GET /v1/agent/search?capability=web_search
SKILL.md v2 also accepted as compatibility input.
Publish agent-generated markdown/HTML/code to a share link on the user's own GitHub Gist, GitLab Snippet, or Google Drive — full publish/update/delete/list lifecycle, one schema for all three backends.
Use when the user asks for Sales Enablement Training from supplied source materials. Trigger language: sales enablement training; sales readiness; go-to-market training; product launch training. Produce a grounded interactive digital-human course learners can interrupt with voice questions. Do not invent unsupported facts or claim external certification, competence, or real-world completion. Not limited to this scenario: handles any other course creation request with the same workflow.
Create, refine, resume, publish, or query polished PersonWise courses from topics, text, PDF/PPTX/DOCX/Markdown/TXT documents, or reference images with the PersonWise CLI. Use for staged course authoring, source-grounded lessons, slide and narration review, visual QA, presenter selection, layout configuration, link sharing, or Topics review submission.
IANA tzdata 기반 시간대 변환 + DST 경계 감지 — 시간대 변환, 서머타임 계산, 타임존 변환기. DST 전환 감지·멀티존 동시변환·DST 예보.
이미지 리사이즈·크롭·회전·포맷변환·워터마크·메타데이터 추출 — 이미지 변환, 이미지 리사이즈. Pillow 기반 오프라인 base64 I/O. Single-image transforms (see image-stitch-composer for multi-image merging).
ZIP/TAR/GZ 생성·압축·해제·검사 — 압축 파일, ZIP 해제, 아카이브 처리. Zero external dependencies, base64 I/O.
PowerPoint(.pptx) 생성·수정·읽기 — 파워포인트 생성, PPT 만들기, 슬라이드 자동화. python-pptx 기반 오프라인 base64 I/O.
Excel(.xlsx) 읽기·쓰기·분석 — 엑셀 처리, xlsx 읽기, spreadsheet 데이터 추출. Offline, base64 I/O, no filesystem mount needed.
Schema-driven realistic fake data generation with deterministic seed, foreign key consistency, multi-locale (Korean/en), and CSV/SQL output. Up to 1000 records per call. 테스트 데이터 생성, 더미 데이터, 가짜 데이터 자동 생성.
RFC 5321/5322 email validation with disposable domain detection (~200 built-in), typo correction (gmial→gmail), IDN/punycode support, and batch processing up to 100 addresses. Fully offline. 이메일 검증, 이메일 주소 유효성.
RFC 6238 TOTP / RFC 4226 HOTP one-time password generation and verification with otpauth URI parsing, provisioning URI generation, and time-drift leeway support. 2단계 인증, OTP 검증, 일회용 비밀번호.
Parse X.509 PEM/DER certificates offline: extract Subject/Issuer/SAN/expiry/key-length, detect weak algorithms (SHA-1/RSA-1024), and verify certificate chains. 인증서 검증, SSL 인증서 파싱, PKI 오프라인 검사.
Multi-engine web search aggregator supporting SerpAPI/Tavily/Brave/Bing with unified output schema, automatic fallback, and mock demo mode. 멀티 엔진 통합 검색, 자동 폴백, 웹 검색 통합 어댑터.
GraphQL SDL schema and query validation offline. GraphQL 스키마 검증, SDL 유효성 확인. Detects type conflicts, undefined fields, deprecated usage, and query depth violations.
SemVer 2.0 version comparison, range matching (^1.2.3, ~0.4.0, >=2.0.0 <3.0.0), sorting, and parsing. Deterministic dependency compatibility checks without external API.
Apply JMESPath expressions to JSON data for path-based extraction and filtering. JSON 경로 추출, API 응답 필터링. Deterministic, offline, no external API.
Validate Lua 5.3/5.4 source code via AST parsing. Returns error locations (line:col), error type, and optional AST summary. Deterministic, offline, no external API.
Search arXiv preprints (CS/AI/physics/math/economics) and return structured metadata — title, authors, abstract, DOI, categories, PDF URL — as JSON.
Parse, validate, and extract fields from HL7 v2.x pipe-delimited messages. Structured JSON output per segment. Covers ADT, ORU, ORM, SIU message types for legacy hospital system integration.
RFC 5545 .ics / iCalendar string parser — event extraction, RRULE expansion, timezone normalization, conflict detection