Prompt Optimizer

Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee...

Security Scan

The skill is internally coherent and implements a local Node.js prompt-optimization tool using the included technique catalog; no credentials or network access are requested, though there are small packaging/metadata and implementation robustness issues you should review before installing.

Purpose & Capability

The skill's name, description, and files align: it provides 58 prompting techniques and code to list/get/apply them. Minor inconsistencies: SKILL.md and usage expect running with node, but the registry metadata lists no required binary; _meta.json ownerId differs from the registry Owner ID in the provided metadata (packaging mismatch). These are not direct security issues but are unexpected and worth verifying.

Instruction Scope

Runtime instructions and code operate on local files included in the package (references/*.md) and print optimized prompts to stdout. There are no instructions to read unrelated system paths, access external endpoints, or exfiltrate data. The only child_process usage is in scripts/test.js for local tests.

Install Mechanism

No install spec is provided (instruction-only style), and all files are included in the package. Nothing downloads external code or extracts archives. This is low-risk from an install perspective.

Credentials

The skill requests no environment variables, credentials, or config paths — consistent with its local text-processing purpose.

Persistence & Privilege

always:false and no special persistence or system-wide configuration changes are requested. The skill does not attempt to modify other skills or agent-wide settings.

Assessment

What to check before installing/using: - Verify Node.js availability: SKILL.md and the code expect node to run index.js, but the package metadata does not declare Node as a required binary. Ensure your environment provides Node or the skill will fail. - Confirm publisher/trust: _meta.json.ownerId differs from the registry owner ID shown in the submission metadata — this could be a benign packaging oversight, but verify you trust the author before installing. - Review included reference files offline: the two large reference markdowns are the data source for the tool; scan them for any unexpected content before use. - Run tests in a sandbox: scripts/test.js uses child_process.execSync to run node commands; run tests in an isolated environment if you want to be extra cautious. - Be aware of functional limits: the index.js parser uses a simple regex to extract technique templates and a basic placeholder replacement; it may miss or mis-handle some templates (functionality, not safety). If you rely on precise outputs, inspect the resulting templates and test with representative prompts. Overall: no red flags for credential exfiltration or network behavior. The main issues are packaging/metadata mismatches and some implementation robustness you may want to validate.

A Node.js implementation of 58 proven prompting techniques cataloged in references/prompt-techniques.md.

Usage

1. List Available Techniques

See all 58 techniques with their IDs and descriptions.

node skills/prompt-optimizer/index.js list

2. Get Technique Details

View the template and purpose of a specific technique.

node skills/prompt-optimizer/index.js get <technique_name>

Example: node skills/prompt-optimizer/index.js get "Chain of Thought"

3. Optimize a Prompt

Apply a specific technique's template to your prompt.

node skills/prompt-optimizer/index.js optimize "<your_prompt>" --technique "<technique_name>"

Example:

node skills/prompt-optimizer/index.js optimize "Write a python script to reverse a string" --technique "Chain of Thought"

References

• references/prompt-techniques.md: Full catalog of techniques.
• references/quality-framework.md: Framework for evaluating prompt quality manually.