Recently Added
Fresh skills just added to the collection. Be the first to try them out!
stock-research
by Mrpixelraf
把「像素先森 v3.1 上市公司深度分析 Pipeline」固化为可一条命令触发的三阶段工作流——后台子 agent 强制采集一手财报（WebFetch ≥ 5）、主会话分段写 15k 字深度报告（11 模块 + 自我证伪机制 + 核心争议专章 + 5 XML schema）、python 质检。Use when user says 深度分析、用我的框架分析、研报、company deep dive、deep dive、个股研究、estimate fair value of a stock. 适用于美股/港股/A 股上市公司的客观估值与投资评级。
bangla-content-generator-finchip
by shohanhasan2672
Description: Instantly generate professional Bangla content for blogs, SEO articles, social media, YouTube scripts, and emails from any topic or idea. Customize style, tone, and keywords for natural, engaging, and SEO-friendly results.
dev-workflow
by orxz
将非平凡开发任务路由到 7 条工作流路径，覆盖从评估到上线的完整生命周期。 强制执行：先规划后编码、TDD、逐任务审查、文档同步、进度持久化。 适用于：多文件功能开发、bug修复、重构、依赖升级、紧急热修复、跨会话任务。 当用户描述一个非平凡开发任务但未选择工作流时，主动建议使用——在任何代码编写之前。
user-story-ac-writer
by ndmnghia
Sinh User Story và Acceptance Criteria chuẩn INVEST + Given-When-Then cho BA/PO. Skill enforce 6 tiêu chí INVEST (Independent, Negotiable, Valuable, Estimable, Small, Testable) và format AC theo Gherkin syntax. Hỗ trợ 3 mode: viết mới từ feature description, refine US đang có, bổ sung AC cho US đã viết. Dùng khi user nói: "viết user story", "viết US", "tạo user story", "viết AC", "viết acceptance criteria", "tạo AC cho story", "user story chuẩn INVEST", "AC theo Given-When-Then", "AC Gherkin", "refine user story", "review US này", "US này đã chuẩn chưa", "bổ sung AC", "viết tiêu chí nghiệm thu", "story cho feature này", "split user story", "story quá to cần tách", kể cả khi paste feature description + nói "viết story đi" hoặc upload PRD + "tạo US list". KHÔNG dùng cho: viết PRD/URD/SRS toàn bộ (dùng prd-writer, srs-writer), viết test case kỹ thuật chi tiết (AC ≠ test case), viết Use Case formal (dùng po-usecase-refiner), business rules (dùng business-rule-generator).
WorldCup Bet 2026 Jingcai Assistant
by nasplycc
```
Flight Monitor Skill
by KardeniaPoyu
```
d-research
by d-init-d
Browser-first deep research and lawful public-data collection for AI agents. Triggers: web research, source discovery, scraping public data, literature reviews, market or technical research, evidence ledgers, blocker reports. Read-only; never bypasses logins, paywalls, captchas, or rate limits.
Design Atlas — v2
by arkbridge
A finished atlas should let the user triage in 15-30 minutes (rate refs, write a few steers, export JSON). The synthesis after feedback should produce a design-system deck rich enough that the sister /scaffold skill can generate a working Next.js project from it WITHOUT requiring further design decisions. Every component spec, every token, every wireframe state must be unambiguous code-input-quality.
abstract-annotation
by LHX200013
Extract exact relevant mentions from academic abstracts, group them into dimensions and subdimensions, and generate review-ready article and dimension outputs.
search-intent-scanner
by kolegadev
Find queries where SERPs are weak and commercial intent is implied. Use during discovery to complement pain-signal scanning with search demand data.
lex-ocpi — agent skill manifest
by alpibrusl
see README.md for the deferred-work tracker.
code2wiki
by woaillr-crypto
为大型后端项目生成和维护面向业务的 Business Context Layer（业务语义层 / 项目知识地图）。当需要总结、梳理、文档化、wiki 化、构建上下文、创建领域 skill、提升 LLM 对既有后端代码库的理解时使用——尤其适用于 10w+ 行、50w+ 行这类需求主要由业务驱动而不是技术模块驱动的系统。支持 Java/Spring、Kotlin（Spring/Ktor）、Python（Django/FastAPI/Flask）、Go（Gin/Echo/gRPC）、TypeScript/JavaScript（NestJS/Express）等多种后端栈；扫描器自动识别项目语言，混合语言 Monorepo 会并行扫描所有命中插件。也适用于多级业务域目录、项目知识地图、API/Database/Code Entrypoint 映射、风险清单、分层上下文（L0/L1/L2/Source）建设等任务。
everclaw
by profbernardoj
Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the [REDACTED] decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to [REDACTED] by default — Claude only kicks in as an escape hatch when needed. Includes [REDACTED] API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth rotation v2 with proactive DIEM balance monitoring and reactive 402 watchdog, Gateway Guardian v5 with direct curl inference probes (eliminates Signal spam), proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver, three-shift cyclic execution engine (v2 with 15-minute execution loops), 24/7 always-on power configuration for macOS, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, ERC-8004 agent registry reader for discovering trustless agents on Base, and hardware-aware local Ollama fallback with auto model selection (Gemma 4 family: E2B/E4B/26B/31B with vision + audio, based on available RAM/GPU).
