🤖
Agent-First API
Agents can autonomously discover, evaluate, and install skills  ·  GET /v1/agent/search?capability=web_search
/llms.txt /v1/agent/info USK Spec Register Skill
USK v3 — AI Skill Store's primary skill standard. Write once, auto-convert for 7 platforms. Anthropic SKILL.md v2 also accepted as compatibility input.
📖 USK Guide USK Spec

🔥 Popular Skills — Top 5 by downloads

💡
Most Wanted · 3 unmet searches
e.g. code_generation searched 23×
Build it →

📦 All Skills 187

approved Data Processing 🔶 DRAFT 🔲 sandbox

A multi-model time series forecasting skill supporting ARIMA, Prophet, and LSTM with automatic model selection, backtesting, and confidence intervals for production-ready business forecasting.

approved Development 🔶 DRAFT 🔲 sandbox

Validates Kubernetes deployment manifests for misconfigurations

approved Data Processing 🔶 DRAFT 🔲 sandbox

Extracts structured data from PDF invoices including vendor name, invoice number, dates, line items, tax, and totals. Part of FinanceFlow AI DocuParse Pipeline v2.

approved Development

OpenAPI 3.0/3.1 spec 검증·보안감사·버전비교·예시생성·완성도 측정 — 30+ 규칙, 외부 의존성 0, 한국어 1급 / OpenAPI linter with 30+ rules, zero deps, Korean-first

approved Security

Static SQL injection vulnerability scanner for code review. Detects vulnerable patterns and suggests safe parameterized alternatives. Defensive use only — does not generate exploit payloads.

approved Development

JSON 데이터를 JSON Schema Draft-07 기준으로 유효성 검사합니다. 에이전트 API 응답 검증에 필수적입니다.

approved Data Processing

로그 파싱·군집·이상탐지·추출·위생검사 — 외부 의존성 0, 한국 PII 우선, 에이전트 네이티브 JSON. Parse, cluster, anomaly-detect, extract, and audit log lines with zero external dependencies and Korean-first PII detection.

approved Text Processing

Markdown parse, TOC, render, frontmatter, audit, summarize — zero external deps, Korean-first, agent-native stdin/stdout

approved AI/ML

LLM prompt static analysis, auto-optimization, security/quality audit (15+ rules), and A/B comparison — zero external deps, Korean-first, agent-native fix_hint

regex-builder v1.0.0
approved Development

자연어 설명으로 정규표현식을 생성하고, 테스트 케이스와 함께 설명을 제공합니다.

approved Text Processing

Rule-based writing style rewriter — 8 presets (Korean/English), formality detection, consistency analysis, fully offline / 룰 기반 문체 변환기 — 8종 프리셋, 격식도 감지, 일관성 분석, 완전 오프라인

jwt-toolkit v1.0.0
approved Security

JWT decode, verify, generate, and security audit — RFC 7519/7515 compliant, 15+ audit rules, Korean-first, fully offline

approved Development

Kubernetes manifest generator, linter, and explainer — 10 resource types, 30 lint rules, Korean/English output

sql-query v1.0.0
approved Development

Generate SQL from natural language, translate between 8 dialects, optimize queries for performance, debug errors, explain complex queries, and output ready-to-use analysis patterns (cohort, funnel, RFM, retention).

code-reviewer v1.0.0
approved Development

Analyze code for security vulnerabilities (OWASP Top 10), code smells, performance issues, and PR diff changes across 10 languages with severity scoring.

approved Knowledge

Draft ESG/sustainability disclosures across GRI, SASB, and TCFD frameworks

approved Knowledge

Compare funding options and recommend optimal capital mix by company stage

approved Knowledge

Internal control evaluation and Segregation of Duties analysis using COSO 2013 framework

approved Knowledge

Multi-dimensional investment ROI analysis with NPV, IRR, MIRR, sensitivity and scenarios

approved Knowledge

ABC costing and multi-dimensional profitability analysis

💬
Frequently Asked Questions
Getting started · Uploads · Most Wanted · Attribution · Security · MCP
See all →