lecture-asset

lecture-asset is a skill for Claude Code from johnfkoo951/cmdspace-plugins. It costs 232 tokens per session (6,318 once invoked), scanned A, original, MIT.

A workflow for turning a finished lecture, seminar, or workshop transcript into organized notes in an Obsidian vault. Obsidian is a note-taking application; the workflow creates a summary hub, preserves the transcript, splits claims into knowledge cards, links related notes, and adds a searchable view.

In plain words
What is it for?
Use it to process transcripts and AI summaries into lecture records, atomic claim cards, cross-links, and an Obsidian Bases table.
Why use it?
It prevents a transcript from becoming a forgotten file and makes the talk's ideas easier to find and reuse. A closing check identifies missing steps before the work is finished.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

Part of the lecture-asset plugin — 1 skill shipped together

Good fit Use it to process transcripts and AI summaries into lecture records, atomic claim cards, cross-links, and an Obsidian Bases table.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/johnfkoo951/cmdspace-plugins/lecture-asset
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 johnfkoo951/cmdspace-plugins --skill lecture-asset
Clone the repo
git clone --depth 1 https://github.com/johnfkoo951/cmdspace-plugins

Made for: Claude Code.

Or install lecture-asset, the plugin that ships this one along with the rest of its 1 skill.

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-asset

README.md
[![agentmods](https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/lecture-asset/github.svg)](https://agentmods.dev/skills/johnfkoo951/cmdspace-plugins/lecture-asset)
Your own site
<a href="https://agentmods.dev/skills/johnfkoo951/cmdspace-plugins/lecture-asset"><img src="https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/lecture-asset/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-asset

Your own site · 80×15
<a href="https://agentmods.dev/skills/johnfkoo951/cmdspace-plugins/lecture-asset"><img src="https://agentmods.dev/badge/skills/johnfkoo951/cmdspace-plugins/lecture-asset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 232 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,318 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 $0.00232 $0.06318
Opus 5.5 $0.00093 $0.02527
Sonnet 5.5 $0.00046 $0.01264
Haiku 4.5 $0.00023 $0.00632

Measured today against content hash 2d71fa376a7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lecture-asset 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 today.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check_asset_run.py, scripts/check_table_wikilinks.py, scripts/test_asset_run.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.

plugins/lecture-asset/skills/lecture-asset/SKILL.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lecture-asset — 강의 자산화 (post-lecture)

강의를 마친 뒤 전사본을 다시 쓸 수 있는 지식 자산으로 바꾸는 워크플로. 강의 한 번이 ① 이벤트 기록(허브) ② 바뀌지 않는 원자료(전사본·요약) ③ 재사용 지식 카드 ④ 날짜·주제별 조회(Base)의 4층 자산이 된다.

원칙: 일이 끝나면 회고를 거쳐 다음에 다시 쓸 수 있는 형태로 남긴다. 녹취를 저장만 하면 다시 열지 않는 파일이 된다. 이 스킬은 그 회고의 강의 버전이다.

이 스킬이 하는 세 가지

하는 일 볼트에서의 모양 단계
요약·인덱싱 허브 노트(한 줄 명제, 카드 목차, 타임코드) + Bases 표 7, 9
원소화 주장 하나 = 카드 하나. 제목은 주장형 문장 5
상호 연결 카드마다 ## 연결 절. 같은 주장은 새 카드 대신 기존 카드에 누적 5, 6

커뮤니티 플러그인이 필요 없다. Properties, 위키링크, 콜아웃, Bases(코어 플러그인)만 쓴다.

경로 설정 (처음 한 번)

아래 자리표시자는 예시 경로다. 쓰는 볼트의 폴더 구조에 맞게 바꾼다.

