lecture-live-edit

lecture-live-edit is a skill for Claude Code from parkjui92/lecture-deck-kit. It costs 250 tokens per session (2,522 once invoked), scanned A, original, MIT.

An operating procedure for live-editing HTML lecture materials or documents in a browser. It moves selected-text feedback through a queue, applies the change to the matching slide, and publishes the update for automatic screen refresh.

In plain words
What is it for?
Use it to start or resume live editing, process pending feedback, locate slides by identifiers and selected text, publish changes, and undo edits.
Why use it?
It prevents feedback from being lost, processed twice, or applied to the wrong slide. It also keeps reversible snapshots before edits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the lecture-deck-kit plugin — 3 skills shipped together

Good fit Use it to start or resume live editing, process pending feedback, locate slides by identifiers and selected text, publish changes, and undo edits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parkjui92/lecture-deck-kit/lecture-live-edit
Install

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.

Any agent
npx skills add parkjui92/lecture-deck-kit --skill lecture-live-edit
Clone the repo
git clone --depth 1 https://github.com/parkjui92/lecture-deck-kit

Made for: Claude Code.

Or install lecture-deck-kit, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for lecture-live-edit

README.md
[![agentmods](https://agentmods.dev/badge/skills/parkjui92/lecture-deck-kit/lecture-live-edit/github.svg)](https://agentmods.dev/skills/parkjui92/lecture-deck-kit/lecture-live-edit)
Your own site
<a href="https://agentmods.dev/skills/parkjui92/lecture-deck-kit/lecture-live-edit"><img src="https://agentmods.dev/badge/skills/parkjui92/lecture-deck-kit/lecture-live-edit/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.

agentmods 80×15 button for lecture-live-edit

Your own site · 80×15
<a href="https://agentmods.dev/skills/parkjui92/lecture-deck-kit/lecture-live-edit"><img src="https://agentmods.dev/badge/skills/parkjui92/lecture-deck-kit/lecture-live-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 250 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,522 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00250 $0.02522
Opus 5.5 $0.00100 $0.01009
Sonnet 5.5 $0.00050 $0.00504
Haiku 4.5 $0.00025 $0.00252

Measured 1mo ago against content hash 6f2d6775424b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lecture-live-edit 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/editor.js, scripts/lle_state.py, scripts/lle.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/lecture-live-edit/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

라이브 편집 운영 규약

브라우저 → 큐 → Claude → 화면 갱신의 루프를 유실 없이, 엉뚱한 슬라이드를 고치지 않고 돌리는 절차.

왜 이 절차를 지켜야 하는가

상태의 진실은 두 파일뿐이다. feedback/queue.jsonl(피드백 원본, 추가 전용)과 feedback/cursor(처리한 줄 수). 미처리 = 줄 수 − 커서라는 산술 하나로만 판정하기 때문에, 알림이 유실되거나 중복돼도, 드레인 도중 새 피드백이 도착해도 아무것도 잃지 않는다. 이 불변식은 lle.py 로만 상태를 바꿀 때 유지된다. 커서를 손으로 고치거나 큐를 편집하면 깨진다.

도구 경로 확인 (세션에서 한 번)

스크립트 4종은 이 스킬 폴더 안 scripts/ 에 있다. 설치 위치는 환경마다 다르므로 한 번 찾아 둔다.

TOOL=$(dirname "$(find ~/.claude -name lle.py -path '*lecture-live-edit/scripts*' 2>/dev/null | head -1)")
echo "$TOOL"     # 이후 python3 "$TOOL"/lle.py … 로 쓴다

찾지 못하면 플러그인이 설치되지 않은 것이다. 사용자에게 설치를 안내한다. 아래 예시의 $TOOL 은 모두 이 경로를 가리킨다.


드레인 절차 (알림이 오면 / "ㄱ" 신호를 받으면 / 턴 시작 시 pending>0이면)

1단계 — 꺼내기

python3 $TOOL/lle.py pending --root <프로젝트폴더>

출력의 items 가 처리 대상, cursor_after 를 3단계에 그대로 넘긴다. 이 명령이 편집 직전 스냅샷을 versions/ 에 남기므로 되돌리기가 항상 가능하다. (pending 이 0이면 아무것도 하지 않고 조용히 끝낸다. 중복 알림은 정상이다.)

