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 agentmods add skills/kyopark2014/agent-plugins/ppt-translatornpx skills add kyopark2014/agent-plugins --skill ppt-translatorgit clone --depth 1 https://github.com/kyopark2014/agent-pluginsWrote 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/kyopark2014/agent-plugins/ppt-translator)<a href="https://agentmods.dev/skills/kyopark2014/agent-plugins/ppt-translator"><img src="https://agentmods.dev/badge/skills/kyopark2014/agent-plugins/ppt-translator.svg" alt="Measured on agentmods" 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 | $0.00114 | $0.01904 |
| Opus 5 | $0.00057 | $0.00952 |
| Sonnet 5 | $0.00023 | $0.00381 |
| Haiku 4.5 | $0.00011 | $0.00190 |
Grade A, and why
ppt-translator scanned grade A with 1 finding 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 4d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`subprocess.run()` 으로 실행할 때는 **`capture_output=False`** 를 사용해 번역 진행 상황을 실시간으로 출력한다. This is a copy
100% identical to ppt-translator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPT Translator (한국어 변환)
Directory Convention (경로 혼동 방지)
| 심볼 | 의미 |
|---|---|
{workspace} |
프로젝트(저장소) 루트 — application/ 디렉터리를 포함하는 최상위 경로 |
{WORKING_DIR} |
application/ 디렉터리 — 이 저장소에서 시스템이 노출하는 작업 루트 |
이 스킬의 유일한 소스·실행 루트:
{WORKING_DIR}/skills/ppt-translator
- 모든
cd,read_file,pip install -r requirements.txt경로는 위 경로를 기준으로 쓴다. python -m ppt_translator.cli를 쓰려면 CWD를 위 경로로 설정해야ppt_translator패키지가sys.path에 잡힌다.
번들 구성
| 항목 | 경로 |
|---|---|
| 에이전트 지침 | {WORKING_DIR}/skills/ppt-translator/SKILL.md (이 파일) |
| 패키지 | {WORKING_DIR}/skills/ppt-translator/ppt_translator/ |
| CLI | python -m ppt_translator.cli (Click) |
| 의존성 | {WORKING_DIR}/skills/ppt-translator/requirements.txt |
| 용어집 예시 | {WORKING_DIR}/skills/ppt-translator/glossary.yaml — CWD에 ./glossary.yaml 이 있으면 자동 탐색 |
전체 옵션: python -m ppt_translator.cli --help 및 각 서브커맨드 --help.
구조·클래스: ppt_translator/ppt_handler.py (FormattingExtractor, TextFrameUpdater, PowerPointTranslator).
upstream 문서: ppt-translator
데이터 흐름 (수정 시 이 순서 유지)
- 진입:
cli.py(Click). - 오케스트레이션:
ppt_handler.PowerPointTranslator— 슬라이드·도형·노트·차트 대상, 서식 보존 번역. - LLM:
translation_engine.py+bedrock_client.py,config.Config의 모델·토큰 한도. - 원문:
language_detection.py— 자동 감지(옵션); 원문==대상이면 API 생략. - 차트:
chart_handler.py— 메타 텍스트만 번역, 수치 유지. - 후처리:
post_processing.py—PowerPointPostProcessor등. - 캐시·비용:
cache.py,pricing.py. - 용어·프롬프트:
glossary.py,prompts.py.
별도 스크립트로 "간단 번역" 파이프라인을 만들지 말고 위 모듈을 확장한다.
한국어(ko) 기본값
ppt_translator/config.py 의 Config.DEFAULT_TARGET_LANGUAGE 는 기본 ko. 언어 미지정 시 대상은 한국어로 둔다. 한국어 폰트는 FONT_KOREAN / FONT_MAP['ko'].
사전 조건
- Python 3.11+
- AWS 자격 증명 + Bedrock 모델 액세스 (
AWS_REGION,BEDROCK_MODEL_ID등 —ppt_translator/config.py) - 선택:
{WORKING_DIR}/skills/ppt-translator/.env(config가 패키지 상위 루트의.env를 로드)
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- glossary.yaml 4.3 KB
- ppt_translator/bedrock_client.py 3.3 KB runs code
- ppt_translator/cache.py 4.6 KB runs code
- ppt_translator/chart_handler.py 8.8 KB runs code
- ppt_translator/cli.py 26 KB runs code
- ppt_translator/config.py 15 KB runs code
- ppt_translator/dependencies.py 2.5 KB runs code
- ppt_translator/glossary.py 3.2 KB runs code
- ppt_translator/language_detection.py 3.7 KB runs code
- ppt_translator/post_processing.py 7.7 KB runs code
- ppt_translator/ppt_handler.py 59 KB runs code
- ppt_translator/pricing.py 3.6 KB runs code
- ppt_translator/progress.py 3.9 KB runs code
- ppt_translator/prompts.py 3.6 KB runs code
- ppt_translator/retry.py 2.5 KB runs code
- ppt_translator/text_utils.py 18 KB runs code
- ppt_translator/translation_engine.py 12 KB runs code
- README.md 1.6 KB
- requirements.txt 108 B
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.
- 4d ago First seen · 149 lines · 114 tokens per session scan A 2a10ed94982a
ppt-translator is a skill published in the GitHub repository kyopark2014/agent-plugins (4 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 1,904 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to ppt-translator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
ppt-translator
Amazon Bedrock 기반 PowerPoint(.pptx) 번역. 서식·레이아웃·차트 메타(제목/축 등)를 보존하며 텍스트를 한국어(ko) 등 대상 언어로 변환. CLI(python -m ppttranslator.cli)·SQLite 캐시·용어집· 원문 언어 자동 감지. PPT/슬라이드 번역, pptx 한국어, Bedrock 프레젠테이션 번역, batch translate, dry-run 비용 추정.
translate-book
Translate books into any language using parallel sub-agents and generate a beautiful print-quality PDF. Converts input -> Markdown chunks -> translated chunks -> HTML -> PDF (6×9 inch, professional typography).
diagrammer
Local Diagram Generator. Translates natural language, structural code skeletons, and database schemas into clean, version-controlled visual models (Mermaid blocks and local Excalidraw JSON files) without external APIs or MCP servers. Enforces the Code -> Diagram -> Document pipeline.
chinese-traditional-conversion
Convert simplified Chinese to Traditional Chinese (zh-TW), covering characters, Taiwan vocabulary, and phrasing. Use when the user asks to convert 簡體 to 正體/繁體, localise mainland Chinese text for Taiwan, fix simplified characters left in a document or repository, check whether content is written in proper zh-TW, or…
deepagents-thread-inspector
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse…
query-writing
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.