Obsidian task board
Skill x2724009/evidence-first-durable-task-orchestrator/skills/obsidian-task-board
A Design Gate for complex AI agent work: design first, execute second, preserve evidence always.
npx -y skills add x2724009/evidence-first-durable-task-orchestrator --skill obsidian-task-boardAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Optionally organize Markdown task records created by evidence-first-durable-task-orchestrator inside an explicitly configured Obsidian vault. Use only when the user wants Obsidian-based task browsing, Dashboard indexing, or vault integration. Do not require Obsidian for the core workflow and never infer a vault path.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.9 KB, 311 tokens by cl100k_base, as published. Nobody here has run it
Obsidian Task Board Adapter
This optional adapter stores the core Skill's Markdown records in a user-selected folder inside an Obsidian vault. It adds organization, not a new execution workflow.
Required user input
Before writing, obtain an explicit task_root path. Confirm the path is inside the user's chosen
vault and writable. Never scan for, guess, or expose vault locations.
Behavior
- Keep the core layout:
Active/,Blocked/,Archive/<year>/, and optionalDashboard.md. - Preserve YAML frontmatter so Obsidian properties and optional Dataview queries can read it.
- If Obsidian is installed, the user may open the folder as a vault; the agent does not need to launch Obsidian to write Markdown.
- If Dataview is absent, maintain a compact manual table in
Dashboard.mdonly when the user requests a dashboard. - Do not install Obsidian, community plugins, or enable sync/publish services without explicit approval.
Optional Dashboard query
When the user already has Dataview installed and asks for an automatic view, use this query:
TABLE WITHOUT ID file.link AS "Task", status AS "Status", current_milestone AS "Milestone", updated AS "Updated"
FROM "Agent-Tasks/Active" OR "Agent-Tasks/Blocked"
SORT updated DESC
If the plugin is unavailable, leave the records fully usable as plain Markdown.
Gives 0 of the 12 instructions most note taking skills give in 311 tokens
Counted across 686 of the 876 authors here whose files we hold, read 2026-08-07
- include a visual element on every slidein 44 of 686, across 13 files
- use wikilinks for internal vault linksin 36 of 686, across 12 files
- commit to a single visual motif across every slidein 34 of 686, across 9 files
- use subagents to visually inspect rendered slidesin 31 of 686, across 7 files
- read pptxgenjs guide before creating presentations from scratchin 30 of 686, across 6 files
- keep 0.5 inch minimum marginsin 30 of 686, across 7 files
- re-verify affected slides after every fixin 27 of 686, across 5 files
- run content QA checks before declaring successin 26 of 686, across 3 files
- Use Markdown links for external URLs onlyin 26 of 686, across 11 files
- pick a bold topic specific color palettein 24 of 686, across 2 files
- read editing guide before editing existing presentationsin 23 of 686, across 1 file
- use one dominant color across all slidesin 23 of 686, across 1 file
Said here and by no other author read
- obtain an explicit task_root path
- confirm the path is writable
- keep the core folder layout
- maintain a manual dashboard table on request
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.