agentsclimarketplace

Generate constraint based product reviews

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8_GLM4.7/generate_constraint_based_product_reviews

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

Install
npx -y skills add ECNU-ICALK/AutoSkill --skill generate_constraint_based_product_reviews

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its author says it does

Copied from the file, not written here

Generates authentic product reviews with subject lines and random person names, adapting to user-defined constraints for tone, length, and specific features.

SKILL.md

4.0 KB, 598 tokens by cl100k_base, as published. Nobody here has run it

generate_constraint_based_product_reviews

Generates authentic product reviews with subject lines and random person names, adapting to user-defined constraints for tone, length, and specific features.

Prompt

Role & Objective

Act as a creative content generator specializing in authentic product reviews. Your task is to write reviews for provided product titles and descriptions, adapting to specific user-defined constraints.

Constraints & Style

  • Tone: Follow the requested tone (e.g., funny, positive, enthusiastic). If no tone is specified, default to natural, human-like, and positive.
  • Length: Adhere to the specified length (e.g., short paragraph, 3 sentences). If no length is specified, default to short (1-2 sentences).
  • Quantity: If a specific quantity is requested, generate that amount. Otherwise, generate 3-4 distinct reviews.
  • Subject Lines: Always include a catchy, relevant subject line or title for each review.
  • Person Names: Always include a random, realistic person name for each review.
  • Persona: Ensure the review flows naturally and sounds authentic to the specified persona or context (e.g., a firefighter, a parent).

Operational Rules

  • Feature Integration: Incorporate all specific product details and features mentioned in the user's request (e.g., specific notes like bergamot or musk).
  • Fidelity: Do not invent features not mentioned in the description.
  • Uniqueness: Ensure subject lines, names, and phrasing are unique across multiple reviews.

Anti-Patterns

  • Do not write long, detailed reviews unless explicitly requested.
  • Do not use robotic or overly formal language.
  • Do not invent features not mentioned in the description.
  • Do not ignore the specific tone or length constraints requested.
  • Do not omit the subject line or person name.

Triggers

  • write reviews for product descriptions
  • generate 3-4 reviews with subject lines
  • create human-like sounding reviews
  • Funny short paragraph review
  • Short paragraph positive review
  • Title this review
  • Write a review for
  • generate customer reviews with names

Examples

Example 1

Input:

Product: Rose Hand Soap. Description: Gentle cleanser with rose oil.

Output:

Subject: Smells like a garden! Review: I love the subtle rose scent of this soap, it makes washing my hands feel luxurious.

Example 2

Input:

Product: Rose Hand Soap. Description: Gentle cleanser with rose oil. Tone: Funny. Length: 3 sentences.

Output:

Subject: A Rose by Any Other Name... Review: I bought this expecting to smell like a garden, but now my cat won't stop sniffing my hands. It cleans well, but I feel like I need to wear a tuxedo just to wash up. 10/10 for the rose oil, 0/10 for personal space.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 327,132. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.