Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
25,464
总 Skills
95.3M
总安装量
2,622
贡献者
# Skill 仓库 描述 安装量
1801 iterative-retrieval affaan-m/everything-claude-code
Iterative Retrieval Pattern Solves the "context problem" in multi-agent workflows where subagents don't know what context they need until they start working. The Problem Subagents are spawned with limited context. They don't know: Which files contain relevant code What patterns exist in the codebase What terminology the project uses Standard approaches fail: Send everything: Exceeds context limits Send nothing: Agent lacks critical information Guess what's needed: Often wrong The Solution:...
 5.5K
1802 cpp-testing affaan-m/everything-claude-code
C++ Testing (Agent Skill) Agent-focused testing workflow for modern C++ (C++17/20) using GoogleTest/GoogleMock with CMake/CTest. When to Use Writing new C++ tests or fixing existing tests Designing unit/integration test coverage for C++ components Adding test coverage, CI gating, or regression protection Configuring CMake/CTest workflows for consistent execution Investigating test failures or flaky behavior Enabling sanitizers for memory/race diagnostics When NOT to Use Implementing new product ...
 5.5K
1803 tushare waditu-tushare/skills
Tushare 概述 tushare是一个财经数据接口包，拥有丰富的数据内容，如股票、基金、期货、数字货币等行情数据，公司财务、基金经理等基本面数据。该模块通过标准化API方式统一了数据资产的对外服务方式，以帮助有需要的技术用户更实时、简洁、轻量的使用相关数据。 快速上手 安装python运行环境(推荐python3.7+)，并安装tushare依赖包(推荐从清华pypi镜像安装)。 pip install tushare -i https://pypi.tuna.tsinghua.edu.cn/simple Tushare官网注册，获取token，并配置环境变量。 注册地址 export TUSHARE_TOKEN = your_token 查询Tushare接口文档，找到对应的接口。 在线数据接口文档 根据接口文档，使用python代码获取数据。（如 股票列表 接口） import os import tushare as ts 读取环境变量中的token, 或者读取本地记录的token token = os . getenv ( 'TUSHARE_TOKEN' ) or ts ...
 5.5K
1804 ctf-crypto ljagiello/ctf-skills
CTF Cryptography Quick reference for crypto CTF challenges. Each technique has a one-liner here; see supporting files for full details with code. Additional Resources classic-ciphers.md - Classic ciphers: Vigenere (+ Kasiski examination), Atbash, substitution wheels, XOR variants (+ multi-byte frequency analysis), deterministic OTP, cascade XOR, book cipher, OTP key reuse / many-time pad modern-ciphers.md - Modern cipher attacks: AES (CFB-8, ECB leakage), CBC-MAC/OFB-MAC, padding oracle, S-box c...
 5.5K
1805 insecure-defaults trailofbits/skills
Finds fail-open vulnerabilities where apps run insecurely with missing configuration. Distinguishes exploitable defaults from fail-secure patterns that crash safely. - Fail-open (CRITICAL): `SECRET = env.get('KEY') or 'default'` → App runs with weak secret - Fail-secure (SAFE): `SECRET = env['KEY']` → App crashes if missing When to Use - Security audits of production applications (auth, crypto, API security) - Configuration review of deployment files, IaC templates, Docker configs - Code ...
 5.5K
1806 superdesign superdesigndev/superdesign-skill
SuperDesign helps you (1) find design inspirations/styles and (2) generate/iterate design drafts on an infinite canvas. Core scenarios (what this skill handles) Help me design X (feature/page/flow) Set design system Help me improve design of X How it works Fetch fresh guidelines below: https://raw.githubusercontent.com/superdesigndev/superdesign-skill/main/skills/superdesign/SUPERDESIGN.md Action accordingly based on instruction in the guidelines Superdesign CLI npm install -g @superdesign...
 5.5K
1807 ctf-osint ljagiello/ctf-skills
CTF OSINT Quick reference for OSINT CTF challenges. Each technique has a one-liner here; see supporting files for full details. Additional Resources social-media.md - Twitter/X (user IDs, Snowflake timestamps, Nitter, memory.lol, Wayback CDX), Tumblr (blog checks, post JSON, avatars), BlueSky search + API, Unicode homoglyph steganography, Discord API, username OSINT (namechk, whatsmyname), platform false positives, multi-platform chains geolocation-and-media.md - Image analysis, reverse image se...
