Pamela Fox pamelafox

name	description	argument-hint
pdf-to-markdown	Converts PDF files to Markdown using Microsoft's markitdown package. Use this skill when the user asks to convert a PDF to Markdown, extract text from a PDF, or read/parse PDF content.	[path to file]

PDF to Markdown Conversion

This skill converts PDF files to Markdown format using Microsoft's markitdown package.

Overall algorithm

This is currently speculation:

When starting a session, it retrieves memories from the associated GitHub repository for the current branch and injects those into the initial user message.
When it sees something it should remember (like if I say "Remember that..."), it uses the memory tool to "view" existing memories, and then uses the memory tool to save the existing memory.
A hook then saves local memories to the GitHub repository and clears them from the local file system.

System prompt: How to use memory

name	description
review_pr_comments	This prompt is used to review comments on an active pull request and decide whether to accept, iterate, or reject the changes suggested in each comment.

We have received comments on the current active pull request. Together, we will go through each comment one by one and discuss whether to accept the change, iterate on it, or reject the change.

Steps to follow:

Fetch the active pull request: If available, use the activePullRequest tool from the GitHub Pull Requests toolset to get the details of the active pull request including the comments. If not, use the GitHub MCP server or GitHub CLI to get the details of the active pull request. Fetch both top level comments and inline comments.
Present a list of the comments with a one-sentence summary of each.

Agents using MCP servers

Framework	MCP integration	Tool filtering?	Example
Langchain	MultiServerMCPClient accepts a dictionary of MCP servers	Filter with get_tools() after connecting to servers	Example
Agent-framework	MCPStreamableHTTPTool for each MCP server	Filter with allowed_tools on that class, or tools on agent.run()	Example
Pydantic AI	MCPServerStreamableHTTP for each MCP server	Apply `.filtered()` method to the server and use result as a toolset for agent	Example

YouTube Talk to Article – Lean MVP Technical Spec

Derived from the original PRD but intentionally simplified for fastest viable implementation. Focus: “folder in, article out” with minimal config, vision-first extraction, and straightforward alignment (no embeddings initially).

1. MVP Goal & Non-Goals

Goal: Given a folder containing a deck.pptx (and optionally a transcript + config.yaml), produce article.md plus slide images using a simple CLI: talk2article <folder>.

Included in MVP:

description	applyTo
Python coding conventions and guidelines	*/.py

Python Coding Conventions

Python Instructions

Write clear and concise comments for each function.

	import asyncio
	import json
	import os

	from azure.ai.evaluation import AzureOpenAIModelConfiguration, IntentResolutionEvaluator
	from azure.identity import DefaultAzureCredential, get_bearer_token_provider
	from dotenv import load_dotenv

	from agentframework_learn import run_agent

	# ------------------- Stage 0: Base Stage ------------------------------
	FROM python:3.13-alpine AS base

	# Install tini, a tiny init for containers
	RUN apk add --update --no-cache tini

	# Install required packages for cryptography and ml-dtypes packages
	# https://cryptography.io/en/latest/installation/#building-cryptography-on-linux
	RUN apk add gcc g++ musl-dev python3-dev libffi-dev openssl-dev cargo pkgconfig

	import os

	from anthropic import AnthropicFoundry
	from dotenv import load_dotenv

	load_dotenv()

	endpoint = "https://pf-claude-foundry-proje-resource.openai.azure.com/anthropic"
	deployment_name = "claude-sonnet-4-5"

	"""Compare documents across two Azure AI Search indexes"""

	import argparse
	import asyncio
	import logging
	import os
	from collections.abc import Iterable, Mapping
	from dataclasses import dataclass, field
	from typing import Any, cast