BC git-worktree-decision
Decide whether a piece of work deserves its own git worktree, before creating one. Use when about to start work that would disturb a dirty or warm working tree, when an urgent fix interrupts work in progress, when launching concurrent/parallel agent sessions on one repo, when tempted to `git stash` or `git switch` to make room, or when worktrees have accumulated and you need to know which should never have existed. Covers the concurrency test, the shared-external-state blocker that makes worktrees backfire, and the teardown commitment. Not a worktree how-to: mechanics, per-worktree ports, and dependency symlinking are out of scope.
Decide whether a piece of work deserves its own git worktree, before creating one.
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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
- warning
description-long-hermesdescription is 639 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 9 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Consistency. The Hermes dialect needs category and tags
- 100Tools and files. No external tools needed
- 100Steps. 13 steps
- 100Execution cost. Instruction body is 1772 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 639: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.