 5.5K
1808 codeql trailofbits/skills
CodeQL Static Analysis When to Use CodeQL Ideal scenarios: Source code access with ability to build (for compiled languages) Open-source projects or GitHub Advanced Security license Need for interprocedural data flow and taint tracking Finding complex vulnerabilities requiring AST/CFG analysis Comprehensive security audits where analysis time is not critical Consider Semgrep instead when: No build capability for compiled languages Licensing constraints Need fast, lightweight pattern matching...
 5.5K
1809 ljg-plain lijigang/ljg-skills
ljg-plain: 白 让人 grok。 不规定怎么写。规定不能怎么写。下限锁死，上限放开。不同主题有不同的最佳写法——类比、故事、问答、递进的例子、一个长场景——由内容决定形式。 格式约束 Org-mode 语法 加粗用 *bold* （单星号），禁止 bold 标题层级从 * 开始，不跳级 ASCII Art 所有图表用纯 ASCII 字符。允许： + - | / \ > < v ^ * = ~ . : [ ] ( ) _ , ; ! ' " 和空格。禁止 Unicode 绘图符号。 Denote 文件规范 时间戳： date +%Y%m%dT%H%M%S 可读时间： date "+%Y-%m-%d %a %H:%M" 文件名： {时间戳}--plain-{简短标题}__plain.org 输出目录： ~/Documents/notes/ Org 文件头 +title: plain-{简短标题} +date: [{YYYY-MM-DD Day HH:MM}] +filetags: :plain:atom: +identifier: {YYYYMMDDT...
 5.5K
1810 ljg-writes lijigang/ljg-skills
写作引擎 对准一个观点下刀，一层层剥开，挖到底。 约束 Org-mode 语法 加粗用 *bold* （单星号），禁止 bold 标题层级从 * 开始，不跳级 ASCII Art 所有图表用纯 ASCII 字符。允许： + - | / \ > < v ^ * = ~ . : [ ] ( ) _ , ; ! ' " 和空格。禁止 Unicode 绘图符号。 Denote 文件规范 时间戳： date +%Y%m%dT%H%M%S 可读时间： date "+%Y-%m-%d %a %H:%M" 文件名： {时间戳}==z--{标题关键词}__write.org 输出目录： ~/Documents/notes/ Org 文件头 +title: {标题} +date: [{YYYY-MM-DD Day HH:MM}] +filetags: :write: +identifier: {YYYYMMDDTHHMMSS} +author: 李继刚 姿态 外科医生的手，朋友的口。下刀时冷静、精准、不抖；讲话时平常、直接、不绕。 心里放一个具体的人，写给他，不写给「读...
 5.5K
1811 ljg-learn lijigang/ljg-skills
Usage Instructions 你是概念解剖师。拿到一个概念，从八个方向切开它，最后把所有切面压成一句顿悟。 1. 定锚 这个概念最通行的定义是什么？常见误解在哪？ 概念里藏着哪几个核心词素？ 2. 八刀 八个方向各切一刀。每刀 2-3 句，只留筋骨，不带水分。 历史 ：最早从哪冒出来 → 怎么变的 → 哪一步拐成了今天的意思 辩证 ：它的反面是什么 → 正反碰撞后，更高一层的理解是什么 现象 ：扔掉所有预设，回到事情本身 → 用一个日常场景把它还原出来 语言 ：拆字源（中/英/希腊/拉丁）→ 画出相邻概念的语义网 → 这个词暗含什么隐喻 形式 ：写一个公式或形式化表达 → 公式在哪里失效 存在 ：这个概念改变了人怎么活着 美感 ：它美在哪？用一个具体意象呈现 元反思 ：我们在用什么隐喻理解它？这个隐喻挡住了什么？换一个会怎样 3. 内观 变成这个概念本身，用第一人称看世界。3-5 句。 八刀之中，哪几刀指向同一个深层结构？把它提出来。 4. 压缩 公式 ： 概念 = ... 一句话 ：用最简单的话说出最深的理解 结构图 ：纯 ASCII 画出概念的骨架（只用 +-|/<>*=_...
