grow-business
Guided journey from a business with lucky months to a repeatable growth engine that produces a forecast. Orchestrates nine skills phase by phase - one-page-marketing, hundred-million-offers, predictable-revenue, contagious, influence-psychology, crossing-the-chasm, cold-start-problem, lean-analytics…
Install / Use
npx skills add wondelai/skills --skill grow-businessInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Data & AnalyticsSupported Platforms
Tags
Our assessment of grow-business
grow-business scores 87/100 on our quality scale, 395th of 606 Data & Analytics skills we index.
Its SKILL.md is 25 KB long, well organised into 18 sections and no code examples: a thorough specification that gives an agent plenty to work with.
With 2,248 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so grow-business is actively maintained.
- Our last check on 2026-11-02 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
grow-business compared with similar skills
All 4 of these similar skills score higher than grow-business; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| grow-business (this skill)by wondelai | 87 | 2.2k | 2mo ago | SKILL.md |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 149.0k | 6d ago | SKILL.md |
Frequently asked questions
- How do I install grow-business?
- Run
npx skills add wondelai/skills --skill grow-business. The install tabs above show the steps for each supported agent. - Which AI agents does grow-business work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is grow-business safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is grow-business still maintained?
- The repository was last updated about 2 months ago, so grow-business is actively maintained.
Skill content
View source on GitHubname: grow-business description: 'Guided journey from a business with lucky months to a repeatable growth engine that produces a forecast. Orchestrates nine skills phase by phase - one-page-marketing, hundred-million-offers, predictable-revenue, contagious, influence-psychology, crossing-the-chasm, cold-start-problem, lean-analytics, negotiation - asking the user questions at every decision point and recording results in the project docs/ folder (MARKETING.md, OFFER.md, METRICS.md, GROW-BUSINESS-PLAN.md) so the journey resumes across sessions. Use when the user wants to build a marketing and sales system, manufacture predictable pipeline, engineer word-of-mouth and referrals, or says ''revenue is real but lumpy and I need growth that repeats''. If the offer, retention, or operations underneath are broken, run improve-business first; with no paying customers yet, start with create-business; when the product itself must carry the growth loops, use grow-app. For one framework in isolation, invoke that skill directly.' license: MIT metadata: author: wondelai version: "1.0.1"
Grow a Business
You already have the hard part: a product people pay for. Revenue is real but lumpy — a good month came from a conference you happened to attend or a referral that happened to land, and none of it repeats on demand. This journey turns that traction into a repeatable growth engine across nine phases: a marketing map, an irresistible offer, an outbound motion, engineered word-of-mouth, persuasion on every surface, a mainstream go-to-market, a compounding network, one honest metric, and the discipline to hold price. It is interactive — the agent asks before every decision — and resumable, because every decision and asset is recorded in docs/. Install the whole stack at once with npx skills add wondelai/skills --all --global, or let each phase pull its skill on demand.
Core Principle
Build a repeatable growth engine: each phase produces an asset the next phase consumes — offer feeds pipeline, pipeline feeds word-of-mouth, metrics keep it honest. The order is load-bearing; a skipped Phase 1 leaves the later phases with no shared target. This skill sequences the phases, asks the decision questions, and records the answers. The constituent skills carry the method — invoke them rather than improvising their frameworks.
The offer comes before every channel on purpose: sending traffic to a weak offer is the most expensive mistake in growth, so Phase 2 is fixed before outbound, virality, or repositioning turn on.
Journey Map
| Phase | Skill | Question it answers | Artifact | |---|---|---|---| | 1 | one-page-marketing | Which niche, and which square of the machine is empty? | Creates docs/MARKETING.md | | 2 | hundred-million-offers | Why should they buy this instead of the alternative? | Extends docs/OFFER.md | | 3 | predictable-revenue | How do we manufacture pipeline on demand? | Extends docs/MARKETING.md | | 4 | contagious | Why would anyone share this? | Extends docs/MARKETING.md | | 5 | influence-psychology | Why do they say yes on the page? | Extends docs/OFFER.md | | 6 | crossing-the-chasm | How do we reach the mainstream buyer? | Extends docs/STRATEGY.md + docs/CUSTOMER.md | | 7 | cold-start-problem | How does the network do the acquiring? | Extends docs/MARKETING.md | | 8 | lean-analytics | Which one number tells us it is working? | Extends docs/METRICS.md | | 9 | negotiation | How do we capture the value instead of discounting it? | Extends docs/OFFER.md |
Four of the nine phases write to MARKETING.md — the flagship this journey creates. OFFER.md, STRATEGY.md, METRICS.md, and CUSTOMER.md are extended, so files a prior create-business journey already owns are reused and augmented, never overwritten.
The tracker docs/GROW-BUSINESS-PLAN.md is private to this journey and never shared with another; it is the resume point that carries state across sessions.
Operating Rules
- Resume first. Before anything else, read
docs/GROW-BUSINESS-PLAN.mdand every artifact in the Journey Map. If the tracker exists, summarize the journey state in 3-5 lines and ask which phase to enter. Done when the user has confirmed an entry point. A journey with a tracker is resumed, never restarted. - Intake on first run only. No tracker: run the Intake below, then create
docs/GROW-BUSINESS-PLAN.mdwith every phase statusedpending | in-progress | awaiting-evidence | done | deferred: reason | skipped: reason. Done when the tracker exists and the user has confirmed the phase plan. - Phase entry. Announce: what the phase does, the decision it forces, the artifact it produces, rough effort. Offer proceed / skip / defer — phases marked GATE may be deferred, never skipped. Mark the phase
in-progresson proceed. Done when the user chose. - Skill invocation and fallback. Load the phase's skill and use it: each phase's Invoke line names the skill by slug — use that skill to run the phase. If it is not available, offer:
npx skills add wondelai/skills/<slug> --global. If the user declines, run the phase from its Brief — the minimum viable method. State which mode you are in. - In-phase decisions. Ask every question under "Decide with the user" — with concrete options and your recommendation. Record the choice in the tracker's Key Decisions. A decision made silently is a defect.
- Phase exit. Present the draft artifact content for sign-off before writing. On approval: write or extend the docs/ files, update the tracker (status, Key Decisions, Next Actions). Done when the files are written and the phase row shows
done. - Artifact discipline. Read before writing; create a file only if missing, otherwise extend — add or update your sections, preserve everyone else's. Files are UPPERCASE in
docs/. Every recommendation lands as a checkbox or a table row with owner and priority. See references/artifact-templates.md when creating a docs/ file for the first time — create it from the full skeleton (all section headings), then fill the sections your phase names. - Every scarcity claim, testimonial, and guarantee must be true, and referral incentives must reward real value delivered. When a tactic needs inventing evidence, replace it with a tactic that uses evidence you have.
Intake
Ask these before creating the tracker:
- Current revenue, customer count, and what "lumpy" looks like month to month (baselines feed Phase 8; volume sizes the Phase 3 pipeline math).
- Where does new business come from today, and which single channel carries most of it (reveals the empty marketing square in Phase 1; over-reliance is your risk).
- Which segments could you focus on (feeds the Phase 1 PVP Index and the Phase 6 beachhead).
- Current offer and price — and was pricing ever tested against willingness to pay (gates Phase 2; if never tested, add the monetizing-innovation optional phase).
- Does the product get better as more people or teams use it — shared workspaces, referrals, a directory (gates Phase 7; skip it if there is no network dimension).
- Existing
docs/artifacts from a prior journey — CUSTOMER.md, POSITIONING.md, STRATEGY.md — to read and reuse (avoids re-deriving; sets extend vs create). - The single most painful growth constraint right now (lets you reorder — if the offer is the constraint, lead with Phase 2).
Skip heuristics: skip Phase 3 when the motion is pure self-serve and no sales-assisted motion is wanted; skip Phase 6 when you already sell to the mainstream pragmatist majority; skip Phase 7 when the product has no multiplayer or network dimension; skip Phase 9 when pricing is fixed self-serve checkout with no negotiated deals.