2단계 — 고치기

항목 하나하나를 다음 순서로 처리한다.

  1. 대상 슬라이드 찾기 — sid 로 data-sid="..." 를 찾는다.
  2. 대조 검증 (필수) — 그 슬라이드의 제목이 titleExcerpt 와 맞는지 본다. 어긋나면 편집하지 말고 그 항목을 --needs-input 으로 돌린다. 엉뚱한 슬라이드를 조용히 고치는 것이 이 시스템의 최악의 실패다.
  3. 정확한 위치 앵커링 — selectedText 를 소스에서 찾는다. 여러 번 나오면 contextBefore / contextAfter 로 좁힌다. elemHint(예: "표 셀 #2")가 있으면 그 요소 안에서 찾는다. scope 가 slide 면 그 장 전체, deck 이면 자료 전체가 대상이다.
  4. 지시 반영 — instruction 이 본문, quickActions 는 보조 신호다. 둘이 충돌하면 instruction 이 이긴다. 퀵칩의 뜻: 둘로 쪼개기=슬라이드 분할 / 근거 보강=수치·출처 추가 / 덜 방어적으로=단정적으로 고쳐 씀 / 더 간결하게=문장 수 줄임 / 표를 대비형으로=행 나열을 A vs B 열 구조로 / 시각화 추가=흐름도·카드·통계 블록.
  5. 마크업 문법은 lecture-deck-build 스킬의 references/slide-contract.md 를 따른다.

슬라이드를 쪼갤 때 — 앞쪽이 기존 sid 를 승계하고, 뒤쪽은 sNN-2, sNN-3 을 새로 받는다. 절대 전체 재번호를 매기지 않는다. 대기 중인 다른 피드백이 엉뚱한 장을 가리키게 된다. 합칠 때는 앞쪽 sid 를 남긴다. 순서를 바꿔도 sid 는 따라다닌다(표시 번호는 런타임이 계산).

3단계 — 마치기

python3 $TOOL/lle.py done --root <폴더> --cursor <1단계의 cursor_after> \
        --note "무엇을 고쳤는지 한 줄" [--needs-input <id,id>] [--skipped <id>]

Read the full file on GitHub · 153 lines

Files

What ships with it

6 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.

Changes

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.

  1. 1mo ago First seen · 153 lines · 250 tokens per session scan A 6f2d6775424b

Subscribe to this mod's changes

lecture-live-edit is a skill published in the GitHub repository parkjui92/lecture-deck-kit (4 stars, last pushed 16d ago), licensed MIT. It adds 250 tokens to every session and 2,522 once invoked, about $0.0010 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

manage-learnus-session

Connect to Yonsei LearnUs in the student's persistent browser profile, reuse the official portal login, and recover from session expiry without receiving credentials in chat. Use when LearnUs login is required, a browser session expired, or the student asks to stay signed in; use the optional terminal session only…

mrcha033/yonsei-skills · 75 tokens

find-yonsei-attendance-discrepancies

Compare displayed and user-expected statuses from the authorized live Yonsei attendance page first, identify records explicitly disputed by the user, and report which items have enough reason and evidence to draft a correction; use a screenshot, pasted table, export, or JSON only when the live page is unavailable or…

mrcha033/yonsei-skills · 82 tokens

re-report

A workflow for turning reverse-engineering results into a standard Korean report for beginners. Reverse engineering means examining software to understand how it works.

sodam-ai/SoDam-Reverse-Eng · 55 tokens

re-analyze-mycode

A read-only skill for explaining how source code you own or are allowed to inspect works, in beginner-friendly Korean.

sodam-ai/SoDam-Reverse-Eng · 61 tokens

skill-maker

A Korean-language helper for designing a new SKILL.md file through conversation. It creates the completed skill instructions with a small number of user inputs and a specified output format.

sodam-ai/SoDam-Prompt-Eng · 53 tokens

study-planner

A Korean-language study-planning guide that creates a weekday-based timetable from a subject, goal, and time period. It includes daily tasks, estimated study time, and regular review.

sodam-ai/SoDam-Prompt-Eng · 0 tokens