BC prompt-engineer
A comprehensive prompt engineering skill for AI developers building LLM-powered applications. Covers system prompt design, few-shot prompting, chain-of-thought reasoning, tool-use patterns, structured output enforcement, context management, prompt templates, evaluation frameworks, multi-turn conversation handling, multimodal prompting, agent patterns such as ReAct and plan-and-execute, and safety guardrails including prompt injection defence.
As a process C 61/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
How to improve
- 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
-
low Exfiltration
read-dotenvscripts/scaffold.sh:120Reads a .env file (quoted — discussed, not commanded)echo " cp .env.example .env # Add your API key"
quoted
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10285 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 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
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (prompt-engineer) differs from the folder (ai-prompt-engineer)
- 40Execution cost. Instruction body is 10285 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 45 steps
- 100Failures and branches. 3 branches, has a failure section
- low 16 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
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)
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 446: enough signal without eating the budget
- +4Structure: 73 headings
- +3Step-by-step instructions: 45 items
- +3Output format is stated explicitly
- +4Has examples (59 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.