 5.5K
1812 academic-paper-reviewer imbad0202/academic-research-skills
Academic Paper Reviewer v1.4 — Multi-Perspective Academic Paper Review Agent Team Simulates a complete international journal peer review process: automatically identifies the paper's field, dynamically configures 5 reviewers (Editor-in-Chief + 3 peer reviewers + Devil's Advocate) who review from four non-overlapping perspectives — methodology, domain expertise, cross-disciplinary viewpoints, and core argument challenges — ultimately producing a structured Editorial Decision and Revision Roadmap....
 5.5K
1813 ponytail-audit dietrichgebert/ponytail
ponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank findings biggest cut first. Tags Same as ponytail-review: delete: dead code, unused flexibility, speculative feature. Replacement: nothing. stdlib: hand-rolled thing the standard library ships. Name the function. native: dependency or code doing what the platform already does. Name the feature. yagni: abstraction with one implementation, config nobody sets, layer with one caller. shrink: same logic, fewer lines. Show the sho...
 5.5K
1814 agentation supercent-io/skills-template
Agentation Setup Set up the Agentation annotation toolbar in this project. Steps Check if already installed Look for agentation in package.json dependencies If not found, run npm install agentation (or pnpm/yarn based on lockfile) Check if already configured Search for <Agentation or import { Agentation } in src/ or app/ If found, report that Agentation is already set up and exit Detect framework Next.js App Router: has app/layout.tsx or app/layout.js Next.js Pages Router: has pages/_app.tsx or ...
 5.4K
1815 configure-ecc affaan-m/everything-claude-code
Configure Everything Claude Code (ECC) An interactive, step-by-step installation wizard for the Everything Claude Code project. Uses AskUserQuestion to guide users through selective installation of skills and rules, then verifies correctness and offers optimization. When to Activate User says "configure ecc", "install ecc", "setup everything claude code", or similar User wants to selectively install skills or rules from this project User wants to verify or fix an existing ECC installation User w...
 5.4K
1816 verification-loop affaan-m/everything-claude-code
Verification Loop Skill A comprehensive verification system for Claude Code sessions. When to Use Invoke this skill: After completing a feature or significant code change Before creating a PR When you want to ensure quality gates pass After refactoring Verification Phases Phase 1: Build Verification Check if project builds npm run build 2 > &1 | tail -20 OR pnpm build 2 > &1 | tail -20 If build fails, STOP and fix before continuing. Phase 2: Type Check TypeScript projects npx tsc --noEmit 2 >...
 5.4K
1817 on-page-seo-auditor aaron-he-zhu/seo-geo-claude-skills
This skill performs detailed on-page SEO audits to identify issues and optimization opportunities. It analyzes all on-page elements that affect search rankings and provides actionable recommendations. When to Use This Skill - Auditing pages before or after publishing - Identifying why a page isn't ranking well - Optimizing existing content for better performance - Creating pre-publish SEO checklists - Comparing your on-page SEO to competitors - Systematic site-wide SEO improvements - Tr...
 5.4K
1818 search-first affaan-m/everything-claude-code
/search-first — Research Before You Code Systematizes the "search for existing solutions before implementing" workflow. Trigger Use this skill when: Starting a new feature that likely has existing solutions Adding a dependency or integration The user asks "add X functionality" and you're about to write code Before creating a new utility, helper, or abstraction Workflow ┌─────────────────────────────────────────────┐ │ 1. NEED ANALYSIS │ │ Define what functionality ...
 5.4K
1819 nutrient-document-processing affaan-m/everything-claude-code
Nutrient Document Processing Process documents with the Nutrient DWS Processor API . Convert formats, extract text and tables, OCR scanned documents, redact PII, add watermarks, digitally sign, and fill PDF forms. Setup Get a free API key at nutrient.io export NUTRIENT_API_KEY = "pdf_live_..." All requests go to https://api.nutrient.io/build as multipart POST with an instructions JSON field. Operations Convert Documents DOCX to PDF curl -X POST https://api.nutrient.io/build \ -H "Authorization:...
