mcp-server-ppt llm-testing-philosophy.instructions.md

mcp-server-ppt llm-testing-philosophy.instructions.md is an instructions file for GitHub Copilot from trsdn/mcp-server-ppt. It costs 3,434 tokens per session, scanned A, a copy of mcp-server-excel llm-testing-philosophy.instructions.md, MIT.

A testing guide for checking whether an AI coding agent can use the project's command-line and MCP tools from natural-language requests. These tests evaluate documentation, tool descriptions, parameter names, error messages, and workflows rather than the AI model itself.

In plain words
What is it for?
Use it when investigating failed AI-assisted workflows, improving tool discoverability, refining instructions, or deciding whether a test failure points to a product or test problem.
Why use it?
It helps reveal when a real user would get stuck because the product is difficult to understand or recover from, rather than masking the problem by weakening the test.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/trsdn/mcp-server-ppt/llm-testing-philosophy
Clone the repo
git clone --depth 1 https://github.com/trsdn/mcp-server-ppt

Made for: GitHub Copilot.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-server-ppt llm-testing-philosophy.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/trsdn/mcp-server-ppt/llm-testing-philosophy.svg)](https://agentmods.dev/instructions/trsdn/mcp-server-ppt/llm-testing-philosophy)
Your own site
<a href="https://agentmods.dev/instructions/trsdn/mcp-server-ppt/llm-testing-philosophy"><img src="https://agentmods.dev/badge/instructions/trsdn/mcp-server-ppt/llm-testing-philosophy.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,434 This file is loaded in full into every session.
When invoked 3,434 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.03434 $0.03434
Opus 5 $0.01717 $0.01717
Sonnet 5 $0.00687 $0.00687
Haiku 4.5 $0.00343 $0.00343

Measured 6d ago against content hash e4c02ad881d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-server-ppt llm-testing-philosophy.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

89% identical to mcp-server-excel llm-testing-philosophy.instructions.md — 138 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/instructions/llm-testing-philosophy.instructions.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Testing Philosophy

⚠️ CORE PRINCIPLE: Tests simulate real users. Failures expose product gaps, not test gaps.

What Are LLM Tests?

LLM tests use an AI coding agent (with its own default system prompt) to exercise our CLI and MCP tools. The agent receives a natural language prompt — the same kind a real user would type — and must figure out how to accomplish the task using our tools.

These tests do NOT test the LLM. They test our product's usability surface:

  • Skill documentation (SKILL.md)
  • CLI --help output
  • MCP tool descriptions (XML /// <summary>)
  • Error messages and recovery hints
  • Parameter naming and discoverability
  • Workflow coherence

The Golden Rule

If the LLM can't figure it out, fix the product — never fix the test.

When an LLM test fails, the root cause is ALWAYS one of:

  1. Our skill docs don't explain the workflow clearly enough
  2. Our tool descriptions are misleading or incomplete
  3. Our CLI --help output doesn't show the right examples
  4. Our error messages don't guide recovery
  5. Our parameter names are confusing or undiscoverable
  6. The test itself is unreasonable (rare — only fix if a human couldn't do it either)

What NEVER Belongs in a Test

❌ xfail or skip Markers

NEVER use @pytest.mark.xfail or @pytest.mark.skip to hide failing tests.

Tests either pass or fail. There is no middle ground.

  • xfail masks real failures and creates a false sense of progress
  • skip hides broken code instead of fixing it
  • If a test fails, fix the product — the test is exposing a real problem (Golden Rule)
  • If a test is flaky, fix the flakiness — don't paper over it with xfail

❌ CLI Command Guidance in Prompts

A real user doesn't know our CLI syntax. Neither should the test prompt.

# ❌ WRONG: Teaching the LLM how to use our CLI
prompt = """
Create a slide layout then set it to use a custom master using 
'pptcli slidemaster' (run --help to see options).
The custom layout uses layout-type value 0.
"""

# ✅ CORRECT: Natural user request
prompt = """
Create a presentation with a custom slide layout showing
title and content areas.
"""

Read the full file on GitHub · 373 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 373 lines · 3,434 tokens per session scan A e4c02ad881d1

Subscribe to this mod's changes

mcp-server-ppt llm-testing-philosophy.instructions.md is an instructions file published in the GitHub repository trsdn/mcp-server-ppt (36 stars, last pushed yesterday), licensed MIT. It adds 3,434 tokens to every session, about $0.0172 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to mcp-server-excel llm-testing-philosophy.instructions.md, differing in 138 lines, and is treated as a copy.

Related

Other instructions, from other repositories