kerplunk-ai-prompts 0.1.7 → 0.1.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 7cb321c8aa762f4ce47ce293762e256112d2d0ac350db7849666be98baf8e742
4
- data.tar.gz: 221eb691f623ae5fd1aeb14fc176d4fc49e9a79eb9266dff037aa7e1e1ccc1d0
3
+ metadata.gz: 5e308279da63b58ef38350a83b737c56c6005f2cac7d4b170f9d4a457ac2377a
4
+ data.tar.gz: 0f6d730df30a88330cd1f90112e9c070d8bb0b30e495a955c081135840784e5e
5
5
  SHA512:
6
- metadata.gz: 063fcf674a13531ee028fc7bcd20d8f479aab291973323c172f7d090c6385604b85eca01030a547ee1162a5694231a029784493688c5091010afce2ddc170540
7
- data.tar.gz: 4d66de228c3d8a3e5b77e73562a7202c4f176a6734c19609832c0aab468f6cfb3150f623a5444d7aaefbc9e7279952fdffa59408e68b84691ab5a68597b4c53e
6
+ metadata.gz: '009b5c9f05782c34407f7f10512e7fcf2e5551586454ed813aeeb45265f9b65e38ba3f1ab129c7a8636d826828f5084f528ee428c994651e3b1caa8b217804da'
7
+ data.tar.gz: e81cf4894706dcfd7c1a7233cf9295992848ec29b26aa0a4095de59614ae4fe787e49270a8a4cebf49b498a6e7411db0ce7172f72f1442c3250f7cc17f2abcdd
@@ -23,7 +23,7 @@ module Kerplunk
23
23
  question_answer_prompts = question_models.collect(&:question_prompt)
24
24
 
25
25
  <<~PROMPT
26
- Respond with a RAW JSON object only. Do not include any explanatory text outside the JSON. The JSON object should have a single key "description" with a value that is a string containing valid HTML for the job description.
26
+ Respond with a RAW JSON object only. Do not include any explanatory text outside the JSON.
27
27
 
28
28
  You are an expert recruiter. You are performing the interview of a candidate to effectively evaluate them for a new role at #{organization_name}.
29
29
 
@@ -18,7 +18,7 @@ module Kerplunk
18
18
  transcript = "<NOTRANSCRIPT />" if transcript.nil? || transcript.empty?
19
19
 
20
20
  <<~PROMPT
21
- Respond with a RAW JSON object only. Do not include any explanatory text outside the JSON. The JSON object should have a single key "description" with a value that is a string containing valid HTML for the job description.
21
+ Respond with a RAW JSON object only. Do not include any explanatory text outside the JSON.
22
22
 
23
23
 
24
24
  You are an expert recruiter. You are performing the interview of a candidate to effectively evaluate them for their #{question_type} skills. Please provide a score from 1 to 100. Please provide three high-level bullet pointed comments about how the candidate did on the question as the `commentary` key.
@@ -19,7 +19,7 @@ module Kerplunk
19
19
  raise ArgumentError, "resume_text is required" if resume_text.nil? || resume_text.empty?
20
20
 
21
21
  <<~PROMPT
22
- Respond with a RAW JSON object only. Do not include any explanatory text outside the JSON. The JSON object should have a single key "description" with a value that is a string containing valid HTML for the job description.
22
+ Respond with a RAW JSON object only. Do not include any explanatory text outside the JSON.
23
23
 
24
24
  You are an expert recruiter. You are performing the interview of a candidate to effectively evaluate them for a new role at #{organization_name}. Please analyze the resume added after `====`. Please provide a score from 1 to 100.
25
25
 
@@ -68,6 +68,9 @@ module Kerplunk
68
68
  This is the score of the candidate's technical skills. This should be based on the candidate's technical knowledge and how well they fit the job description.
69
69
 
70
70
  An example output should be JSON and look like the below. Please be sure the output is a valid JSON format even if you cannot generate the interview questions. The JSON should not include any markdown or newline characters such as "```json" that would normally be used for rendering in markdown.
71
+
72
+ Please do NOT include any explanatory text outside the JSON. The data returned should be a valid JSON format. Please double check the output is valid json with no explanatory text.
73
+
71
74
  === JSON Output
72
75
  {
73
76
  "scores": {
@@ -12,7 +12,7 @@ module Kerplunk
12
12
  raise ArgumentError, "description is required" if description.nil? || description.empty?
13
13
 
14
14
  <<~PROMPT
15
- Respond with a RAW JSON object only. Do not include any explanatory text outside the JSON. The JSON object should have a single key "description" with a value that is a string containing valid HTML for the job description.
15
+ Respond with a RAW JSON object only. Do not include any explanatory text outside the JSON.
16
16
 
17
17
  You are an expert recruiter. You are performing the interview of a candidate to effectively evaluate them on all fronts: personal skills, technical skills, job-specific skills, soft-skills, and the “x-factor”. The interview should start off with a few questions about the candidate, then go to exactly 5 questions regarding the job posting listed below after ###, and then finally please ask a few questions to help assess personality and cultural fit (you can be creative here). These questions should aim to be simple, effective, empathetic, non-biased, and descriptive enough to be used in further prompts when analyzing the results of the interview.
18
18
 
@@ -3,7 +3,7 @@
3
3
  module Kerplunk
4
4
  module AI
5
5
  module Prompts
6
- VERSION = "0.1.7"
6
+ VERSION = "0.1.9"
7
7
  end
8
8
  end
9
9
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: kerplunk-ai-prompts
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.7
4
+ version: 0.1.9
5
5
  platform: ruby
6
6
  authors:
7
7
  - Kyle Schutt
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2024-06-24 00:00:00.000000000 Z
11
+ date: 2024-06-28 00:00:00.000000000 Z
12
12
  dependencies: []
13
13
  description: A collection of AI prompt templates for use in Kerplunk
14
14
  email: