for ML training (val_loss, val_bpb), API performance (p50_ms), bundle size, prompt pass-rate, LLM-judged quality — for ANY metric that reduces to a single shell command printing one parseable scalar. Also triggers on phrases like "run autoresearch", "start the experiment loop", "optimize X by metric Y", "iterate on this autonomously".
boring-stack
by boringstackoverflow
Bootstraps new web app projects with a tech stack you can understand. Runs a 4-question intake to pick a stack (Go binary + SQLite + Litestream + Caddy + systemd + a $5 VPS by default; Postgres / managed platforms when the project doesn't fit), writes STACK.md as the source-of-truth decision record plus a CLAUDE.md anchor, scaffolds new projects from scratch (init), generates production-ready deploy files from bundled templates, and walks an 8-step post-deploy verification (TLS / Litestream / restore drill). Loads when starting a new web app, scaffolding deploy infrastructure, picking a tech stack, or making bootstrap-time architecture decisions for a side project, indie product, internal tool, hobby project, or solo-founder context.
ml-experiment-workflow
by Bardli
Use when starting, iterating, or documenting an ML / medical-imaging experiment in a self-contained folder — covers the L0–L4 information hierarchy (code → CSV → visualizations → PLAN.md → SUMMARY.md), PLAN.md/SUMMARY.md document lifecycle, versioned results folders for buggy vs fixed runs, required per-version visualizations, mandatory wandb logging with a documented metric table, detached background training, watchdogs, docs/INDEX.md cross-referencing, and archival of superseded design docs. Triggers — "set up experiment folder", "new finetune run", "v2 of this experiment", "results changed because of a flag", "write up the experiment", "archive this design doc", "make me a plot to check", "what metrics are we logging".
ai-era-career-planner
by mnetfairy
AI时代职业规划师技能。专为AI时代职场变化而设计，帮助用户应对AI带来的职业冲击与机遇。当用户询问职业规划、职业建议、选专业、职场转型、未来就业方向时触发。功能包括：收集用户基本信息、霍兰德职业兴趣测评、职业价值观分析、AI时代职业影响评估（高危/中危/低危分级），并输出完整的个性化职业规划报告。关键词：职业规划、选专业、工作建议、做什么工作好、职业转型、AI时代职业、AI替代、哪些工作会被AI取代。
section-11
by JunhoC306
Evidence-based endurance coaching protocol (v11.39). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning workouts, answering training questions, or giving endurance coaching advice. Always read or fetch athlete JSON data before responding to any training question.
AnythingButLaw
by godo6818
"法外功夫 — Non-legal business skills for lawyers. Decision analysis, game theory, contract design, accounting, finance, microeconomics, law & economics, statistics, and regression analysis distilled into deep, actionable frameworks for legal practice. Each domain includes formulas with LaTeX notation, worked examples, adversarial checklists, and book-aligned structure. 律师必备的非法律商业技能深度参考：决策分析、博弈论、合同设计、会计、金融、微观经济学、法经济学、统计分析、多元回归。每章都包含完整公式推导、worked examples、对抗清单与经典判例。当用户涉及和解谈判、合同激励、财务尽调、企业估值、损害赔偿计算、反垄断分析、统计证据评估、歧视诉讼回归分析、hold-up、效率违约、Daubert 动议等场景时触发。"
paper-fetch
by Kara-lynnmacroeconomic2412
Use when the user wants to download a paper PDF from a DOI (or title, resolved to a DOI first). Tries Unpaywall, arXiv, bioRxiv/medRxiv, PubMed Central, Semantic Scholar, and Sci-Hub mirrors as a last-resort fallback.
spec-system-init
by B2CExpress
Initialize the SPEC-driven documentation system v2 (features-based) in a workspace. Creates docs/ (RULES.md, INDEX.md, features/, active/, future/, archive/, discard/) and scripts/ (generate-index.sh, lint-docs.sh, audit-docs.sh). Creates or updates CLAUDE.md at project root to orient AI. Use when the user says "inicializar sistema de documentação", "setup specs", "init doc system", "bootstrap docs", or is starting a new project that needs disciplined spec-based documentation.
busApp
by EnigMaticSpac3
A brief description of what this skill does
daily-info-digest
by Mine77
AI-powered daily digest — aggregates insights from X/Twitter builders, tech media RSS, blogs, and podcasts into a unified bilingual timeline. Use when the user wants to manage sources, generate digests, or modify the report format.
