by DoHyun468 · Claude Skill · ★ 218
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
claude plugin install claw-hwp@claw-hwpTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 218 |
| Forks | 32 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 60/100 |
| Open Issues | 1 |
| Last Updated | 2026-11-07 |
| Created | 2026-05-07 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~15k |
claw-hwp Claude 에서 한글 문서 (.hwp / .hwpx) 를 다루는 Agent Skill — 읽기 · 만들기 · 편집 + 한컴오피스/한컴독스 호환 저장 보장. Claude Code · Desktop · 웹 어디서든. rhwp 파싱 엔진 + 자체 편집 인프라. 한국어 · English 소개 는 Claude 가 한글 문서 (.hwp / .hwpx) 를 직접 다룰 수 있도록 해주는 Agent Skill 입니다. 한국 사무 환경에서는 한컴오피스 형식이 사실상 표준인데, Claude 는 기본적으로 이 형식을 읽거나 편집하지 못합니다.
Looking for a claw-hwp alternative? If you're comparing claw-hwp with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
MCP server for reading and writing HWP/HWPX (Korean Hangul) documents — built on rhwp. 34 tools, Claude/Cursor
비개발자를 위한 한국 실무 AI 코워커 패밀리 — Claude Cowork·ChatGPT Work에서 /project 한 번으로 시작
Let AI agents edit Word documents without breaking them: fill in forms, update tables, restyle, write reports,
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
AI-writing humanizer for KO/EN/ZH/JA
모두의 AI (MoAI) — Claude Cowork & Claude Code 한국 실무 도메인 AI 하네스·플러그인 마켓플레이스. 사업계획서·세무·법률·HR·마케팅·커머스·BI·콘텐츠 도메인 스킬
Explore other popular claude skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: