AC obsidian-remote
Full remote control of a running Obsidian desktop app via the built-in obsidian CLI. Use INSTEAD of the older obsidian-cli skill packaged with OpenClaw — this skill covers the real, feature-complete CLI that ships with Obsidian itself. Handles reading/writing/searching notes, daily notes, tasks, properties/frontmatter, tags, backlinks, templates, plugins, sync, publish, bookmarks, bases, themes, CSS snippets, file history, and dev tools (CDP, DOM, eval JS, screenshots). Triggers on obsidian, vault, daily note, obsidian tasks, obsidian search, obsidian properties, obsidian plugins, obsidian sync, obsidian publish, obsidian bookmarks, obsidian bases, obsidian templates, obsidian tags. Requires Obsidian desktop app running. NOT the same as obsidian-cli (URI-based tool).
As a process C 57/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2705 tokens
- low 23 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 777: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (20 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.