 5.4K
1820 meme-rush binance/binance-skills-hub
Meme Rush Skill Overview Meme Rush — Launchpad token lifecycle tracking rankType Stage Description 10 New Freshly created meme tokens still on bonding curve 20 Finalizing Tokens about to migrate (bonding curve nearly complete) 30 Migrated Tokens that just migrated to DEX Topic Rush — AI-powered market hot topic discovery rankType Stage Description 10 Latest Newest hot topics 20 Rising Rising topics with all-time high inflow between $1k–$20k 30 Viral Viral topics with all-time high inflow above $...
 5.4K
1821 web-scraping jamditis/claude-skills-journalism
Web scraping methodology Patterns for reliable, ethical web scraping with fallback strategies and anti-bot handling. Scraping cascade architecture Implement multiple extraction strategies with automatic fallback: from abc import ABC , abstractmethod from typing import Optional import requests from bs4 import BeautifulSoup import trafilatura for .py files from playwright . sync_api import sync_playwright from playwright_stealth import stealth_sync for .ipynb files import asyncio from playwright ....
 5.4K
1822 query-address-info binance/binance-skills-hub
Query Address Info Skill Overview This skill queries any on-chain wallet address for token holdings, supporting: List of all tokens held by a wallet address Current price of each token 24-hour price change percentage Holding quantity API Endpoint Query Wallet Token Balance Method : GET URL : https://web3.binance.com/bapi/defi/v3/public/wallet-direct/buw/wallet/address/pnl/active-position-list Request Parameters : Parameter Type Required Description address string Yes Wallet address, e.g., 0x0000...
 5.4K
1823 speech-to-text elevenlabs/skills
ElevenLabs Speech-to-Text Transcribe audio to text with Scribe v2 - supports 90+ languages, speaker diarization, and word-level timestamps. Setup: See Installation Guide . For JavaScript, use @elevenlabs/* packages only. Quick Start Python from elevenlabs import ElevenLabs client = ElevenLabs ( ) with open ( "audio.mp3" , "rb" ) as audio_file : result = client . speech_to_text . convert ( file = audio_file , model_id = "scribe_v2" ) print ( result . text ) JavaScript import { ElevenLabsClient } ...
 5.4K
1824 threejs-geometry cloudai-x/threejs-skills
Three.js Geometry Quick Start import * as THREE from "three"; // Built-in geometry const box = new THREE.BoxGeometry(1, 1, 1); const sphere = new THREE.SphereGeometry(0.5, 32, 32); const plane = new THREE.PlaneGeometry(10, 10); // Create mesh const material = new THREE.MeshStandardMaterial({ color: 0x00ff00 }); const mesh = new THREE.Mesh(box, material); scene.add(mesh); Built-in Geometries Basic Shapes // Box - width, height, depth, widthSegments, heightSegments, depthSegments new THREE.BoxG...
 5.4K
1825 ctf-forensics ljagiello/ctf-skills
CTF Forensics & Blockchain Quick reference for forensics CTF challenges. Each technique has a one-liner here; see supporting files for full details. Additional Resources 3d-printing.md - 3D printing forensics (PrusaSlicer binary G-code, QOIF, heatshrink) windows.md - Windows forensics (registry, SAM, event logs, recycle bin, USN journal, PowerShell history, Defender MPLog, WMI persistence, Amcache) network.md - Network forensics (PCAP, SMB3, WordPress, credentials, NTLMv2 cracking, USB HID steno...
 5.4K
1826 agent-harness-construction affaan-m/everything-claude-code
Agent Harness Construction Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion. Core Model Agent output quality is constrained by: Action space quality Observation quality Recovery quality Context budget quality Action Space Design Use stable, explicit tool names. Keep inputs schema-first and narrow. Return deterministic output shapes. Avoid catch-all tools unless isolation is impossible. Granularity Rules Use micro-tools for h...
 5.4K
1827 query-token-audit binance/binance-skills-hub
Query Token Audit Skill Overview API Function Use Case Token Security Audit Token security scan Detect honeypot, rug pull, scam, malicious functions Use Cases Pre-Trade Safety Check : Verify token security before buying or swapping Scam Detection : Identify honeypots, fake tokens, and malicious contracts Contract Analysis : Check for dangerous ownership functions and hidden risks Tax Verification : Detect unusual buy/sell taxes before trading Supported Chains Chain Name chainId BSC 56 Base 8453 ...
 5.4K
1828 task-management anthropics/knowledge-work-plugins
Task Management Tasks are tracked in a simple TASKS.md file that both you and the user can edit. File Location Always use TASKS.md in the current working directory. If it exists, read/write to it If it doesn't exist, create it with the template below Dashboard Setup (First Run) A visual dashboard is available for managing tasks and memory. On first interaction with tasks: Check if dashboard.html exists in the current working directory If not, copy it from ${CLAUDE_PLUGIN_ROOT}/skills/dashboard.h...
 5.4K
1829 argent-android-emulator-setup software-mansion/argent
1. Prerequisites Android SDK Platform Tools on PATH — provides adb . Android Emulator on PATH — needed to boot AVDs. If you will only use an already-running emulator or a physical device, adb alone is sufficient. An AVD created via Android Studio or avdmanager create avd . Verify with adb version and emulator -list-avds . 2. Setup Find a ready device — call list-devices . Filter for entries with platform: "android" . Ready devices ( state: "device" ) come first. Pick the first serial (e.g. emula...
 5.4K
1830 ljg-rank lijigang/ljg-skills
降秩引擎 输入一个领域，输出它的秩。 秩是什么 秩不是"关键要素"，不是"核心原则"，不是"总结要点"。 秩是：这个领域里真正独立的生成器有几个？用它们能反向生成全部现象？能，才算找到。 四条心内判据 这四条是你写之前心里过完的内功， 不是叙事的钩子 。 生成性 ——生成器能把每个现象推回来 最小性 ——拿掉任何一根，就有现象解释不了 独立性 ——每对都能找到"一个变另一个没变"的案例 预测力 ——能推出清单外的现象，现实中确实存在 过不了一条，推倒重来。 判据心里扎实过，但 不要写进文章 ——不要出现"砍一刀看看""拆一根试试"这种验证动作。它们会打断读者从"乱"到"简"的那口气。读者看不到验证，但感觉得到背后是硬的。 怎么写 一气呵成的散文。 带读者走一段路——从"这个领域看着挺乱"走到"原来就这几根线在牵"。不设章节，不加小标题，让推理自身推着往前走。 三条要求： 一口气读完 ——不了解这个领域的人也停不下来 记得住 ——读完能转身跟朋友用一句话说清楚 有落差 ——从混沌到极简的反差，就是降秩的美感 文末配一张 ASCII 结构图 光说"这几根线"不够——要 画出这几根之间的关系...
 5.4K
1831 thermo-nuclear-code-quality-review cursor/plugins
No SKILL.md available for this skill. View on GitHub
 5.4K
1832 argent-device-interact software-mansion/argent
Unified tool surface All interaction tools below accept a udid parameter and auto-dispatch iOS vs Android based on its shape (UUID → iOS simulator, anything else → Android adb serial). You use the same tool names on both platforms. For platform-specific caveats (Metro adb reverse , locked-screen describe errors, etc.), see § 9 Platform-specific notes at the bottom. 1. Before You Start If you delegate simulator tasks to sub-agents, make sure they have MCP permissions. Use list-devices to get a ta...
 5.4K
1833 argent-react-native-app-workflow software-mansion/argent
No SKILL.md available for this skill. View on GitHub Installs 871 Repository software-mansion/argent GitHub Stars 1.1K First Seen Apr 28, 2026
 5.4K
1834 argent-ios-simulator-setup software-mansion/argent
1. Setup Steps If you delegate simulator tasks to sub-agents, make sure they have MCP permissions. Find a booted simulator Use list-devices . Filter for entries with platform: "ios" — booted iPhones are listed first. If none are booted, call boot-device with udid: <chosen UDID> . Verify connection All interaction tools ( gesture-tap , gesture-swipe , gesture-custom , etc.) auto-start the server if not already running. 2. Notes UDIDs look like: A1B2C3D4-E5F6-7890-ABCD-EF1234567890
 5.4K
1835 argent-test-ui-flow software-mansion/argent
No SKILL.md available for this skill. View on GitHub Installs 875 Repository software-mansion/argent GitHub Stars 1.1K First Seen Apr 28, 2026
 5.4K
1836 argent-react-native-profiler software-mansion/argent
This skill is complementary to argent-react-native-optimization , not a replacement for it. 2. Tool Overview React Profiler (Hermes / React commits) Tool Purpose react-profiler-start Start CPU sampling + inject React commit-capture hook. Optional: sample_interval_us (default 100). react-profiler-stop Stop recording; stores cpuProfile + commitTree in session. react-profiler-status Call if you were interrupted in the middle of the flow, never in another scenario (debugger drop, Metro reload, pause...
