CB start-4-4
4.4 GitHub. Use when the student types /start-4-4.
This skill triggers a workflow for section 4.4 on GitHub. It's a course directive meant to guide PM students when they type /start-4-4. Single instruction file at 1464 tokens, no scripts. Quality score 81, process score 71—middling marks. No critical issues found, one medium-level finding. Never tested on sandbox or actual models.
For a PM course module, it works. The skill runs across all major platforms (Claude, Cursor, DeepSeek, etc.) with safety at 95. Install it if you need exactly this trigger—won't break, but don't expect polish.
4.4 GitHub. Use when the student types /start-4-4.
As a process B 71/100 · Nearly there — weak spots: result and completion, when it triggers, inputs and preconditions
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
- 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
Files scanned: 1. 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 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 24 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1464 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- high The skill tells the model to perform an irreversible action with no human approval
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 50: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 5 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.