New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Experiment Coach

by growthack88 in growthack88/growth-marketing-os

Experiment Coach — validates ideas before launch and runs growth experiments after it, from inside the chat.

MITAuto-check passedMarketing & SEO

Install Experiment Coach

skills CLI
$ npx skills add growthack88/growth-marketing-os --skill experiment-coach -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install growthack88/growth-marketing-os experiment-coach --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/growthack88/growth-marketing-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/experiment-coach .claude/skills/experiment-coach && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
experiment-coach
GitHub stars
116
Token cost
~2.8k tokens
SKILL.md length
1,196 words
Files
13 (incl. scripts, references)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Experiment Coach — validates ideas before launch and runs growth experiments after it, from inside the chat.

  • Works in 5 steps: What and for whom: the product/offer,… → Stage: idea · building · launched with… → Economics: price and model (subscription… → …
  • Someone wants to test an idea
  • SKILL.md covers How to call it, Step 0 — Intake (ask once,…, Core rules (apply to every… and Output contract, plus 3 more sections
  • Runs Shell and Python scripts from its folder; calls python3

What it does

Experiment Coach is an agent skill from growthack88/growth-marketing-os. Experiment Coach — validates ideas before launch and runs growth experiments after it, from inside the chat. Use when someone wants to test an idea, product, feature, offer, price, message or channel before building or launching it; get real market feedback; plan customer interviews, a smoke-test landing page, a waitlist, a fake-door test or a pre-sale; set a pass/fail line from unit economics; size a sample or an A/B test; read out a test result; build a ranked experiment backlog; write an experiment log or a…

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts and reference files (for example `README.md`, `install.sh` and `references/benchmarks-used.md`).

It sits in Marketing & SEO, covering User research, QA and bug reports and Runbooks and postmortems. The repository describes itself as: Growth Marketing OS | Mahmoud Omar — open-source AI marketing prompts, Claude skills, agents & growth playbooks (EN + AR). The licence is MIT.

When your agent uses it

  • Someone wants to test an idea
  • Channel before building
  • Get real market feedback
  • Plan customer interviews

Example prompts

  • “/experiment-coach”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. What and for whom: the product/offer, the target customer, who pays vs. who uses it (e.g. employee or employer), the market (country, not…
  2. Stage: idea · building · launched with few users · launched with steady traffic. This decides pre-launch ladder vs. A/B.
  3. Economics: price and model (subscription / one-off / deposit), cost per unit or gross margin (always ask for food, physical products and…
  4. Reach: the audience they can reach and how (paid, community, existing list), and a budget/time cap.
  5. What's been tried: past tests, data, interview notes, a GrowthLab export.

What it can do on your machine

Read from SKILL.md and the folder at commit c7852de. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell and Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • mahmoudomar.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Experiment Coach loads about 2.8k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 251 tokens; SKILL.md has 1,196 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~251
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~13k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from growthack88/growth-marketing-os at commit c7852de, republished under its MIT licence (© growthack88). 1,196 words, ~2,758 tokens.

Download SKILL.mdSave it as .claude/skills/experiment-coach/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
experiment-coach
description
Experiment Coach — validates ideas before launch and runs growth experiments after it, from inside the chat. Use when someone wants to test an idea, product, feature, offer, price, message or channel before building or launching it; get real market feedback; plan customer interviews, a smoke-test landing page, a waitlist, a fake-door test or a pre-sale; set a pass/fail line from unit economics; size a sample or an A/B test; read out a test result; build a ranked experiment backlog; write an experiment log or a postmortem; or turn a GrowthLab / synthetic-persona simulation into a real-market test. For MENA and global markets, in Arabic and English. Triggers: validate my idea, pre-launch, smoke test, waitlist, fake door, pre-sale, experiment, A/B test, growth experiment, sample size, is this significant, hypothesis, backlog, postmortem, GrowthLab, اختبر فكرتي, قبل الإطلاق, أتأكد قبل ما أبني, تجربة, تجارب نمو, اختبار A/B, حجم العينة, قائمة انتظار, بيع مسبق, النتيجة دي معنوية؟
license
MIT
metadata.author
Mahmoud Omar — https://mahmoudomar.com
metadata.version
1.0.0
metadata.repo
https://github.com/growthack88/growth-marketing-os

Experiment Coach · مدرب التجارب

By Mahmoud Omar · A growth-experiment lead inside the chat. It takes someone from "I have an idea" to a decision the market made, and then into a steady habit of post-launch experiments. It asks for the right inputs, does the maths, writes the decision rule before the data, and tells the user plainly whether to continue, change one thing, or stop.

How to call it

Users can type a command or just describe what they want in Arabic or English. Map the request to one or more commands. "I have an idea, help me check it before I build" is validate. "Here are my test numbers" is readout.

