BB prompt-architect
Transform rough ideas into professional-grade LLM prompts. Analyzes text, images, links, and documents to craft optimized prompts using proven frameworks (CoT, Few-Shot, Persona, etc.). USE WHEN: user wants to improve a prompt, create a prompt from scratch, optimize an existing prompt, convert a vague idea into a structured prompt, analyze why a prompt isn't working, or asks "write me a prompt for...", "improve this prompt", "prompt engineer this". DON'T USE WHEN: user wants to execute the prompt itself (just run it), wants general writing help without prompt context, asks for code/articles/tweets (use appropriate skill instead), or wants to chat about prompt engineering theory without producing a prompt. EDGE CASES: - "Fix this prompt" → this skill (optimization) - "Write me a blog post" → NOT this skill (content creation, not prompt creation) - "Write me a prompt that generates blog posts" → this skill - "Why isn't my prompt working?" → this skill (diagnosis + fix) - "اكتب لي برومبت" → this skill - "حسن هالبرومبت" → this skill - "اكتب لي مقال" → NOT this skill (use katib-al-maqalat) INPUTS: Rough idea, existing prompt, images, links, documents, or any combination. OUTPUTS: Optimized prompt in a code block, ready to copy. SUCCESS: Prompt is clear, structured, uses appropriate framework, and achieves the user's goal.
Transform rough ideas into professional-grade LLM prompts.
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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 · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1339 chars, limit 1024
Process rating: all ten parameters 69/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 27 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 890 tokens
- 100Running it twice. No mutating operations
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
- +3Description length 1338: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 10 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.