technical-pm

technical-pm is a skill for Claude Code from aroyburman-codes/pm-skills. It costs 34 tokens per session (1,820 once invoked), scanned A, original, MIT.

A structured guide for answering technical product-management questions about AI systems. It covers topics such as reinforcement learning from human feedback, testing model behavior, search-assisted generation, deployment, system design, and APIs.

In plain words
What is it for?
Working through AI system designs, model and deployment questions, retrieval-based systems, API choices, and technical trade-offs from a product-manager perspective.
Why use it?
It gives AI product discussions a consistent technical structure and prompts attention to capabilities, scale, architecture, and trade-offs. This helps avoid vague answers about how an AI product should work.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the pm-skills plugin — 17 skills shipped together

Good fit Working through AI system designs, model and deployment questions, retrieval-based systems, API choices, and technical trade-offs from a product-manager perspective.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aroyburman-codes/pm-skills/technical-pm
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.

Any agent
npx skills add aroyburman-codes/pm-skills --skill technical-pm
Clone the repo
git clone --depth 1 https://github.com/aroyburman-codes/pm-skills

Made for: Claude Code.

Or install pm-skills, the plugin that ships this one along with the rest of its 17 skills.

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 technical-pm

README.md
[![agentmods](https://agentmods.dev/badge/skills/aroyburman-codes/pm-skills/technical-pm.svg)](https://agentmods.dev/skills/aroyburman-codes/pm-skills/technical-pm)
Your own site
<a href="https://agentmods.dev/skills/aroyburman-codes/pm-skills/technical-pm"><img src="https://agentmods.dev/badge/skills/aroyburman-codes/pm-skills/technical-pm.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,820 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 $0.00034 $0.01820
Opus 5 $0.00017 $0.00910
Sonnet 5 $0.00007 $0.00364
Haiku 4.5 $0.00003 $0.00182

Measured 8d ago against content hash 124350fe07f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

technical-pm 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 8d 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.

skills/technical-pm/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical PM Skill

Apply a structured framework to technical PM questions targeting AI product roles.

When to Use

  • User asks about RLHF, fine-tuning, evals, inference, model architecture
  • User asks "Design a system that uses LLMs to X"
  • User asks "How would you build a RAG system for X"
  • User asks about technical trade-offs in AI/ML systems
  • User asks about API design for AI products
  • User says /technical-pm followed by a question
  • Any question requiring ML/AI technical depth from a PM perspective

Context

  • Tuned for: AI product roles at frontier AI companies
  • What matters: Going deep with researchers and engineers. You don't need to implement, but you need to understand the technical landscape well enough to make informed product decisions.
  • Common pitfall: Hand-waving on technical details. Be specific about architectures, trade-offs, and constraints.

Framework: AI PM Technical Method (6 Sections)

Section 1: Technical Clarifications & Constraints

Before designing anything, scope the technical problem:

  • Capability Assumptions: What model capabilities are available? (reasoning, multimodal, tool use, code gen)
  • Scale: How many users/queries? What latency requirements?
  • Infrastructure: Cloud vs. on-prem? What compute budget?
  • Data: What training/eval data exists? Privacy constraints?
  • Integration: What systems does this need to plug into?
  • Timeline: MVP vs. production-grade?

Section 2: Users (Developer & End-User Personas)

For technical products, think about two user layers:

  • Developers/Engineers: Who builds on this? What's their skill level? What do they expect?
  • End Users: Who consumes the output? What quality bar do they need?

For each persona: current workflow, technical sophistication, key frustrations.

Section 3: High-Level System Design

Draw the system architecture (describe it clearly):

  • Data Pipeline: How does data flow in? (user input → preprocessing → model → postprocessing → output)
  • Model Layer: Which model(s)? Foundation model + fine-tuned? Routing? Ensemble?
  • Orchestration: How are multi-step workflows managed? (agents, chains, state machines)
  • Storage: What needs to be persisted? (conversation history, embeddings, user preferences, model artifacts)
  • Serving: How is inference served? (batch vs. real-time, edge vs. cloud)

Read the full file on GitHub · 173 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. 8d ago First seen · 173 lines · 34 tokens per session scan A 124350fe07f6

Subscribe to this mod's changes

technical-pm is a skill published in the GitHub repository aroyburman-codes/pm-skills (25 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 1,820 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

markitdown

Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.

K-Dense-AI/scientific-agent-skills · 61 tokens

rag-architect

Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality. Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic…

Jeffallan/claude-skills · 73 tokens

pgvector-semantic-search

Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…

timescale/pg-aiguide · 190 tokens

postgres-hybrid-text-search

Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…

timescale/pg-aiguide · 162 tokens

bedrock

AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.

itsmostafa/aws-agent-skills · 36 tokens

rag-construction

Build RAG systems for construction knowledge bases. Create searchable AI-powered construction document systems.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 20 tokens