agentsclimarketplace

Product creation

Skill IrvanFza/product-ops/.agents/skills/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

Install
npx -y skills add IrvanFza/product-ops --skill product-creation

Assembled 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

#Stageproduct-ops modemarketingskills routed
1Ideationideatecustomer-research, marketing-ideas, marketing-psychology, free-tools
2Name & brandbrandcompetitor-profiling, customer-research, product-marketing, offers
3Business plan / pricingplanpricing, offers, revops
4Marketing plan / launchmarketproduct-marketing, marketing-plan, launch, content-strategy, seo-audit, ads
5Growth / operationsoperatereferrals, 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

StageTemplate → output
Brandtemplates/brand-guide.html → output/{slug}-brand-guide.pdf
Plantemplates/business-plan.html → output/{slug}-business-plan.pdf
Markettemplates/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 URLauto-pipeline
Wants to generate/refine an ideastage 1 → ideate
Wants naming / positioning / brandstage 2 → brand
Wants a business plan / pricingstage 3 → plan
Wants a marketing plan / launchstage 4 → market
Wants growth / regular operationsstage 5 → operate
Wants a pitch deck / one-pagerstage 4 (option)
Asks to evaluate one ideaevaluate
Asks to compare ideasevaluate (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, never modes/_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.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.