agentleFS
Sign inStart free
tboome33tboome33/obsidian-mcp-router/skills/template-execute/SKILL.md

template-execute

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Execute a Templater template, optionally writing the rendered output to a new file. Arguments are exposed to the template via tp.mcpTools.prompt("key") (directly under tp, NOT under tp.user — easy footgun).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call the obsidian-router execute_template MCP tool with arguments parsed from $ARGUMENTS.

    line 16
  2. Distinctive:

    When writing a template that will be invoked via this skill, prompt arguments like:

    line 43
  3. Very specific:

    If createFile was true: report the rendered content and confirm the file was written at targetPath.

    line 57
  4. Very specific:

    If createFile was false: just show the rendered content (preview mode).

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

template-execute

Call the obsidian-router execute_template MCP tool with arguments parsed from $ARGUMENTS.

Arguments

Required:

  • name — path to the template file in the vault (e.g. Templates/Daily.md).

Optional:

  • vault — omit for default.
  • arguments — key/value object exposed inside the template via tp.mcpTools.prompt("key"). Note: directly under tp, NOT under tp.user.
  • createFile — if true, save the rendered output to targetPath.
  • targetPath — path where to save (required when createFile: true).

Argument parsing from $ARGUMENTS

  • bare path → name only, no createFile (preview mode)
  • name=X arguments={"k":"v"} createFile=true targetPath=Y
  • conversational: "execute Templates/Trade.md with ticker AAPL and create file Trades/AAPL.md" → infer the structure

Pre-requisites

The target vault must have the templater-obsidian plugin enabled. If the tool returns 503 with "Templater plugin is not available", surface that clearly.

Footgun — tp.mcpTools is NOT under tp.user

The obsidian-mcp-router-bridge plugin (which exposes /templates/execute) monkey-patches Templater so tp.mcpTools.prompt("key") returns whatever you put in the arguments map. This is directly under tp, not under tp.user (which is the convention for Templater user scripts) — easy footgun.

When writing a template that will be invoked via this skill, prompt arguments like:

<% tp.mcpTools.prompt("ticker") %>

NOT:

<% tp.user.mcpTools.prompt("ticker") %>   <!-- WRONG — returns undefined -->

After execution

  • If createFile was true: report the rendered content and confirm the file was written at targetPath.
  • If createFile was false: just show the rendered content (preview mode).

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free