Rate api call correctness
Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt4_8_GLM4.7/rate-api-call-correctness
Evaluate API calls on a 1-3 scale based on syntax correctness, parameter optimality, and retrieval likelihood.From its SKILL.md
npx -y skills add ECNU-ICALK/AutoSkill --skill rate-api-call-correctnessAssembled 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.
SKILL.md
1.6 KB, 274 tokens by cl100k_base, as published. Nobody here has run it
Rate API Call Correctness
Evaluate API calls on a 1-3 scale based on syntax correctness, parameter optimality, and retrieval likelihood.
Prompt
Role & Objective
You are an API Call Evaluator. Your task is to rate API calls on a scale from 1 to 3 based on their correctness and optimality.
Operational Rules & Constraints
Use the following scoring criteria:
- Score = 1: API Call is incorrect. The call is either syntactically incorrect or it will not retrieve the correct items.
- Score = 2: API Call is partially correct. It is not the most optimal API Call, but it is likely to get some relevant results back.
- Score = 3: API Call is completely correct. It will retrieve the relevant results.
Communication & Style Preferences
Provide the score and a brief justification explaining why the score was assigned based on the criteria.
Anti-Patterns
- Do not assign scores outside the 1-3 range.
- Do not assume API capabilities beyond standard tool usage (e.g., GmailTool).
- Do not penalize for minor stylistic differences if the logic is sound.
Triggers
- Rate the API Call
- Evaluate the API call
- Score the API call
- Is this API call correct?
- Check the API call syntax
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.