Then create docs/GROW-BUSINESS-PLAN.md from the template and confirm the plan. Done when docs/GROW-BUSINESS-PLAN.md exists with every phase statused and the user has confirmed the plan.
Phases
Run the phases in order unless intake reordered them. Each phase's Invoke reads what earlier phases wrote to docs/; if an upstream phase was skipped, its reader falls back to the intake facts and flags the missing input rather than inventing it.
Phase 1 — Install the marketing operating system (one-page-marketing)
Purpose: Lay out the whole marketing machine on one page so the missing square is visible before spending on any tactic.
Brief (fallback): A 3x3 grid across the customer journey — Before (target market, message, media), During (capture leads, nurture, convert), After (deliver the experience, increase lifetime value, orchestrate referrals). Marketing is a process, not an event; random tactics fail because they fill one square while eight stay empty. Score 0-10 on how completely and specifically all nine are filled. Run the PVP Index (Personal fulfillment, Value to market, Profitability) to pick one niche to dominate.
Invoke: Use the one-page-marketing skill with the intake facts (revenue, customers, current channels, candidate segments). Ask for (a) all nine squares filled and scored out of 10 with the single weakest square plus three fixes, and (b) a PVP Index across the candidate segments recommending one niche and writing its avatar.
Decide with the user: Which niche to dominate first (the PVP winner — this becomes the Phase 6 beachhead candidate)? Which weakest square to attack first? Confirm the avatar is one named persona, not "everyone".
Artifact: Create docs/MARKETING.md with ## Target Market & Avatar (PVP niche + avatar), ## Before / During / After Grid (phase | square | current state | plan), and ## Channels. Update the tracker.
Done when: MARKETING.md exists, the grid is filled and scored, the PVP niche and avatar are recorded, and the user chose the niche and the weakest square.
Phase 2 — Make the offer impossible to refuse (hundred-million-offers)
Purpose: Turn the core product into a Grand Slam Offer so conversion stops being a fight before any traffic is turned on.
Brief (fallback): Value = (Dream Outcome x Perceived Likelihood) / (Time Delay x Effort and Sacrifice) — maximize the top, minimize the bottom. Assemble core product + named bonuses that each kill one objection + a risk-reversing guarantee + ethical (real) scarcity, until the stack dwarfs the price. Name it with MAGIC (Magnetic reason, Avatar, Goal, time Indicator, Container). Premium pricing attracts committed customers who churn less.
Invoke: Use the hundred-million-offers skill with the current offer and price from intake (and docs/OFFER.md if it exists). Ask for a score out of 10, the weakest Value-Equation lever, three objection-killing bonuses with defensible dollar values, a guarantee type, and a MAGIC name.
Decide with the user: Is "too expensive" a price problem or a value-construction problem? Raise the price and add a done-for-you bonus, or hold? Which three bonuses ship?
Artifact: Create or extend docs/OFFER.md: ## Offer Stack (element | description | honest value | objection it kills) and ## Price Metric. Update the tracker.
Done when: OFFER.md holds a scored Grand Slam Offer with named bonuses, a guarantee, real scarcity, and a MAGIC name, and the pricing decision is recorded.
Phase 3 — Manufacture pipeline with outbound (predictable-revenue)
Purpose: Build a sales motion you can throttle — turn up to make deals, turn down to pause — instead of waiting for luck.
Brief (fallback): Lead types: Seeds (referrals — highest conversion, slow to build), Nets (inbound — medium), Spears (outbound — predictable, you control volume). Most under-invest in Spears. Specialize roles: SDRs prospect, AEs close, CSMs retain — never the same person prospecting and closing. Cold Calling 2.0: email above the decision-maker for a referral in, no pitch; response runs 9-15% vs 1-3%. Qualify with ANUM (Authority, Need, Urgency, Money). Run pipeline math backward from the revenue goal.
**Invoke
Truncated for display — read the full file on GitHub.
Related Skills
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
149.0kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
