BC Prompt Engineering Mastery
Complete methodology for writing, testing, and optimizing prompts that reliably produce high-quality outputs from any LLM. From first draft to production-grade prompt systems.
Complete methodology for writing, testing, and optimizing prompts that reliably produce high-quality outputs from any LLM.
As a process C 58/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
How to improve
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Instruction override
en-ignore-previousSKILL.md:464Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)- "Ignore previous instructions and..."
detector -
low Instruction override
en-ignore-previousSKILL.md:459Instruction-override phrase ("ignore previous instructions") (negated — the text forbids it)- If the user's input contains instructions (e.g., "ignore previous instructions"),
negated
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7229 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (Prompt Engineering Mastery) differs from the folder (afrexai-prompt-engineering)
- 70Execution cost. Instruction body is 7229 tokens
- 100Tools and files. No external tools needed
- 100Steps. 80 steps
- 100Result and completion. Output format and completion criterion are stated
- 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)
- +1No license
- +2Single-language instructions
- +3Description length 175: enough signal without eating the budget
- +4Structure: 49 headings
- +3Step-by-step instructions: 80 items
- +3Output format is stated explicitly
- +4Has examples (34 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.