get-more-from-ai

get-more-from-ai is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 135 tokens per session (1,084 once invoked), scanned A, original, MIT.

A practical guide to improving how you work with AI, from asking one-off questions to giving context, iterating, showing examples, breaking down tasks, and checking results.

In plain words
What is it for?
Use it to review your current AI habits, compare your existing approach with an improved one, and build better practices step by step.
Why use it?
It identifies the few habits most limiting your results instead of overwhelming you with a long list of techniques.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it to review your current AI habits, compare your existing approach with an improved one, and build better practices step by step.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/get-more-from-ai
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,352 stars · on GitHub · mohitagw15856.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

Made for: Cursor.

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 get-more-from-ai

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/get-more-from-ai/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/get-more-from-ai)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/get-more-from-ai"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/get-more-from-ai/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 get-more-from-ai

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/get-more-from-ai"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/get-more-from-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,084 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 $0.00135 $0.01084
Opus 5 $0.00068 $0.00542
Sonnet 5 $0.00027 $0.00217
Haiku 4.5 $0.00014 $0.00108

Measured 8d ago against content hash 579029b1fc03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

get-more-from-ai 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.

exports/cursor/pm-ai-native/get-more-from-ai/get-more-from-ai.mdc · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Get More From AI

Most people use AI at a fraction of its capability — one-shot questions, accept the first answer, move on — and never learn the handful of techniques that separate a frustrating tool from a force multiplier. The gap isn't a better model; it's how you use the one you have. This reads how you use AI now, picks the two or three techniques that would help you most next, and shows the difference on your own examples — a targeted level-up, not a firehose of a hundred tips.

What This Skill Produces

  • An honest read of your current use — how you use AI now and the specific habits capping your results (one-shot asking, no context, accepting first drafts, no examples)
  • Your highest-leverage next techniques — the 2–3 that would most improve your results, from: giving rich context, iterating instead of accepting, showing examples, decomposing big asks, assigning a role, and verifying output
  • A before/after on your own use — the same task done your current way vs the leveled-up way, so the payoff is concrete
  • A simple practice path — how to build the new techniques into habits one at a time, not all at once
  • The mindset shift — from "search box" to "collaborator you brief, iterate with, and check" — the frame behind all the techniques

Required Inputs

Ask for these if not provided:

  • How you use AI now — a real example of a prompt or task (shows exactly what to level up)
  • Where it frustrates you — where results fall short (points at the missing technique)
  • What you use it for — your main tasks and domains
  • Your level — beginner / regular / trying to go advanced

Framework: Close The Gap One Technique At A Time

  1. Diagnose the current pattern. Look at how the person actually uses AI — the habit capping their results is usually obvious (one-shot, context-starved, first-draft-accepting) and points straight at the fix.
  2. Pick the 2–3 that pay off most. Don't dump every technique. From context-giving, iterating, showing examples, task decomposition, role-setting, and verifying — choose the few that fix this person's bottleneck.
  3. Show the payoff on their example. Take their real task and show it done the leveled-up way beside their current way — the gap is the motivation.
  4. Reframe the mindset. The through-line: AI is a collaborator you brief richly, push back on, and iterate with — not a vending machine you query once. The techniques follow from the frame.
  5. Practice one at a time. Build one technique into a habit before adding the next — layering beats a firehose that nothing sticks from.

Read the full file on GitHub · 65 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 · 65 lines · 135 tokens per session scan A 579029b1fc03

Subscribe to this mod's changes

get-more-from-ai is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 135 tokens to every session and 1,084 once invoked, about $0.0007 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 2026-09-03.