brycewang-stanford/Auto-Empirical-Research-Skills / skills/33-Galaxy-Dawn-claude-scholar/skills/obsidian-link-graph
obsidian-link-graph
VerifiedUse this skill when the user wants to repair or strengthen Obsidian wikilinks among existing canonical project notes, especially across papers, knowledge notes, experiments, results, and writing.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.4 KB |
SKILL.md
View on GitHub---
name: obsidian-link-graph
description: Use this skill when the user wants to repair or strengthen Obsidian wikilinks among existing canonical project notes, especially across papers, knowledge notes, experiments, results, and writing.
---
# Obsidian Link Graph
This is a **legacy compatibility helper**.
Despite the name, the current default workflow is **not** graph-heavy. Use this skill to repair navigation among existing canonical notes, not to generate graph artifacts by default.
## Responsibilities
- strengthen wikilinks among `00-Hub.md`, `01-Plan.md`, `Knowledge/`, `Papers/`, `Experiments/`, `Results/`, `Writing/`, and `Daily/`
- improve backlinks where a durable relationship is already clear
- help route a new reference to the best existing canonical note
- reduce disconnected durable notes without creating concept or dataset sprawl
## Link heuristics
- Prefer one canonical note per durable object.
- Link through stable project objects, not ad-hoc phrases.
- Avoid overlinking every paragraph; keep only meaningful edges.
- Prefer repairing existing links over creating new auxiliary notes.
- If the best target is unclear, narrow the search first and use `find-canonical-note` from `obsidian-project-memory` when helpful.
## Do not assume by default
- `Concepts/`
- `Datasets/`
- `Maps/`
- `Views/`
- `.canvas`
- `.base`
Create those only if the user explicitly asks for them.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |