plg-ideas

plg-ideas is a skill for Claude Code from SkeneTechnologies/plg-skills. It costs 84 tokens per session (5,058 once invoked), scanned A, original, MIT.

A reference of more than 100 product-led growth ideas. Product-led growth, or PLG, means growing a product mainly through people trying, using, and sharing the product themselves.

In plain words
What is it for?
Use it to brainstorm, filter, prioritise, and score tactics for acquisition, activation, retention, monetisation, or expansion.
Why use it?
It helps turn a broad growth problem into a shortlist of ideas matched to the team's capacity, goals, and weakest growth area.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the plg-skills plugin — 27 skills shipped together

Good fit Use it to brainstorm, filter, prioritise, and score tactics for acquisition, activation, retention, monetisation, or expansion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skenetechnologies/plg-skills/plg-ideas
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 SkeneTechnologies/plg-skills --skill plg-ideas
Clone the repo
git clone --depth 1 https://github.com/SkeneTechnologies/plg-skills

Made for: Claude Code.

Or install plg-skills, the plugin that ships this one along with the rest of its 27 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 plg-ideas

README.md
[![agentmods](https://agentmods.dev/badge/skills/skenetechnologies/plg-skills/plg-ideas/github.svg)](https://agentmods.dev/skills/skenetechnologies/plg-skills/plg-ideas)
Your own site
<a href="https://agentmods.dev/skills/skenetechnologies/plg-skills/plg-ideas"><img src="https://agentmods.dev/badge/skills/skenetechnologies/plg-skills/plg-ideas/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 plg-ideas

Your own site · 80×15
<a href="https://agentmods.dev/skills/skenetechnologies/plg-skills/plg-ideas"><img src="https://agentmods.dev/badge/skills/skenetechnologies/plg-skills/plg-ideas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,058 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 $0.00084 $0.05058
Opus 5 $0.00042 $0.02529
Sonnet 5 $0.00017 $0.01012
Haiku 4.5 $0.00008 $0.00506

Measured 12d ago against content hash 80399977148c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

plg-ideas 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 12d 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/plg-ideas/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PLG Ideas

You are a PLG tactician and idea curator. A mega-reference of 100+ Product-Led Growth tactics and strategies organized by category. Use this as a brainstorming tool, prioritization input, or roadmap inspiration. Each idea includes difficulty, impact potential, and which PLG lever it primarily affects.

Diagnostic Questions

Before recommending ideas, ask the user:

  1. What is your weakest PLG lever right now? (Acquisition / Activation / Retention / Monetization / Expansion)
  2. What is your team size and engineering capacity? (Solo founder / Small team / Growth team / Full engineering org)
  3. What have you already tried? What worked and what didn't?
  4. What is your current biggest growth bottleneck?
  5. Do you have a working growth loop, or are you still finding product-market fit?
  6. What is your timeline -- do you need quick wins or are you investing for the long term?

How to Use This Skill

  1. Diagnose: Ask the diagnostic questions above to understand the user's context
  2. Filter: Narrow the 108 ideas to the relevant PLG lever and difficulty level
  3. Shortlist: Select the top 5-10 ideas that match the user's context, capacity, and bottleneck
  4. Score: Use ICE scoring (Impact x Confidence x Ease, each 1-10) to rank the shortlist -- see growth-experimentation for the full ICE framework
  5. Recommend: Present the top 3-5 ideas with a brief rationale for each
  6. Plan: For the user's chosen idea(s), outline a concrete next-steps plan

Legend

  • Difficulty: Low (days), Medium (weeks), High (months)
  • Impact: Low (incremental), Medium (meaningful), High (step-change)
  • PLG Lever: Acquisition, Activation, Retention, Monetization, Expansion

Activation and Onboarding Ideas

# Idea Description Diff Impact Lever
1 Interactive Product Tour Guided walkthrough highlighting key features on first entry. Tools: Appcues, Userflow, or custom. Low High Activation
2 Personalized Onboarding by Role Ask role/use case at signup, customize flow to show most relevant features first. Med High Activation
3 Sample Data Pre-Loading Pre-populate with realistic sample data so users see a "full" experience, not a blank canvas. Low Med Activation
4 Onboarding Checklist + Progress Bar Visible checklist with endowed progress effect (start at 20%). Celebrate each step. Low High Activation
5 "Quick Win" First-Run Experience Design first 5 minutes to deliver a tangible result. Front-load the value. Med High Activation
6 Video Walkthroughs Short (60-90s) contextual videos at key moments. Multiple micro-videos, not one long tutorial. Low Med Activation
7 In-Product Help Center Searchable help, tooltips, contextual docs without leaving the product. Med Med Activation
8 AI-Assisted Onboarding AI guides setup: auto-configure settings, suggest next steps, generate initial content. High High Activation
9 Template Gallery Pre-built templates/examples users can duplicate and customize. Solves blank canvas problem. Med High Activation
10 Guided Setup Wizard Multi-step wizard for essential config: integrations, preferences, data import, team invites. Med Med Activation
11 Sandbox / Playground Separate environment for risk-free experimentation. Valuable for infrastructure/financial tools. High Med Activation
12 Time-to-Value Sprint Dedicated sprint to reduce time between signup and first value moment. Map and eliminate friction. Med High Activation
13 Activation Email Sequence Behavior-triggered emails for first 7-14 days based on what user has NOT done yet. Med Med Activation
14 Stalled User Nudges In-product/email nudges for users who signed up but haven't progressed. Triggered by inactivity. Low Med Activation
15 Milestone Celebrations Animations, confetti, badges when users complete key steps. Small dopamine hits reinforce behavior. Low Low Activation
16 Contextual Empty States Helpful empty states with clear CTA, example content, or direct path to create first item. Low Med Activation
17 Progressive Disclosure Reveal advanced features as users master basics. Prevents overwhelm, creates discovery. Med Med Activation

Read the full file on GitHub · 263 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. 12d ago First seen · 263 lines · 84 tokens per session scan A 80399977148c

Subscribe to this mod's changes

plg-ideas is a skill published in the GitHub repository SkeneTechnologies/plg-skills (19 stars, last pushed 7mo ago), licensed MIT. It adds 84 tokens to every session and 5,058 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens