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

/growth-hacking-loop

@7cbc184
Run it yourself

Run rapid growth experiments across acquisition, activation, retention, and revenue using a structured growth team process. Use when the user mentions growth hacking, growth teams, rapid experimentation, activation, retention, or a stalled acquisition funnel.

  • 2 files
  • 5 KB
  • Updated last month
  • GitHub
Use this Skill: https://skilld.dev/gh/salikshah/startup-agent-skills/growth-hacking-loop

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈70 tokens for metadata: the name and description. ≈758 when used: this file. ≈413 more on demand in 1 file.

Description uses 3.5% 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 ≈281 characters, or 3.5%.

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.

Growth Hacking Loop

Intent

Use Sean Ellis's growth hacking methodology to systematically find and scale your highest-leverage growth channel through rapid, structured experimentation across the AARRR funnel.

Inputs

  • Product or service with at least minimal traction
  • Access to analytics and user behavior data
  • Cross-functional team (engineering, marketing, product)
  • Defined north-star metric
  • List of potential growth hypotheses

Process (SOP)

  1. Step 1: Form a growth team with a dedicated growth lead, engineer, marketer, and product manager — this team owns growth across functions.
  2. Step 2: Identify your north-star metric (e.g., weekly active users, monthly recurring revenue) that best captures delivered value.
  3. Step 3: Map the full AARRR funnel (Acquisition, Activation, Retention, Revenue, Referral) and identify the weakest, highest-impact stage.
  4. Step 4: Brainstorm a large quantity of growth ideas (aim for 20+) targeting the weakest funnel stage.
  5. Step 5: Prioritize ideas using an impact-confidence-ease scoring framework (ICE or similar) — select the top 3-5 for testing.
  6. Step 6: Design each experiment with a clear hypothesis, success metric, and minimum detectable effect.
  7. Step 7: Run experiments rapidly (1-2 week cycles) — ship MVPs of growth features, not final products.
  8. Step 8: Analyze results rigorously; kill what does not move the metric, double down on what does.
  9. Step 9: Scale winning experiments by increasing investment incrementally and monitoring diminishing returns.
  10. Step 10: Systematize wins into repeatable playbooks and move to the next funnel stage.

Outputs

  • A prioritized pipeline of growth experiments with ICE scores
  • A tested, documented set of winning growth levers
  • Scaled user acquisition and/or retention
  • A repeatable growth playbook

Evidence

Source: "Hacking Growth" by Sean Ellis & Morgan Brown. Key concepts: growth team structure, high-tempo testing, ICE prioritization, AARRR pirate funnel, north-star metric, diminishing returns curves.

Examples

A B2B SaaS company discovers activation is their bottleneck — signups are strong but few users complete onboarding. They run 12 activation experiments in 6 weeks. A guided checklist + progress bar lifts activation by 22%. They scale it globally and document it in their growth playbook.

Metrics

  • Number of experiments run per month (target: 10+)
  • Win rate of experiments (healthy range: 10-30%)
  • North-star metric growth rate week-over-week
  • Cost per acquisition trend across scaled channels

Anti-Patterns

  • Running experiments without a clear hypothesis
  • Declaring victory after one positive data point without statistical confidence
  • Letting HiPPOs (highest paid person's opinions) override experiment results
  • Neglecting retention to chase acquisition — growth without retention leaks
  • Running too many experiments simultaneously, making results uninterpretable
  • Copying growth tactics from other companies without testing them in your context

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 third-party reports yet.

Signed by skilld at 7cbc184. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last month
disable-model-invocation
false
Other metadata
triggers
[
  "growth hacking",
  "growth team",
  "rapid experimentation",
  "user activation",
  "retention loop"
]

README badge

README badge for salikshah/startup-agent-skills/growth-hacking-loop