DC start-2-1
Module 2.1: Write a PRD. Guides the student through templates, Socratic questioning, multiple PRD drafts, and review.
The skill promises to walk students through PRD templates, Socratic questioning, and multiple draft iterations. Twelve files on board, but quality score dropped to 52—not a typo. The audit found concealed code, which is a red flag. Safety sits at 82, but process score limps at 64, and you'll feel it. The skill generates templates for learning, but does it in a way that makes instructions tedious to parse. Skip it—there are clearer materials covering the same ground.
Module 2.1: Write a PRD. Guides the student through templates, Socratic questioning, multiple PRD drafts, and review.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
high Concealment
en-hide-from-userSKILL.md:9Instruction to hide actions from the userAt the start of this lesson, silently copy the bundled lesson assets into the workspace if they are not already present. Do not show command output to the student.
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 8086 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 8086 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 101 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
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 117: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -220 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 101 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.