chore: import upstream snapshot with attribution
CodeQL / Analyze (csharp) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 13:21:23 +08:00
commit b957a53def
5423 changed files with 863745 additions and 0 deletions
@@ -0,0 +1,13 @@
{
"schema": 1,
"description": "Turn natural language into code",
"execution_settings": {
"default": {
"max_tokens": 256,
"temperature": 0.0,
"top_p": 0.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0
}
}
}
@@ -0,0 +1,2 @@
Explain what you would like to happen in natural language. This will generate the corresponding code. It helps to provide a programming language.
Description: {{$input}}
@@ -0,0 +1,17 @@
{
"schema": 1,
"description": "Turns natural language into Python code like a Python Copilot.",
"execution_settings": {
"default": {
"max_tokens": 256,
"temperature": 0.0,
"top_p": 0.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"stop_sequences": [
"[done]",
"# Done"
]
}
}
}
@@ -0,0 +1,10 @@
WRITE PYTHON CODE TO SOLVE GIVEN PROBLEM. WRITE A SINGLE FUNCTION. ANY EXPLANATIONS MUST BE A COMMENT. USE CLASSES AND TYPINGS WHERE APPROPRIATE. Emit [done] when done.
# Start
# Function to print all strings in a list
def appendprefix(values):
foreach(val in values):
print(val)
# Done
#{{$input}}
@@ -0,0 +1,16 @@
{
"schema": 1,
"description": "Turns natural language into Python command line scripts. Reads variables from args, operates on stdin, out",
"execution_settings": {
"default": {
"max_tokens": 256,
"temperature": 0.0,
"top_p": 0.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"stop_sequences": [
"# Done"
]
}
}
}
@@ -0,0 +1,22 @@
WRITE PYTHON 3.x command line scripts. WRITE A SINGLE FUNCTION.
USE sys.argv, sys.stdin.
HANDLE ERRORS. EXPLANATIONS MUST BE A COMMENT.
# Start
# command line script. Read filename from args, open file, copy stdin to file
import sys
if (len(sys.argv) != 2:
print("not_handled")
sys.exit()
filename = sys.argv[1]
file = open(filename, 'w')
file.write(sys.stdin.read())
file.close()
# Done
# Start
#{{$input}}
# Read input sfrom stdin. print all output
@@ -0,0 +1,18 @@
{
"schema": 1,
"description": "Turns your intent into a SAFE DOS batch script",
"execution_settings": {
"default": {
"max_tokens": 1000,
"temperature": 0.0,
"top_p": 0.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"stop_sequences": [
"exit /b %ERRORLEVEL%",
"exit /b 1",
"exit /b 0"
]
}
}
}
@@ -0,0 +1,19 @@
[BANNED COMMANDS]
FORMAT
DISKPART
PARTITION
CREATE PARTITION
FSUTIL
[END]
WRITE A DOS SCRIPT. End each script with an exit /b %ERRORLEVEL%
NEVER USE BANNED COMMANDS. BANNED COMMANDS DO DAMAGE. YOU NEVER WANT TO DO DAMAGE.
INSTEAD ECHO "SORRY {{$firstName}}, I CAN'T DO THAT. "
List all pdf files in current folder
dir *.pdf
exit /b %ERRORLEVEL%
{{$input}}
@@ -0,0 +1,16 @@
{
"schema": 1,
"description": "Search the Microsoft Graph for Email",
"execution_settings": {
"default": {
"max_tokens": 256,
"temperature": 0.0,
"top_p": 0.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"stop_sequences": [
"[done]"
]
}
}
}
@@ -0,0 +1,32 @@
SEARCH FOR EMAILS using Microsoft Graph using CONTEXT, and Query criteria below.
Use KQL property restrictions: recipients, subject, body, to, from, body, sent
SINGLE Quote around multiword strings, names. Don't include $search.
ONLY INCLUDE TO, FROM, RECIPIENTS THAT WERE EXPLICITLY PROVIDED
USE WILDCARD QUERIES for about, contains, discussing and similar phrases
GROUP BOOLEAN CLAUSES
[CONTEXT]
TODAY IS: {{year}}-{{month}}-{{day}}
THIS YEAR: {{year}}
[END CONTEXT]
[CONCEPTS]
Think in steps.
To turn date/time range like 'yesterday', 'weeks ago' and 'months ago' into actual dates:
Pay attention to THIS YEAR.
1. totalDaysOffset = number of days from range
2. NewDate = TODAY from CONTEXT - totalDaysOffset.
[END CONCEPTS]
USE [CONCEPTS] TO LEARN
BECAUSE YOU ARE WORKING WITH CLASSIC TEXT SEARCH ENGINE, ADD SYNONYMS, EXPAND OR USE ACRONYMS, OR ALTERNATIVE FORMS A PHRASE TO IMPROVE QUERY QUALITY
NEVER SHOW YOUR REASONING
Query criteria:
Email from toby mcduff about LLMs
from:'toby mduff' AND (subject:'LLM*' or subject:'Large Language Models*' OR body:'LLM*' OR body:'Large Language Models*')
[done]
Query criteria:
{{$input}}
@@ -0,0 +1,16 @@
{
"schema": 1,
"description": "Given text, annotate all recognized entities. You specify the tags to use.",
"execution_settings": {
"default": {
"max_tokens": 256,
"temperature": 0.0,
"top_p": 0.0,
"presence_penalty": 0.0,
"frequency_penalty": 0.0,
"stop_sequences": [
"[done]"
]
}
}
}
@@ -0,0 +1,8 @@
Inject xml tags inline into the given text for the following:
{{$tags}}
- If there is nothing to tag, don't insert one.
- output [done] when original text was processed
{{$input}}