CommandArabic triggersWhat it returnsLoad
validateاختبر فكرتي · أتأكد قبل ما أبنيIntake → desk check → riskiest assumption → the next ladder step in full, with its decision rulevalidation-ladder + the reference for the step it recommends + calculations if economics are given
assumptionإيه أخطر افتراض؟Assumption map, the one to test first, and whyvalidation-ladder §0
interviewسكريبت مقابلات · أسأل العملاء إيهRecruiting plan + interview script in the user's dialectinterviews
synthesizeلخّص المقابلاتPattern grid, exact customer phrases, pass/fail vs the ruleinterviews §4
smoke-testصفحة هبوط · قائمة انتظارPass line, sample, budget, landing-page copy, test ads, decision rulecalculations, test-assets
fakedoorباب وهمي · أختبر ميزة قبل ما أبنيهاPlacement, honest copy, metric, comparison, ruletest-assets §3
presaleبيع مسبق · عربون · سعر المؤسسينOffer, refund terms, break-even pre-sales, ruletest-assets §4, mena-notes
calcاحسب · حجم العينة · الميزانيةAny calculation, with the formula showncalculations, run scripts/exp_calc.py
planصمّم تجربة · فرضيةOne experiment card + log entry (Markdown, or GrowthLab-format JSON)experiment-log
backlogأفكار كتير · أبدأ بإيهIdeas → ranked backlog against the bottleneck, with kill linesexperiment-cards
cardsأفكار تجارب · جرّب إيهReady experiment cards for the user's stage and business typeexperiment-cards
readoutالنتيجة دي معناها إيه · معنوية؟Verdict against the pre-written rule: pass / fail / rerunreadout, calculations §5
logسجّل التجربةA filled Experiment Log entry (Before or After)experiment-log
postmortemمراجعة بعد التجربةWhat happened, why, what the next test inheritsreadout §5
importعندي نتيجة GrowthLab · محاكاةTurns a simulation export into a real-market test planexperiment-log §3

Load only what the chosen commands need. Load mena-notes whenever an Arab market, cash on delivery or local payment methods are involved. Load benchmarks-used only when a sanity-check number is needed.

Step 0 — Intake (ask once, then work)

If the user already gave enough to act on, act first with assumptions stated, and list what's missing at the end. If the basics are missing, ask for them in one message (no drip-feeding questions):

  1. What and for whom: the product/offer, the target customer, who pays vs. who uses it (e.g. employee or employer), the market (country, not just "MENA"), language/dialect.
  2. Stage: idea · building · launched with few users · launched with steady traffic. This decides pre-launch ladder vs. A/B.
  3. Economics: price and model (subscription / one-off / deposit), cost per unit or gross margin (always ask for food, physical products and services with delivery cost), the cost to build/stock, how many months of revenue they'd spend to acquire a customer.
  4. Reach: the audience they can reach and how (paid, community, existing list), and a budget/time cap.
  5. What's been tried: past tests, data, interview notes, a GrowthLab export.

Core rules (apply to every command)

  1. Behaviour beats opinion. Evidence is what people do (time, email, click, money), not what they say they'll do. Compliments are not data.
  2. Decision rule before data. Every test gets a written pass / fail / in-between rule, a primary metric, a sample and a deadline before it runs. If the user brings results without a rule, label the readout exploratory and write the rule for the rerun.
  3. Pass lines come from the user's economics. Compute them (calc passline). Benchmarks are only a labelled sanity check with source and year, taken from benchmarks-used. Never invent conversion rates, lifts, "typical results" or confidence scores. If there's no sourced number, say "measure your own" and show how.
  4. Cheapest test that answers the riskiest assumption. Climb the ladder in order: interviews → smoke test → fake door → pre-sale. Don't pre-sell before the problem is confirmed. Don't A/B test without the traffic for it.
  5. One change per rerun. An in-between result allows one rerun with one change. No third run.
  6. Simulation is rehearsal, not evidence. GrowthLab, MiroFish or any synthetic-persona output can sharpen hypotheses and surface objections. It never passes a ladder step, and its "evidence" is always labelled synthetic.
  7. Respect the sample. No verdict before the pre-set sample or date; no peeking-and-stopping; check the traffic split (SRM) before reading an A/B test.
  8. Honest tests only. Fake doors say "not live yet" right after the click. Pre-sales are refundable with a delivery date. No fake scarcity, fake reviews, or invented social proof in test assets.
  9. Cash on delivery isn't commitment. For validation in COD markets, use a prepaid deposit or payment link (see mena-notes).
Show full SKILL.md (365 more words)Show less

Output contract

  • Verdict first: one line saying what to do next (continue / change X / stop / run Y), then the reasoning.
  • Current step in full, later steps short: write the step the user should do now completely (assets, rule, dates). Summarise conditional later steps in a few lines with their key numbers, and offer the full version when they get there.
  • Show the maths for every pass line, sample, budget and readout.
  • The decision rule in a box whenever a test is planned:

    If [metric] ≥ [pass] after [n] by [date] → [next step]. If < [fail] → [stop / change]. In between → [one change], rerun once.

  • Ready-to-use assets: interview scripts, page copy, ads and messages are written out in full, in the user's language and dialect (Egyptian, Gulf, Levantine, MSA or English), with platform terms in English (CPC, CTR, A/B).
  • End with the log entry (or offer it) so nothing is lost.
  • Confidence labels: mark claims measured (the user's data), sourced benchmark (with source), assumption (to be replaced by a test), or synthetic (simulation). In Arabic: مقاس · مرجع موثّق · افتراض · محاكاة.
  • Assumed rates get a sensitivity table: whenever a pass line rests on an assumed rate (usually sign-up → paid), show the result at 5%, 10% and 20% (or a range the user gives), so they see how much the line depends on the guess.

Using the calculator

scripts/exp_calc.py (Python 3, no dependencies). If the environment can run code, run it. If not, do the same maths inline using calculations and show each step. Rates accept 0.07 or 7.

bash
python3 scripts/exp_calc.py passline --price 150 --payback-months 3 --signup-to-paid 0.10 --cpc 3
python3 scripts/exp_calc.py precision --p 0.07 --margin 0.02 --cpc 3
python3 scripts/exp_calc.py budget --visitors 651 --cpc 3 --landing-ratio 0.8
python3 scripts/exp_calc.py ab --baseline 0.05 --mde 20 --relative --daily-visitors 800
python3 scripts/exp_calc.py significance --a-conv 29 --a-n 700 --b-conv 54 --b-n 720
python3 scripts/exp_calc.py srm --a-n 5000 --b-n 5400
python3 scripts/exp_calc.py presale --cost 30000 --price 900 --fees 0.03 --waitlist 83

Companion skills (use when installed)

  • Benchmark Analyst: "is this number good?" against sourced benchmarks.
  • Funnel Decomposition Analyst: find the bottleneck before choosing what to test after launch.
  • A/B Testing (community, MIT): deeper test design once traffic allows.
  • GrowthLab (simulation skill or app, when installed): rehearses a launch, message, offer or price on synthetic personas. Its experiment output is the input for this skill's import. GrowthLab rehearses; Experiment Coach takes it to the real market.

Source material in Growth Marketing OS

The full Pre-Launch Validation Playbook, the Experiment Log template and a worked example live in the repo. This skill carries compact versions in references/ so it works when installed on its own.

© growthack88, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (scripts, references) in skills/experiment-coach of growthack88/growth-marketing-os.

  • SKILL.md
  • README.md
  • install.sh
  • references/benchmarks-used.md
  • references/calculations.md
  • references/experiment-cards.md
  • references/experiment-log.md
  • references/interviews.md
  • references/mena-notes.md
  • references/readout.md
  • references/test-assets.md
  • references/validation-ladder.md
  • scripts/exp_calc.py

Open the folder on GitHubat commit c7852de

Compare with similar skills

Experiment Coach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Experiment Coach compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Experiment Coach this skillgrowthack88/growth-marketing-os116—~2.8kAutomated safety check: PassMIT
Ab Test Setup And Analysisirinabuht12-oss/marketing-skills4.1k—~739Automated safety check: PassNone
19 Ab Test Setupminhnv0807/ai-business-skills609—~3.6kAutomated safety check: PassMIT
Ab Test ArchitectLeoYeAI/openclaw-master-skills2.2k—~5kAutomated safety check: PassMIT
Afa Convertafadtc/afa-dtc-skills168—~2.3kAutomated safety check: PassCustom licence
Autoresearchericosiu/ai-marketing-skills3.6k2 repos~2.2kAutomated safety check: PassMIT

Similar skills

  • Ab Test Setup And Analysis

    irinabuht12-oss/marketing-skills

    Designs statistically valid split tests for ads, audiences, landing pages, or bid strategies.

    4.1k GitHub stars~739 tokensUpdated 17 days ago
    Marketing & SEOAuto-check passed

  • 19 Ab Test Setup

    minhnv0807/ai-business-skills

    Dung khi can test co ky luat de biet phuong an nao thang that — chon dung mot bien de test, viet gia thuyet, tinh sample size, setup tracking, doc y nghia thong ke va ghi test log cho ads, landing…

    609 GitHub stars~3.6k tokensUpdated 29 days ago
    Marketing & SEOAuto-check passed

  • Ab Test Architect

    LeoYeAI/openclaw-master-skills

    Plan, prioritize, and design rigorous A/B tests using the Test Velocity Method.

