CD start-gsd-3
Learn GSD lesson 3 through its file-backed planning and build workflow. Use when the student types /start-gsd-3.
The skill promises to deliver GSD lesson 3 through file-backed planning and build workflow. Description is sparse, but files are present. Checks found broken references—the skill points to files that don't exist in the folder. This means students will hit errors instead of a complete lesson. Safety score is solid, quality score is middling, and process score sits at 49—something's off with execution logic. One medium-level finding flags a nuisance rather than a blocker.
Skip it until the author fixes the broken links. Right now it's educational material with holes in the foundation.
Learn GSD lesson 3 through its file-backed planning and build workflow.
As a process D 49/100 · Unfinished process — References files that are not bundled: expense-splitter/
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Write Bash AskUserQuestion Skill
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: expense-splitter/
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: expense-splitter/
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 85Steps. 22 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1445 tokens
- 100Running it twice. Mutating operations check current state
- low 12 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)
- +3Description length 112: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 13 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.