workspace-mode
Skill166 starsChanged 5 months agoMITView on GitHub
Switch between named Obsidian Workspace layouts (interview / scrum / 1-on-1 / recap) for context-appropriate file/pane layouts. Wraps `obsidian workspace`.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/qmd-search.mdcCursor rule
- .cursor/rules/skill-conventions.mdcCursor rule
- .cursor/rules/skill-registry.mdcCursor rule
- cache-notesSkill
- commitSkill
- defuddleSkill
- fill-participantsSkill
- followup-todosSkill
- json-canvasSkill
- last-1on1Skill
- mail-transcriptsSkill
- meetingSkill
- migrate-tagsSkill
- note-statusSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-markdownSkill
- onboard-personSkill
- organize-meetingsSkill
- otter-fetchSkill
- people-stubsSkill
- qmdSkill
- recapSkill
- sprint-retroSkill
- sync-upstream-obsidianosSkill
- vault-healthSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
No args → run obsidian workspace format=json and present the list with the current one starred.
- Very specific: line 52
Read-only by default — only save writes (and that's to .obsidian/workspaces.json, not vault content).
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Workspace Mode
Usage
/workspace-mode— List available workspaces and the current one./workspace-mode <name>— Switch to a named workspace./workspace-mode save <name>— Save current pane layout as a new workspace (delegates to Obsidian's Workspace plugin command).
Why this skill exists
Different work modes want different layouts:
- interview: Meetings.base Interviews view + the active candidate's @Name.md + a blank scratchpad pane.
- scrum: Today's
Meetings/Engineering/Scrum/YYYY-MM-DD.md+ Tracker.md + Meetings.base Pending view. - 1-on-1: OneOnOnes view + the current person's @Name.md + their last 1:1 note.
- recap: Recaps/ folder + Meetings.base ThisWeek view + Tracker.md.
Switching by hand means dragging panes around. This skill flips between saved layouts in one command.
Workflow
Step 1: List or switch
- No args → run
obsidian workspace format=jsonand present the list with the current one starred. <name>arg → runobsidian workspace load name=<name>(or use the Obsidian "Workspaces: Load workspace" command ifloadisn't a direct subcommand:obsidian command name="Workspaces: Load workspace layout").
Step 2: Save
save <name>→ runobsidian command name="Workspaces: Save layout"then prompt for the name in Obsidian's modal. (Or useobsidian evalto call the plugin API directly if needed.)
Suggested workspace presets
These don't exist out of the box — the user creates them once in Obsidian via Workspaces plugin, then this skill flips between them:
| Workspace | Files / Views Open |
interview | Meetings.base (Interviews view), latest interview note, blank scratchpad |
scrum | Today's Scrum daily, Tracker.md, Meetings.base (Pending view) |
1-on-1 | Meetings.base (OneOnOnes view), People.base (Active view) |
recap | Recaps/Recap YYYY-MM-DD.md, Meetings.base (ThisWeek view), Tracker.md |
default | The main layout (current) |
Important Notes
- Workspaces are stored in Obsidian's
.obsidian/workspaces.json— they're per-vault, not per-device. - Requires the Workspaces core plugin enabled in Obsidian.
- Read-only by default — only
savewrites (and that's to.obsidian/workspaces.json, not vault content). No commit step.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

