General
PromptBeginner5 minmarkdown
- Ensure that despite AMBIGUITY
there is STILL A SINGLE VERIFIABLE ANSWER
0
Explore
Find agent skills by outcome
74,761 skills indexed with the new KISS metadata standard.
Showing 24 of 74,761Categories: Data, General, Coding & Debugging, Cursor-rules
General
PromptBeginner5 minmarkdown
- Questions may require specific output formats (datetime vs. epoch time
JSON vs. MARKDOWN)
0
General
PromptBeginner5 minmarkdown
- For example
do not count:
0
General
PromptBeginner5 minmarkdown
- File IDs
names
0
General
PromptBeginner5 minmarkdown
- URLs
GIDs
0
General
PromptBeginner5 minmarkdown
- Timestamps and datetimes (months
days
0
General
PromptBeginner5 minmarkdown
- Require multiple searches
analyzing multiple related items
0
General
PromptBeginner5 minmarkdown
- May elicit tools returning large JSON objects or lists
overwhelming the LLM
0
General
PromptBeginner5 minmarkdown
- Use synonyms
related concepts
0
General
PromptBeginner5 minmarkdown
- Complex
requiring potentially dozens of tool calls or steps
0
General
PromptBeginner5 minmarkdown
3. **Questions must be REALISTIC
CLEAR
0
General
PromptBeginner5 minmarkdown
- Answerable with a single
verifiable value that you identify in advance
0
General
PromptBeginner5 minmarkdown
Create 10 human-readable questions requiring ONLY READ-ONLY
INDEPENDENT
0
General
PromptBeginner5 minmarkdown
The measure of quality of an MCP server is NOT how well or comprehensively the server implements tools
but how well these implementations (input/output schemas
0
General
PromptBeginner5 minmarkdown
- Answers must be single
verifiable values
0
General
PromptBeginner5 minmarkdown
- **Performance testing**: Check behavior under load
timeouts
0
General
PromptBeginner5 minmarkdown
- Questions must be READ-ONLY
INDEPENDENT
0
General
PromptBeginner5 minmarkdown
This document provides guidance on creating comprehensive evaluations for MCP servers. Evaluations test whether LLMs can effectively use your MCP server to answer realistic
complex questions using only the tools provided.
0
General
PromptBeginner5 minmarkdown
- Provide helpful
specific error messages with suggested next steps
0
General
PromptBeginner5 minmarkdown
- **Security testing**: Validate auth
input sanitization
0
Coding & Debugging
PromptBeginner5 minmarkdown
- Store API keys in environment variables
never in code
0
General
PromptBeginner5 minmarkdown
- Single-user
single-session scenarios
0
General
PromptBeginner5 minmarkdown
**Important**: Annotations are hints
not security guarantees. Clients should not make security-critical decisions based solely on annotations.
0
General
PromptBeginner5 minmarkdown
- Simple setup
no network configuration needed
0