ai-judge
by reguorier
Local-first multi-model AI jury system with v3.3 fixed persona seats, evidence tracing, and dissent. Query 9 AI seats, score claims with auditable functions, detect bluff risk and echo-chamber consensus, profile cognitive proxy signals, render reasoning trees, and keep final authority with the human.
murmur
by xiaopengde
把一段中文（或任意 Whisper 支持语言）的会议/面试录音用本地 Whisper large-v3 转成文本，再清洗成带说话人标签、修过 ASR 错字、分好章节的 markdown 文档（可选再转成 docx）。跨平台（macOS Apple Silicon 用 mlx-whisper，Windows/Linux/Intel Mac 用 whisper-ctranslate2）。零云端、零订阅、隐私不出本机。适用：替代飞书妙计/通义听悟/Otter.ai 这类付费转录服务、需要在 VS Code 或 Word 里直接拿到可读稿、在 AI agent（Claude Code/Copilot/Codex/Cursor）里端到端跑通。不适用：实时转录、强噪声多人重叠会议、需要严格说话人分离的场景。
drupal-testing
by ThomasRoger76
Use when writing PHPUnit tests for Drupal modules (Unit, Kernel, Functional, FunctionalJavascript), configuring phpunit.xml for Drupal, mocking services with UnitTestCase, testing Entity API or Config API with KernelTestBase, simulating user navigation with BrowserTestBase, testing AJAX with WebDriverTestBase, setting up CI/CD pipelines for Drupal automated testing in Drupal 8-11+, running PHPStan/phpcs/Rector static analysis on Drupal code, or testing an existing Drupal site without reinstalling using Drupal Test Traits (DTT)
flight-delay-risk
by ZhangHejunjie
全球航班延误风险助手。当用户输入任意航班号（如 CA1234、EK201、BA456、UA100 等，国内外均支持）或询问"航班会不会延误""要不要早点去机场""这个航班靠谱吗""会准点吗"时触发。调用 AviationStack API 获取实时航班状态，同时用 wttr.in 查询出发地和目的地机场天气，综合分析后给出延误风险评级（低/中/高）和具体出行建议。只要用户提到航班号、问延误风险、问要不要提前去机场，都应使用这个 skill。
BookKaroo — Coding Skills & Standards
by Sanjay12089
❌ No any, no monolithic files, no hard deletes, no inline styles, no FKs, no Redis
adai-contribute
by a-digital-arts-institute
Contribute to the A(DAI) Digital Arts Knowledge Commons graph (https://adai-basel.fly.dev) on behalf of a practitioner using their bearer token in ADAI_TOKEN. Use this skill when the user wants to add a text signal about an existing node, create a new node (practitioner, artwork, concept, scene, institution, collective, platform, etc.), add or supersede an edge between two nodes (CREATED_BY, EMBODIES, PRACTICES, EXHIBITED_AT, CLASSIFIED_BY, BELONGS_TO, COLLABORATES_WITH, USES_TECHNIQUE, INFLUENCES, RESPONDS_TO), upload an image and attach it to a node, or — with an admin-scope token — mint, list, or revoke contributor tokens for others. Talks to /api/v1/* via curl. Respects trust tiers (auto/reviewed go live, probationary queue at /review for curator approval). Never infer INFLUENCES or RESPONDS_TO from style or visual similarity; both require attested artist intent.
dao-skill
by HiccupRL
面向毛泽东选集/毛泽东著作、王阳明心学/传习录、曾国藩家书三类中文思想材料的语料检索、对照阅读、观点归纳与写作辅助 skill。当用户要求比较毛泽东、王阳明、曾国藩，或要求基于这些原典做读书笔记、主题索引、摘录、研究备忘录、文章草稿时触发。
browser-automation-skill
by xicv
Drives a real browser from Claude Code by routing across four backends (chrome-devtools-mcp, playwright-cli, playwright-lib, obscura), so verbs like open/click/fill/scrape/inspect/audit pick the cheapest adapter that supports each operation. Persists credentials, sessions, captures, and per-action telemetry strictly local under $HOME/.browser-skill/ (mode 0700 dir, 0600 files); secrets never appear on argv, in git, or in the Claude transcript. Surfaces a balance-of-tokens-accuracy-latency audit via browser-stats.
banjar-sental-kawan
by banjar-sental-kawan
Official page for Krama Banjar Sental kawan
/trendupdate
by D-watanabe1130
GitHubトレンドと公式ドキュメントを調査してknowledgeベースを更新する。「トレンド調査」「ベストプラクティス更新」「/trend-update」と言われたら使用する。
repo-security-audit
by WyrdWerk
Quick security checklist for evaluating GitHub repos and npm packages before/after installation. For non-coders and users. Heavy details live in references/.