Product creation
Top-level orchestrator that routes a product from idea to operating business across 5 stages. For solo founders taking a product from ideation to growth: (1) Ideation, (2) Name & brand, (3) Business plan & pricing, (4) Marketing plan & launch, (5) Growth & operations. Each stage calls the relevant marketingskills (product-marketing foundation, customer-research, pricing, offers, launch, ab-testing, etc.) and invokes the matching product-ops mode (ideate, brand, plan, market, operate). product-marketing writes .agents/product-marketing.md, the shared context every later skill reads first. End-to-end flow in modes/auto-pipeline.md; scoring in modes/_shared.md. Local-first, human-in-the-loop — STOP before publish/spend/launch. No fabrication: keywords reformulated, never invented.From its SKILL.md
npx -y skills add IrvanFza/product-ops --skill product-creationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
5.0 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it
product-creation — product-creation orchestrator
product-creation is the top-level router/orchestrator that drives a new
product from idea to operating business. It is not a worker — it routes each
stage to the right marketingskills skills (under .agents/skills/) and
invokes the matching product-ops mode (in modes/). Read modes/_shared.md
first for the product-fit scoring system + Sources-of-Truth rule, and
modes/auto-pipeline.md for the full end-to-end flow (paste an idea or
competitor URL → research → evaluate → brand/plan PDFs → tracker).
The 5 stages
| # | Stage | product-ops mode | marketingskills routed |
|---|---|---|---|
| 1 | Ideation | ideate | customer-research, marketing-ideas, marketing-psychology, free-tools |
| 2 | Name & brand | brand | competitor-profiling, customer-research, product-marketing, offers |
| 3 | Business plan / pricing | plan | pricing, offers, revops |
| 4 | Marketing plan / launch | market | product-marketing, marketing-plan, launch, content-strategy, seo-audit, ads |
| 5 | Growth / operations | operate | referrals, free-tools, co-marketing, onboarding, signup, churn-prevention, analytics, ab-testing |
product-marketing is the foundation. It writes
.agents/product-marketing.md (product / audience / positioning), the shared
context every other stage reads first. If missing, create/update it in stage 2
(brand) before anything downstream runs.
Assessment loop (after the A–G evaluation, before/during plan):
feasibility (technical) → financials (cost / timeline / infrastructure) →
review (red-team Block I) → decision (GO/NO-GO/PIVOT verdict). validate
(customer proof) is opt-in to strengthen Block A; compliance gates launch.
Wired into auto-pipeline.md Steps 1b/1c/2b/2c + the Step 4 compliance gate.
Artifacts by stage
| Stage | Template → output |
|---|---|
| Brand | templates/brand-guide.html → output/{slug}-brand-guide.pdf |
| Plan | templates/business-plan.html → output/{slug}-business-plan.pdf |
| Market | templates/marketing-plan.html → output/{slug}-marketing-plan.pdf |
| Market (optional) | templates/pitch-deck.html, templates/one-pager.html → output/{slug}-{deck,one-pager}.pdf |
Render via generate-pdf.mjs (Playwright HTML→PDF, a4, printBackground: true).
Slash-menu
| If the user... | Route to |
|---|---|
| Pastes idea or competitor URL | auto-pipeline |
| Wants to generate/refine an idea | stage 1 → ideate |
| Wants naming / positioning / brand | stage 2 → brand |
| Wants a business plan / pricing | stage 3 → plan |
| Wants a marketing plan / launch | stage 4 → market |
| Wants growth / regular operations | stage 5 → operate |
| Wants a pitch deck / one-pager | stage 4 (option) |
| Asks to evaluate one idea | evaluate |
| Asks to compare ideas | evaluate (compare) |
| "Is it technically possible?" | feasibility |
| "How much / how big a server / timeline?" | financials |
| "Should I build this? Verdict?" | decision |
| "Pressure-test / review this eval" | review |
| "Validate demand with customers" | validate |
| "Is it compliant? (UU PDP / Ads ToS)" | compliance |
Critical rules
- No fabrication. Keywords reformulated, never invented. Claims cite a
Source-of-Truth file (
idea.md,config/product.yml,modes/_profile.md,.agents/product-marketing.md,proof-points.md,brand/*) or are flagged(assumed)/(unconfirmed). - Human-in-the-loop gates. Draft, evaluate, plan — but STOP before publish / spend / launch. The founder clicks. No auto-publish, no auto-spend.
- Discourage low fit. Score < 4.0 → recommend against building; < 3.5 skips PDF generation.
- Data contract. Never write user data into system files. Customization →
modes/_profile.md/config/product.yml, nevermodes/_shared.md. - Bounded research. No
deep-research, no subagents, stop at the query cap (modes/_shared.md).
product-creation orchestrates; the modes and marketingskills do the work.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most product growth skills give in ~1.1k tokens
Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07
- Read product marketing context before asking questionsin 24 of 728, across 18 files
- Define the ideal customer profilein 21 of 728, across 3 files
- Document a rollback plan before deploymentin 21 of 728, across 12 files
- Analyze the codebase to understand the productin 19 of 728, across 1 file
- Ask clarifying questions about the value propositionin 19 of 728, across 1 file
- Search for companies matching the criteriain 19 of 728, across 1 file
- Look for signals of immediate needin 19 of 728, across 1 file
- Assign a fit score from one to tenin 19 of 728, across 1 file
- Identify the target decision-maker rolein 19 of 728, across 1 file
- Suggest a personalized contact strategyin 19 of 728, across 1 file
- Provide conversation starters for outreachin 19 of 728, across 1 file
- Format results in a scannable markdown templatein 19 of 728, across 1 file
Said here and by no other author read
- invoke the matching mode for each stage
- run the assessment loop after evaluation
- generate PDFs from HTML templates
- recommend against building if score is low
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.