General
PromptBeginner5 minmarkdown
usage: evaluation.py [-h] [-t {stdio
sse
0
Explore
Find agent skills by outcome
119,216 skills indexed with the new KISS metadata standard.
Showing 24 of 119,216Categories: Research & Learning, General, Coding & Debugging, Data
General
PromptBeginner5 minmarkdown
After creating your evaluation file
you can use the provided evaluation harness to test your MCP server.
0
General
PromptBeginner5 minmarkdown
- LLM might format differently (JSON array
comma-separated
0
General
PromptBeginner5 minmarkdown
<answer>repo1
repo2
0
General
PromptBeginner5 minmarkdown
- The answer will change as issues are created
closed
0
General
PromptBeginner5 minmarkdown
- Requires filtering bugs by date
priority
0
General
PromptBeginner5 minmarkdown
- Answer is a simple
verifiable value
0
General
PromptBeginner5 minmarkdown
<question>Among all bugs reported in January 2024 that were marked as critical priority
which assignee resolved the highest percentage of their assigned bugs within 48 hours? Provide the assignee's username.</question>
0
Coding & Debugging
PromptBeginner5 minmarkdown
<question>Look for pull requests that modified files in the /api directory and were merged between January 1 and January 31
2024. How many different contributors worked on these PRs?</question>
0
General
PromptBeginner5 minmarkdown
- In all tool call requests
use the `limit` parameter to limit results (<10)
0
General
PromptBeginner5 minmarkdown
- Make INCREMENTAL
SMALL
0
General
PromptBeginner5 minmarkdown
- Ensure each subagent is only performing READ-ONLY
NON-DESTRUCTIVE
0
General
PromptBeginner5 minmarkdown
- Use your intuition and understanding to create reasonable
realistic
0
General
PromptBeginner5 minmarkdown
- Understand input/output schemas
docstrings
0
Coding & Debugging
PromptBeginner5 minmarkdown
After understanding the API and tools
USE the MCP server tools:
0
General
PromptBeginner5 minmarkdown
- Message concept: message ID
message string
0
General
PromptBeginner5 minmarkdown
- If ambiguity exists
fetch additional information from the web
0
General
PromptBeginner5 minmarkdown
- Channel concept: channel ID
channel name
0
Research & Learning
PromptBeginner5 minmarkdown
- Example: if finding a paper name
be SPECIFIC enough so answer is not confused with papers published later
0
General
PromptBeginner5 minmarkdown
- User concept: user ID
user name
0
General
PromptBeginner5 minmarkdown
- Answers must not require special formatting or complex
structured output
0
General
PromptBeginner5 minmarkdown
- Examples: names
first name
0
General
PromptBeginner5 minmarkdown
- Timestamp
datetime
0
General
PromptBeginner5 minmarkdown
- File ID
file name
0