Index of every page on this site: llms.txt
All skills
illyism avatar

/understand-customers

@a158c36
by Ilias Ismillyism/seo-skills1.8k stars
181
Run it yourself

Builds a buyer-psychology research brief covering customer pains, switching triggers, objections, inner monologue, and verbatim phrasing before writing a word of copy. Use when researching an ICP before landing page or ad copy, or when the user mentions "understand customers", "empathy engine", or "customer pain points".

Use this Skill: https://skilld.dev/gh/illyism/seo-skills/understand-customers

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈86 tokens for metadata: the name and description. ≈486 when used: this file.

Description uses 4.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈345 characters, or 4.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

For my product/service, [Briefly describe your product/service, e.g., "an AI-powered link building tool"], help me create Blitz Copy by first deeply understanding my ideal user. Answer these questions:

  1. Core Identity & Role:

    • Who are they really (e.g., "ambitious SaaS founder," "overwhelmed marketing manager," "freelancer struggling to scale")?
    • What's their primary goal related to the problem my product solves?
  2. Deepest Pains & Frustrations (The "Nightmare Scenario"):

    • What is their current biggest, most visceral nightmare related to [the problem your product solves, e.g., "link building," "content creation," "sales outreach"]?
    • What specific words or phrases do they use to describe this pain?
    • What deep inner thoughts or inner monologue is driving them?
    • What have they tried before that failed or disappointed them? Why?
    • What are the emotional consequences of this pain (e.g., "feeling stuck," "wasting money," "falling behind competitors," "imposter syndrome")?
  3. Unspoken Desires & Aspirations (The "Magic Wand" Outcome):

    • If they could wave a magic wand, what's the ultimate, almost "too good to be true" outcome they dream of regarding [the problem area]?
    • Beyond the functional benefit (e.g., "more backlinks"), what does this outcome mean for them emotionally or in terms of status (e.g., "market leader," "peace of mind," "industry recognition," "freedom")?
    • What would make them feel like they've found a "cheat code" or an "unfair advantage"?
  4. Language & Worldview:

    • What specific jargon, tools, or influencers are part of their world?
    • What's a core belief they hold about [the problem area] that my product can affirm or satisfyingly challenge?

Based on these insights, let's brainstorm initial Blitz Copy angles (Identity Triggers, Emotional Hooks, Pattern Interrupts, Dopamine-Driven Payoffs).

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts9d3 checks · Risk SAFE
  • Gen Agent Trust Hub10d

    This skill is a set of natural language prompts for customer research. It contains no executable code, tool calls, or security risks.

  • Socket9d

    No alerts

  • Snyk10d

    Risk: LOW · No issues

Signed by skilld at a158c36. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
Other metadata
metadata
{
  "version": "1.0.0",
  "author": "illyism",
  "source": "https://il.ly/skills/understand-customers"
}

README badge

README badge for illyism/seo-skills/understand-customers