원클릭으로 Manus에서 모든 스킬 실행

sprang-knowledge

스타1

포크1

업데이트2026년 6월 4일 08:48

Build an interactive knowledge graph from a folder of markdown notes — Obsidian, Logseq, Dendron, Foam, Zettelkasten, or plain markdown. Use when the user says "/sprang-knowledge", "index my notes", "build graph from notes", or "analyze my Obsidian vault".

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

FavioVazquez

FavioVazquez/sprang

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

관련 직업SOC

SOC 직업 분류 기준

소프트웨어 개발자컴퓨터 및 수학직·SOC 15-1252

SKILL.md

readonly

name	sprang-knowledge
description	Build an interactive knowledge graph from a folder of markdown notes — Obsidian, Logseq, Dendron, Foam, Zettelkasten, or plain markdown. Use when the user says "/sprang-knowledge", "index my notes", "build graph from notes", or "analyze my Obsidian vault".

Build an interactive knowledge graph from a folder of markdown notes — Obsidian, Logseq, Dendron, Foam, Zettelkasten, or plain markdown.

Analyze markdown notes and produce .sprang/knowledge-graph.json with typed nodes (article/entity/topic/claim/source), wikilink edges, topic clusters, and a guided reading tour.

Quick phases:

Pre-flight — resolve notes root, detect format (Obsidian/Logseq/Dendron/Foam/Zettelkasten/plain), check .sprangignore
Scan notes — find all .md files, extract titles/wikilinks/tags/frontmatter, build wikilink resolution map
Analyze notes — read each note in batches of 15, classify type (article/entity/topic/claim/source), write 2-3 sentence summaries, infer edge types from context
Cluster + layer — group notes into 3-10 topic clusters by tag density and wikilink patterns
Assemble + save — write knowledge-graph.json with "kind": "knowledge" + SPRANG_REPORT.md

After completion: dashboard auto-switches to knowledge view mode with KnowledgeInfo sidebar and ReadingPanel.

$ARGUMENTS

이 저장소의 다른 Skills

같은 저장소

sprang-analyze

FavioVazquez/sprang

Analyze a codebase to produce a rich semantic knowledge graph — file summaries, architecture layers, guided tour, domain map, risk scores. Use when the user says "/sprang-analyze", "analyze the codebase", "full analysis", or "run sprang-analyze".

Build or refresh the Sprang knowledge graph for this workspace. Use when the user says "/sprang", "build the knowledge graph", "scan the codebase", "index this project", or "run sprang".

2026-06-171

sprang

FavioVazquez/sprang

Build or refresh the Sprang knowledge graph for this workspace. Use when the user says "/sprang", "build the knowledge graph", "scan the codebase", "index this project", or "run sprang".

2026-06-171

sprang-onboard

FavioVazquez/sprang

Guided architecture tour for new team members — adapts to junior, senior, or PM persona. Use when the user says "/sprang-onboard", "onboard me", "give me a tour", "I'm new to this codebase", or "walk me through the architecture".

2026-06-081

sprang-team

FavioVazquez/sprang

Browse and write team annotations attached to graph nodes — institutional knowledge, decision history, ownership. Use when the user says "/sprang-team", "add annotation", "team knowledge", "who owns this", or "document this decision".

2026-06-081

name	sprang-knowledge
description	Build an interactive knowledge graph from a folder of markdown notes — Obsidian, Logseq, Dendron, Foam, Zettelkasten, or plain markdown. Use when the user says "/sprang-knowledge", "index my notes", "build graph from notes", or "analyze my Obsidian vault".

Build an interactive knowledge graph from a folder of markdown notes — Obsidian, Logseq, Dendron, Foam, Zettelkasten, or plain markdown.

Analyze markdown notes and produce .sprang/knowledge-graph.json with typed nodes (article/entity/topic/claim/source), wikilink edges, topic clusters, and a guided reading tour.

Quick phases:

Pre-flight — resolve notes root, detect format (Obsidian/Logseq/Dendron/Foam/Zettelkasten/plain), check .sprangignore
Scan notes — find all .md files, extract titles/wikilinks/tags/frontmatter, build wikilink resolution map
Analyze notes — read each note in batches of 15, classify type (article/entity/topic/claim/source), write 2-3 sentence summaries, infer edge types from context
Cluster + layer — group notes into 3-10 topic clusters by tag density and wikilink patterns
Assemble + save — write knowledge-graph.json with "kind": "knowledge" + SPRANG_REPORT.md

After completion: dashboard auto-switches to knowledge view mode with KnowledgeInfo sidebar and ReadingPanel.

$ARGUMENTS