자리표시자 예시 값 무엇
{projects} Outputs/Lectures/ 강의 준비 자료와 강의 기록이 있는 폴더
{cards} Assets/Lecture Cards/ 지식 카드 라이브러리 (강의마다 하위 폴더 하나)
{shared} Assets/Lecture Cards/_Shared/ 강의를 넘나드는 공통 자산 노트 (선택)
{base} Bases/Lecture.base 강의 조회 Base. 예시 파일은 이 스킬의 assets/Lecture.base
{corrections} Assets/Transcription/corrections.yaml STT 오인식 교정 사전 (선택)
{wiki-vault} My Wiki 개념을 따로 정리하는 두 번째 볼트 이름 (선택)
{author} [[Your Name]] 작성자 노트
  • 사용자가 경로를 알려 주지 않았으면 볼트에서 비슷한 폴더를 찾아 제안하고 확인받는다. 없는 폴더를 마음대로 만들지 않는다.
  • 확정한 값은 볼트의 에이전트 설정 파일(CLAUDE.md, AGENTS.md 등)에 적어 두라고 제안한다. 다음 강의부터 묻지 않는다.

입력

입력 필수 비고
강연 전사본 (STT 텍스트) ✅ 녹음 파일만 있으면 먼저 전사한다
AI 요약 (녹음 앱 요약 등) 선택 있으면 원문 그대로 보존
일정 정보 (캘린더 캡처·텍스트) 선택 행사명·슬롯 시각·소요시간 추출
행사명·주최·청중 정보 선택 없으면 볼트에서 찾아본 뒤 사용자에게 확인

출력 맵 (4층 구조)

{projects}/{강의 프로젝트 폴더}/                      ← ①② 이벤트 기록 (준비 자료와 같은 폴더)
├── (기존 준비 자료 — 손대지 않음)
├── YYYY-MM-DD {행사} - {제목}.lecture.md             ← ① 허브 (type: lecture)
├── YYYY-MM-DD {행사} - 전사본.md                      ← ② 원자료 (type: transcript, 불변)
├── YYYY-MM-DD {행사} - AI 요약.md                     ← ② 원자료 (있을 때만)
└── NN-강의-회고와-개선.md                             ← 회고 (번호는 기존 준비 자료 다음 번호)

{cards}/YYYY-MM-DD {행사}/                            ← ③ 지식 카드 (재사용 라이브러리)
└── {주장형 제목}.md × 8~16장                          ← type: lecture-chunk

{base}                                               ← ④ 조회 (하나만 둔다. type 필터로 자동 등록)

Read the full file on GitHub · 279 lines

Files

What ships with it

5 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. today First seen · 279 lines · 232 tokens per session scan A 2d71fa376a7f

Subscribe to this mod's changes

lecture-asset is a skill published in the GitHub repository johnfkoo951/cmdspace-plugins (7 stars, last pushed today), licensed MIT. It adds 232 tokens to every session and 6,318 once invoked, about $0.0009 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 2026-10-23.

Related

Other skills, from other repositories

gh-discussions

A guide for answering GitHub Discussions, a question-and-answer area separate from issue reports. In its Q&A categories, a maintainer can mark a reply as the accepted answer.

tonydzi/second-brain-starter-kit · 136 tokens

cognitive-compile

Use when source material must be transformed into a compact, evidence-aware model for learning, decisions, or an Obsidian concept note.

Mark393295827/third-brain-v7-skills · 32 tokens

brain-onboard

An onboarding workflow that helps another person create and use their own private knowledge store, sometimes called a second brain. It gathers their information with consent, saves it in their own workspace, and demonstrates a first useful result.

tonydzi/second-brain-starter-kit · 121 tokens

notebooklm

Drive NotebookLM over a programmatic CLI with no browser: turn a vault slice into an audio overview, study guide or mind map, and fold the artifacts back into the vault. Browser automation is the fallback if CLI auth breaks. Triggers: "/notebooklm", "make an audio digest of ", "podcast from the vault".

tonydzi/second-brain-starter-kit · 74 tokens

interview-prep

An interview preparation workflow that researches a company and role, checks them against your CV, and prepares an English introduction, answers, questions, and practical details.

tonydzi/second-brain-starter-kit · 109 tokens

guide

Write an evergreen teaching longform for non-technical readers built from your own real material (systems you run, dated failures, numbers), structured as a stitched lesson that can live as a blog post, a GitHub guide hub and a newsletter issue. Use when turning lived engineering experience into a durable how-to.…

tonydzi/second-brain-starter-kit · 81 tokens