Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
SkillScore73Maintained
Automatic
◆AI Engineer pack
Last verified 8/16/2026
What it changes
Passed 15 of 21 test cases with the skill, and 9 of 21 without it.
Without skill41%
With skill73%
Checks it passed that the model alone missed
The response lists Add Verification as the highest-priority principle.
The corrected version adds explicit verification steps to confirm the fix.
The transformed prompt requires running API test suites after implementation.
and 13 more in the full report
10 fixed6 passed either way3 still failing3 broke
Pass-rate lift
+32 pp
Tokens
+226%
Agent turns
0%
Response time
-16%
Model gemini-3.6-flashMeasured 8/16/2026v116 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
I selected 'Transform directly' for this prompt: 'fix it'. Since this prompt is extremely brief and lacks context, apply the standard fallback procedure.
What was checked, without and with the skill
Checked
Without skill
With skill
The response asks a single clarifying question regarding what details are needed for success.
Missed
Passed
The response avoids interrogating the user with multiple detailed questions.
Passed
Passed
case-15 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md493 lines6 files
Best Practices — Prompt Transformer
Transform prompts by adding what Claude needs to succeed.
Start Here
Based on user's request:
User provides a prompt to transform:
→ Ask using AskUserQuestion:
Question: "How should I improve this prompt?"
Header: "Mode"
Options:
Transform directly — "I'll apply best practices and output an improved version"
Build context first — "I'll gather codebase context and intent analysis first"
User asks to learn/understand:
→ Show the 5 Transformation Principles section
User asks for examples:
→ Link to references/before-after-examples.md
User asks to evaluate a prompt:
→ Use the Success Criteria eval rubric at the end of this document
If "Transform directly"
Apply the 5 principles below and output the improved prompt immediately.
If "Build context first"
Launch 3 parallel agents to gather context:
Run these agents IN PARALLEL using the Task tool:
- Task task-intent-analyzer("[user's prompt]")
- Task best-practices-referencer("[user's prompt]")
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful `whyHere` notes, and create a starter pack once the first pass is solid.