 5.4K
1837 argent-metro-debugger software-mansion/argent
No SKILL.md available for this skill. View on GitHub Installs 870 Repository software-mansion/argent GitHub Stars 1.1K First Seen Apr 28, 2026
 5.4K
1838 argent-native-profiler software-mansion/argent
1. Tools native-profiler-start — start profiling on a booted device. iOS: xctrace recording for CPU, hangs, and leaks. native-profiler-stop — stop the profiler and export trace data to timestamped XML files. native-profiler-analyze — parse exported trace data and return a structured bottleneck payload. profiler-stack-query — drill into parsed data: hang stacks, function callers, thread breakdown, leak details. profiler-load — list and reload previous trace sessions from disk for re-investigation...
 5.4K
1839 argent-react-native-optimization software-mansion/argent
Rules Do not apply shotgun optimizations. Measure first, define what "good enough" looks like (target metric + threshold), fix the top offender, re-measure honestly. Quick scan — react-profiler-renders for a live render count table. Identifies hot components instantly. Deep measure — load argent-react-native-profiler skill. react-profiler-start → interact → react-profiler-stop → react-profiler-analyze . Inspect — react-profiler-component-source per finding. react-profiler-fiber-tree to trace com...
 5.4K
1840 sanity-migration sanity-io/agent-toolkit
Sanity Migration Use this skill for CMS-to-Sanity migration work. Treat migration as a content strategy and ETL project, not a blind lift-and-shift. Required Workflow Read references/general.md first. If the source platform is known, also read its guide: AEM / Adobe Experience Manager: references/aem.md Contentful: references/contentful.md Strapi: references/strapi.md Webflow: references/webflow.md WordPress / WXR / Elementor: references/wordpress.md Payload: references/payload.md Drupal: refere...
 5.4K
1841 django-verification affaan-m/everything-claude-code
Django Verification Loop Run before PRs, after major changes, and pre-deploy to ensure Django application quality and security. When to Activate Before opening a pull request for a Django project After major model changes, migration updates, or dependency upgrades Pre-deployment verification for staging or production Running full environment → lint → test → security → deploy readiness pipeline Validating migration safety and test coverage Phase 1: Environment Check Verify Python version python ...
 5.4K
1842 argent-create-flow software-mansion/argent
1. Overview A flow is a recorded sequence of MCP tool calls saved to a .yaml file in the .argent/flows/ directory. Each step is executed live as you add it, so you verify it works before it becomes part of the flow. Replay a finished flow with flow-execute . 2. Tools Tool Purpose flow-start-recording Start recording — takes a name and executionPrerequisite, creates the file flow-add-step Execute a tool call live and record it if it succeeds flow-add-echo Add a label/comment that prints during re...
 5.4K
1843 geo-content-optimizer aaron-he-zhu/seo-geo-claude-skills
GEO Content Optimizer SEO & GEO Skills Library · 20 skills for SEO + GEO · Install all: npx skills add aaron-he-zhu/seo-geo-claude-skills Research · keyword-research · competitor-analysis · serp-analysis · content-gap-analysis Build · seo-content-writer · geo-content-optimizer · meta-tags-optimizer · schema-markup-generator Optimize · on-page-seo-auditor · technical-seo-checker · internal-linking-optimizer · content-refresher Monitor · rank-tracker · backlink-analyzer · performance-reporter · al...
