prompt-improver
Prompt Improver refines code-related prompts by evaluating task clarity, investigation depth, verification steps, and scope control. It applies transformation rules to strengthen prompts for implementation, debugging, refactoring, code review, and testing tasks. The skill ensures prompts follow investigation-first principles and include appropriate verification checks before execution.
Prompt Improver optimizes code-related prompts by applying investigation-first thinking and verification best practices.
AI-generated summary based on this skill's SKILL.md
Install
existential-birds/beagle/prompt-improver · repository language: TypeScript
git clone https://github.com/existential-birds/beagle
cp -r beagle/plugins/beagle-core/skills/prompt-improver ~/.claude/skills/prompt-improverFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I improve prompts for testing with prompt-improver?
Prompt Improver refines testing prompts by evaluating task clarity, investigation depth, and verification steps. It applies transformation rules to strengthen your prompts, ensuring they follow investigation-first principles and include appropriate verification checks before execution. This approach helps AI systems understand test requirements more precisely and catch edge cases earlier.
What makes prompt-improver optimize prompts for coding tasks?
Prompt Improver optimizes coding prompts through systematic evaluation of task clarity, scope control, and investigation depth. It transforms prompts to strengthen implementation, debugging, refactoring, and code review tasks by adding verification steps and ensuring investigation-first principles are applied. The skill helps developers write clearer, more actionable prompts that yield better AI-assisted results.
Can prompt-improver enhance prompts for code review?
Yes. Prompt Improver enhances code review prompts by refining task clarity, adding verification steps, and controlling scope. It applies transformation rules that strengthen prompts for review tasks, ensuring they follow investigation-first principles. This helps reviewers ask AI systems more specific questions about code quality, maintainability, and potential issues.
What prompt engineering best practices does prompt-improver teach?
Prompt Improver teaches investigation-first principles, scope control, and verification-step inclusion for software development. It demonstrates how to evaluate task clarity and depth before execution, apply transformation rules to strengthen prompts, and structure prompts for debugging, refactoring, testing, and implementation tasks. These practices help developers write more effective AI prompts consistently.
How does prompt-improver add verification to existing code prompts?
Prompt Improver adds verification and scope control to existing prompts by evaluating current task clarity and investigation depth, then applying targeted transformation rules. It strengthens prompts by inserting verification checks before execution and clarifying scope boundaries. This ensures AI systems validate assumptions and stay focused on the intended task.
What is prompt-improver licensed under?
Prompt Improver is licensed under Apache-2.0, allowing free use, modification, and distribution with proper attribution. This open license supports collaborative development and integration into other software development tools and workflows.
SKILL.md
rendered from the published skill — quoted content, verbatim
Prompt Improver
Optimize code-related prompts for clarity, investigation-first thinking, and verification.
Input
$ARGUMENTS
Step 1: Analyze the Prompt
Evaluate the input prompt across these dimensions:
| Dimension | What to check |
|---|---|
| Task Clarity | Is the task type clear? (implement, fix, refactor, review, test) Are boundaries defined? |
| Investigation | Does it specify reading/understanding before acting? |
| Verification | Are there appropriate checks? (run tests, build, lint) |
| Context Anchoring | Does it reference specific files, functions, or patterns? |
| Action Specificity | Is the desired outcome explicit? Quality expectations stated? |
| Scope Control | Is it appropriately scoped? Clear stopping points? |
Identify which dimensions are weak or missing in the input prompt.
Gates (sequenced)
Complete in order; do not skip steps.
- **Audit gate (end of Step
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 1 file
plugins/beagle-core/skills/prompt-improver/SKILL.md