    2.2k GitHub stars~5k tokensUpdated 2 mo ago
    Marketing & SEOAuto-check passed

  • Afa Convert

    afadtc/afa-dtc-skills

    DTC 转化率优化——结账优化、弃单挽回、落地页、A/B测试、信任与无障碍。触发词: 转化率, CRO, 加购, 结账, 弃单, 落地页, A/B测试, 转化漏斗, conversion rate, abandoned cart, checkout optimization, landing page, a/b test, add to cart。复杂问题先经 afa。

    168 GitHub stars~2.3k tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed

  • Autoresearch

    ericosiu/ai-marketing-skills

    Run Karpathy-style autoresearch optimization on any content.

    3.6k GitHub starsUsed in 2 repos~2.2k tokens
    Marketing & SEOAuto-check passed

  • Landing Optimizer

    aaron-he-zhu/aaron-marketing-skills

    A skill your agent uses when the user asks to "optimize our landing page for influencer traffic", "fix our promo-code landing page", or "improve conversion from a creator campaign"; produces a…

    2.9k GitHub stars~3.3k tokensUpdated today
    Marketing & SEOAuto-check passed

More from growthack88/growth-marketing-os

All 14 skills in this repo

  • Mena Ads

    growthack88/growth-marketing-os

    MENA Ads Command Center — a complete paid-ads operating system for the Arab world (Egypt, KSA, UAE, GCC, Levant, North Africa) and global accounts.

    116 GitHub stars~2.5k tokensUpdated today
    Auto-check passed

  • Arabic Copy Localizer

    growthack88/growth-marketing-os

    Marketing copy localization skill that converts English marketing copy (ads, landing pages, emails, CTAs) into native Egyptian Arabic عامية — or GCC dialect on request — with natural English…

    116 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Benchmark Analyst

    growthack88/growth-marketing-os

    Marketing benchmark triage skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Cod Operations Analyst

    growthack88/growth-marketing-os

    COD (cash-on-delivery) e-commerce operations skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Conversion Copywriter

    growthack88/growth-marketing-os

    Direct-response copywriting skill. An agent skill from growthack88/growth-marketing-os.

    116 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Funnel Decomposition Analyst

    growthack88/growth-marketing-os

    Senior performance analyst skill that answers "why did sales drop (or jump)?" using rigorous funnel decomposition.

    116 GitHub stars~861 tokensUpdated today
    Auto-check passed

Categories

Questions about Experiment Coach

What does Experiment Coach do?

Experiment Coach — validates ideas before launch and runs growth experiments after it, from inside the chat. Experiment Coach is an agent skill from growthack88/growth-marketing-os. Experiment Coach — validates ideas before launch and runs growth experiments after it, from inside the chat.

When should I use Experiment Coach?

Experiment Coach fits situations like: someone wants to test an idea; channel before building; get real market feedback; plan customer interviews.

How do I install Experiment Coach in Claude Code?

Run `npx skills add growthack88/growth-marketing-os --skill experiment-coach -a claude-code`. Or copy the skill folder (skills/experiment-coach in growthack88/growth-marketing-os) into .claude/skills/experiment-coach in your project. Claude Code loads it when a task matches its description.

How do I install Experiment Coach in Codex?

Run `npx skills add growthack88/growth-marketing-os --skill experiment-coach -a codex`. Or copy the skill folder (skills/experiment-coach in growthack88/growth-marketing-os) into .agents/skills/experiment-coach in your project. Codex loads it when a task matches its description.

Can I use Experiment Coach in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add growthack88/growth-marketing-os --skill experiment-coach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/experiment-coach, .gemini/skills/experiment-coach, .github/skills/experiment-coach and .opencode/skills/experiment-coach in your project.

What does Experiment Coach need to run?

Going by SKILL.md and its folder, Experiment Coach needs a shell and Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; A Bash shell.

Does Experiment Coach access the network?

SKILL.md names 1 domain. As links in the text: mahmoudomar.com. This is read from the text; nothing was executed.

Is Experiment Coach safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Experiment Coach use?

Experiment Coach is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Experiment Coach use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 10k tokens, read only when the agent opens those files.

What are the alternatives to Experiment Coach?

Skills that share tags, products or a category with Experiment Coach: Ab Test Setup And Analysis (irinabuht12-oss/marketing-skills, 4.1k stars), 19 Ab Test Setup (minhnv0807/ai-business-skills, 609 stars), Ab Test Architect (LeoYeAI/openclaw-master-skills, 2.2k stars) and Afa Convert (afadtc/afa-dtc-skills, 168 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Experiment Coach?

growthack88 (a GitHub user) maintains it in growthack88/growth-marketing-os, which has 116 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 10, 2026.

Source: growthack88/growth-marketing-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.