mcp-server-ppt: Instructions file for GitHub Copilot

.github/instructions/mcp-llm-guidance.instructions.md

mcp-server-ppt mcp-llm-guidance.instructions.md is an instructions file for GitHub Copilot from trsdn/mcp-server-ppt. It costs 1,195 tokens per session, scanned A, original, from a forked repository, MIT.

Instructions for writing guidance files that help AI assistants use the trsdn/mcp-server-ppt server correctly. MCP is a way for an AI assistant to call external tools.

In plain words
What is it for?
Use them when creating or editing an MCP guidance file for PowerPoint-related operations.
Why use it?
They help document server-specific actions, choices, quirks, examples, and common mistakes without explaining general PowerPoint concepts.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is trsdn/mcp-server-ppt's own configuration. It tells GitHub Copilot how to work on mcp-server-ppt itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-server-ppt configures →

Reuse

Borrowing it

Nothing to install: this file belongs to trsdn/mcp-server-ppt. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/trsdn/mcp-server-ppt/main/.github/instructions/mcp-llm-guidance.instructions.md
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 mcp-llm-guidance.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/trsdn/mcp-server-ppt/mcp-llm-guidance/github.svg)](https://agentmods.dev/instructions/trsdn/mcp-server-ppt/mcp-llm-guidance)
Your own site
<a href="https://agentmods.dev/instructions/trsdn/mcp-server-ppt/mcp-llm-guidance"><img src="https://agentmods.dev/badge/instructions/trsdn/mcp-server-ppt/mcp-llm-guidance/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-server-ppt mcp-llm-guidance.instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/trsdn/mcp-server-ppt/mcp-llm-guidance"><img src="https://agentmods.dev/badge/instructions/trsdn/mcp-server-ppt/mcp-llm-guidance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,195 This file is loaded in full into every session.
When invoked 1,195 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
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 $0.01195 $0.01195
Opus 5 $0.00598 $0.00598
Sonnet 5 $0.00239 $0.00239
Haiku 4.5 $0.00120 $0.00120

Measured 10d ago against content hash a034f98893ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-server-ppt mcp-llm-guidance.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 10d 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.

.github/instructions/mcp-llm-guidance.instructions.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP LLM Guidance Creation Guide

How to create effective guidance for LLMs consuming the MCP server

Core Principle

Write FOR expert LLMs (GitHub Copilot, Claude), not ABOUT the system.

LLMs already know PowerPoint, JSON, and MCP protocol. They need server-specific patterns only.

What to Include

1. Action Catalog:

  • Complete list of valid action values
  • Example: "Actions: get-values, set-values, clear-all"

2. Action Disambiguation:

  • When to use each action
  • Example: "clear-all removes formatting, clear-contents preserves it"

3. Tool Selection:

  • When to use this tool vs other tools
  • Example: "Use shape for content, slide for lifecycle"

4. Server-Specific Behavior:

  • Quirks of THIS implementation
  • Example: "Single cell returns [[value]] (2D array), not scalar"
  • Example: "For named ranges, use sheetName='' (empty string)"

5. Common Mistakes:

  • Pitfalls specific to this server
  • Example: "Don't forget batch mode for multiple operations"

6. Parameter Value Examples:

  • Actual values for string parameters
  • Example: rangeAddress can be "A1", "A1:C10", or "SalesData"

What to Exclude

❌ DON'T explain:

  • PowerPoint concepts (slides, shapes, animations)
  • JSON syntax
  • Programming basics (arrays, null, types)
  • MCP protocol syntax
  • Parameter types/requirements (schema provides)

Prompt File Structure

## [Tool Name] Tool

**Actions**: [comma-separated list]

**When to use [tool_name]**:
- [Scenario 1]
- Use [other_tool] for [different scenario]

**Server-specific behavior**:
- [Quirk 1]
- [Quirk 2]

**Action guide**:
- [action-name]: [What makes this different]
- [action-name]: [When to choose this]

**Common mistakes**:
- [Mistake 1 specific to this server]

Length Guidelines

  • ✅ One markdown file per tool
  • ✅ 50-150 lines total per tool
  • ✅ Focus on disambiguation, not explanation
  • ❌ Don't write PowerPoint tutorials
  • ❌ Don't explain JSON syntax

Format Guidelines

All MCP prompts are auto-generated from skills/shared/*.md:

  • Source of truth: skills/shared/*.md — edit these files
  • Auto-embedded and auto-generated PptSkillPrompts.g.cs at build time
  • NEVER create hand-crafted prompt files — add .md to skills/shared/ instead
  • To add a new prompt: add .md to skills/shared/, add description override in GenerateSkillPromptsClass task in McpServer.csproj, rebuild

Read the full file on GitHub · 153 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. 10d ago First seen · 153 lines · 1,195 tokens per session scan A a034f98893ea

Subscribe to this mod's changes

mcp-server-ppt mcp-llm-guidance.instructions.md is an instructions file published in the GitHub repository trsdn/mcp-server-ppt (37 stars, last pushed 5d ago), licensed MIT. It adds 1,195 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

Other instructions, from other repositories