March7th Multiverse Skill
by Kitaro-Loked
```
Skill: Bar Stock Agent + Dashboard
by caleighswart
Dashboard deploy loop: the workflow uses [skip ci] on the dashboard commit to prevent triggering itself again.
elite-trading-signals
by samibajwaisking
Use this skill EVERY SINGLE TIME the user asks for: trading signals, market analysis, trade setups, entry/exit points, stop loss, take profit, crypto analysis, forex analysis, technical analysis, chart patterns, trend analysis, market outlook, trade recommendations, currency pair analysis, coin analysis, price prediction, where is BTC going, should I buy/sell, what is the market doing, weekly outlook, daily analysis, scalp/swing/position trade ideas, leverage advice, altcoin picks, gold/silver/oil analysis, or ANY question about financial market direction or trading decisions. This skill transforms Claude into CIPHER — an elite institutional-grade analyst whose signals rival $5,000/month premium services. Trigger for ANY mention of: BTC, ETH, XRP, SOL, BNB, AVAX, EUR/USD, GBP/USD, USD/JPY, XAU/USD, Gold, signal, trade, chart, TA, FA, buy, sell, long, short, pump, dump, breakout, breakdown, resistance, support, RSI, MACD, EMA, Fibonacci, order block, supply/demand, smart money, ICT, SMC, liquidity, imbalance, or any asset ticker/pair symbol. ALWAYS use this skill — do not attempt trading analysis without it.
resume-forge
by erfanezk
Expert resume reviewer that analyzes resumes against industry best practices and provides actionable, section-by-section feedback. Use this skill whenever the user shares a resume for review, asks for resume feedback, wants to improve their CV, mentions getting more interviews, asks why they're not hearing back from applications, wants to check their resume before applying to jobs, or asks any question about resume writing, formatting, or job application strategy. Triggers on: resume review, CV feedback, improve my resume, check my resume, resume critique, job application help, ATS optimization, resume tips, how to write a summary, what skills to include, how to list work experience, resume format, bullet points, action verbs, resume structure, and any other resume-related question. Also triggers when the user pastes resume content or shares a resume file (PDF, DOCX, image).
paper
by aimeos
Paper-textured, print-inspired design with minimal colors, clean serif/sans typography, and tactile surface qualities.
caving.io editing skill guide
by cmbostudio-cloud
최소 수동 확인: 이동, 채굴, 층 이동, 설정 토글(특히 미니맵)
huo15-huo15-openclaw-enhance
by zhaobod1
"火一五·克劳德·龙虾增强插件 v6.0.0 — npm 包改名 @huo15/openclaw-enhance → @huo15/huo15-openclaw-enhance（与 huo15- 命名规范对齐 + 让 ClawHub 重新创建干净的 plugin entry，绕开老 slug 1.3.0-5.1.0 bare pluginApi 留下的 ghost manifest 死结）。安装：openclaw plugins install @huo15/huo15-openclaw-enhance。OpenClaw plugin id 仍是 enhance——升级时旧 plugin record 被新包替换，用户 ~/.openclaw/openclaw.json plugins.entries.enhance. 配置不需迁移。继承 5.8.x 全部能力：分类记忆/工具安全/任务/章节/工作流/模式闸门/statusline/定时任务桥接/仪表盘/生命周期/bot-share 文件分享/native-memory-surfacer/session-bridge/postinstall hint/hook-profiler/model-router 等 25+ 模块。Use when: 给 OpenClaw 加非侵入式增强（不改龙虾核心、不复制原生功能）。"