 5.3K
1844 springboot-verification affaan-m/everything-claude-code
Spring Boot Verification Loop Run before PRs, after major changes, and pre-deploy. When to Activate Before opening a pull request for a Spring Boot service After major refactoring or dependency upgrades Pre-deployment verification for staging or production Running full build → lint → test → security scan pipeline Validating test coverage meets thresholds Phase 1: Build mvn -T 4 clean verify -DskipTests or ./gradlew clean assemble -x test If build fails, stop and fix. Phase 2: Static Analysis Ma...
 5.3K
1845 cost-aware-llm-pipeline affaan-m/everything-claude-code
Cost-Aware LLM Pipeline Patterns for controlling LLM API costs while maintaining quality. Combines model routing, budget tracking, retry logic, and prompt caching into a composable pipeline. When to Activate Building applications that call LLM APIs (Claude, GPT, etc.) Processing batches of items with varying complexity Need to stay within a budget for API spend Optimizing cost without sacrificing quality on complex tasks Core Concepts 1. Model Routing by Task Complexity Automatically select chea...
 5.3K
1846 okx-sentiment-tracker okx/agent-skills
OKX News & Sentiment Crypto news aggregation and coin sentiment analysis for OKX. All commands are read-only and require API credentials (OAuth2.1). Capabilities User Intent Command Latest/important news okx news latest Coin-specific news okx news by-coin Keyword news search okx news search Sentiment-filtered news okx news by-sentiment Full article content okx news detail Coin sentiment snapshot okx news coin-sentiment Sentiment trend okx news coin-trend Sentiment ranking okx news sentiment-rank...
 5.3K
1847 agentic-engineering affaan-m/everything-claude-code
Agentic Engineering Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls. Operating Principles Define completion criteria before execution. Decompose work into agent-sized units. Route model tiers by task complexity. Measure with evals and regression checks. Eval-First Loop Define capability eval and regression eval. Run baseline and capture failure signatures. Execute implementation. Re-run evals and compare delta...
 5.3K
1848 changelog-generator composiohq/awesome-claude-skills
Changelog Generator This skill transforms technical git commits into polished, user-friendly changelogs that your customers and users will actually understand and appreciate. When to Use This Skill Preparing release notes for a new version Creating weekly or monthly product update summaries Documenting changes for customers Writing changelog entries for app store submissions Generating update notifications Creating internal release documentation Maintaining a public changelog/product updates p...
 5.3K
1849 ljg-invest lijigang/ljg-skills
投资报告 生成一份投资分析报告。核心只问一个问题：这个东西在创造新秩序，还是在搬运旧秩序？ 认知起点 财富不是钱，是被欲望照亮的秩序。投资就是拿手里的秩序去换一台更好的秩序生成器。 所以不称重，看相： 不问"这个公司值多少钱"，问"这台机器转不转得起来" 不问"市场多大"，问"市场在用什么过时的眼睛看它" 不问"能涨多少"，问"我拿什么换什么，换完之后谁更聪明" 输入 公司名称、BP、文字介绍、对话记录，或任何描述项目的材料。知名公司只给名字即可——用 Research skill 或 subagent 抓取最新财报和行业数据。 报告结构 以下五个区块是骨架，不是填空题。对某个项目来说哪个区块最有料，那个区块就多写；没料的一两句带过或直接跳过。报告为判断服务，不为完整性服务。 一、这是什么 一张表 + 一句自定义赛道定义。 维度 内容 项目名称 赛道定义 用我们自己的语言，不用市场标签 阶段 融资情况 金额 / 估值 / 条款（有则填，无则标注） 数据快照 关键运营数据 赛道定义要穿透表面标签。"搜索引擎公司"是隔的，"人类认知基础设施的垄断运营商"是不隔的——后者告诉你它真正在做什么...
 5.3K
1850 solve-challenge ljagiello/ctf-skills
CTF Challenge Solver You're a skilled CTF player. Your goal is to solve the challenge and find the flag. Workflow Step 1: Recon Explore files -- List the challenge directory, run file * on everything Triage binaries -- strings , xxd | head , binwalk , checksec on binaries Fetch links -- If the challenge mentions URLs, fetch them FIRST for context Connect -- Try remote services ( nc ) to understand what they expect Read hints -- Challenge descriptions, filenames, and comments often contain clues ...
 5.3K