Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hg-pyun/claude-code-marketplace --skill doctor-korean-documentgit clone --depth 1 https://github.com/hg-pyun/claude-code-marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hg-pyun/claude-code-marketplace/doctor-korean-document)<a href="https://agentmods.dev/skills/hg-pyun/claude-code-marketplace/doctor-korean-document"><img src="https://agentmods.dev/badge/skills/hg-pyun/claude-code-marketplace/doctor-korean-document/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hg-pyun/claude-code-marketplace/doctor-korean-document"><img src="https://agentmods.dev/badge/skills/hg-pyun/claude-code-marketplace/doctor-korean-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00229 | $0.05409 |
| Opus 5 | $0.00114 | $0.02704 |
| Sonnet 5 | $0.00046 | $0.01082 |
| Haiku 4.5 | $0.00023 | $0.00541 |
Grade A, and why
doctor-korean-document scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Use_When>
- User points at a Korean markdown/document file and asks to make it read naturally ("이 문서 다듬어줘", "번역투 고쳐줘")
- An AI-generated Korean doc (README, spec, guide) needs a humanizing pass before sharing
- User invokes
/doctor-korean-document <file>with one or more file paths - Another skill (e.g.,
github-pr) needs its drafted Korean prose polished — it applies this skill's catalog and principles to its draft text </Use_When>
<Do_Not_Use_When>
- The text is not in a file (pasted text, chat drafts) — this skill is file-only by design; polish inline text ad hoc without invoking the skill
- User wants meaning-level edits: restructuring content, adding/removing information, summarizing
- User wants translation (Korean→English or vice versa)
- The document is not primarily Korean
- User only wants mechanical spelling/spacing checks — a linter does that better </Do_Not_Use_When>
<Why_This_Exists>
AI writes Korean that is grammatically fine but recognizably machine-flavored: "~에 대해", "~를 통해", double passives like "~되어집니다", English word order wearing Korean particles. Readers spot it instantly and trust drops. Fixing it by hand is repetitive — the same dozen patterns recur in every generated document. This skill freezes those patterns into a maintainable catalog (consistent, personal-taste-tunable) and covers the long tail with stated principles, so any Korean document file can be brought to human-natural prose in one pass, reviewed through git diff like any other change.
</Why_This_Exists>
<Execution_Policy>
- File-only. Input is one or more file paths. The skill never operates on inline text when invoked directly. (Other skills may borrow the catalog and principles for their own draft text — that is their step, not this skill's invocation.)
- Edit in place. Modify the target file directly;
git diffis the review surface. Never create a side-by-side copy, never require pre-approval per change. - Intensity is bound to mechanism:
- Catalog pattern matched → phrase-level substitution only (swap the pattern, keep the sentence frame).
- Judgment (principle-based) → up to one-sentence rewrite (reorder, de-passivize, de-nominalize within that sentence).
- Never merge, split, reorder, or delete sentences; never restructure paragraphs. Verbosity trimming beyond the matched pattern is out of scope.
- Meaning is inviolable. A rewrite that could shift nuance is skipped, not risked. When unsure between a natural phrasing and the original meaning, keep the meaning.
- Protected regions are never edited (see
<Protected_Regions>). - Terminology is out of scope: never translate, replace, or "consistify" technical terms — deprioritized by design.
- Non-Korean sentences are left untouched (English paragraphs, foreign quotes).
- No auto-commit, no PR. The skill ends with the edited file and a short report; committing is the user's move.
- Session dialogue (the report) follows the calling-session language; the document itself stays Korean regardless of
$LANGUAGE. </Execution_Policy>
<Settings_Reference>
$LANGUAGE(pluginsettings.language, defaultKorean) does not govern this skill's output: the edited document is Korean by definition. Only the closing report follows the session language.--langis accepted but affects the report only. </Settings_Reference>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 207 lines · 229 tokens per session scan A f30842a14c24
doctor-korean-document is a skill published in the GitHub repository hg-pyun/claude-code-marketplace (2 stars, last pushed 2mo ago), licensed MIT. It adds 229 tokens to every session and 5,409 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.