← Back to Skills Marketplace
leooooooow

Cold Start Path

by LeroyCreates · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
153
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install cold-start-path
Description
Choose the best first growth path for a new product, new shop, or weak early-stage offer based on product shape, margin room, content readiness, and channel...
README (SKILL.md)

Cold Start Path

Choose the first path before the team wastes time spreading effort everywhere.

Skill Card

  • Category: Growth Planning
  • Core problem: What should we try first for cold start?
  • Best for: New products, new stores, and stalled early-stage launches
  • Expected input: Product info + margin room + asset readiness + channel constraints
  • Expected output: First-path recommendation + why now + what to delay
  • Creatop handoff: Feed decision into first-week content, creator, and ad execution

Before you run

Ask the user to clarify:

  • product category
  • average selling price
  • margin room
  • whether the item is standard or non-standard
  • whether they have content assets already
  • whether they have creator access
  • whether they have ad budget
  • which channels are already live

If key facts are missing, ask for them before recommending a path.

Optional tools / APIs

Useful but not required:

  • store export
  • ad spend export
  • product sheet
  • search trend export
  • Google Sheets / CSV

If no tools are connected, continue with user-provided constraints and label the result as rule-based guidance.

Workflow

  1. Confirm cold-start scope.
  2. Classify the product by margin, complexity, and content-friendliness.
  3. Check readiness across five paths:
    • search
    • merchant content
    • creator content
    • paid ads
    • live selling
  4. Recommend the best first path.
  5. Name the second path to add later.
  6. Explicitly say what not to do yet.

Output format

Return in this order:

  1. Executive summary
  2. Best first path
  3. Why this path fits now
  4. What to delay
  5. First 7-day move list

Fallback mode

If the user only gives a rough product description:

  • infer the most likely first path from product type, margin, and asset readiness
  • mark assumptions clearly
  • avoid fake certainty

Quality rules

  • Do not recommend five paths at once.
  • Favor sequencing over complexity.
  • Match the path to actual constraints, not ideal conditions.
  • Say “not enough info” when the path depends on missing economics.

License

Copyright (c) 2026 Razestar.

This skill is provided under CC BY-NC-SA 4.0 for non-commercial use. You may reuse and adapt it with attribution to Razestar, and share derivatives under the same license.

Commercial use requires a separate paid commercial license from Razestar. No trademark rights are granted.

Usage Guidance
This skill is an instruction-only advisor and appears coherent and low-risk: it will not access your accounts or files unless you explicitly provide exports or connect tools. Before using it, (1) be prepared to answer the clarifying questions the skill asks; (2) avoid attaching full account credentials—if you share exports (store CSV, ad spend), sanitize or remove sensitive fields you don't want exposed; (3) note the license: CC BY-NC-SA 4.0 for non-commercial use and a separate paid license is required for commercial use; and (4) if you plan to connect live services, review and authorize those connections separately and only when necessary.
Capability Analysis
Type: OpenClaw Skill Name: cold-start-path Version: 1.0.0 The skill bundle is a growth strategy tool designed to guide an AI agent in recommending marketing paths for new products. It contains only metadata, markdown instructions (SKILL.md), and an output template (references/output-template.md). There is no executable code, no evidence of data exfiltration, and no malicious prompt injection; the instructions are strictly aligned with the stated purpose of business analysis.
Capability Assessment
✓ Purpose & Capability
The name and description (choose a first growth path for cold starts) match the SKILL.md: it asks for product/category, margin, content readiness, and channel constraints. There are no unrelated environment variables, binaries, or config paths requested.
ℹ Instruction Scope
The runtime instructions stay within the growth-planning scope (ask clarifying questions, classify product, check readiness across five paths, recommend first path, provide 7-day moves). It optionally refers to connecting exports (store export, ad spend, Google Sheets/CSV) which are relevant to the task; the skill appropriately says to proceed with rule-based guidance when no tools are connected. Recommend that users only supply or connect data they are comfortable sharing and sanitize sensitive fields before providing exports.
✓ Install Mechanism
No install spec and no code files beyond documentation — instruction-only. Nothing is downloaded or written to disk by the skill itself.
✓ Credentials
The skill declares no required environment variables or credentials. The optional tools listed (store exports, ad spend, sheets) are proportional to the purpose but would require user consent to provide; there is no automatic credential access requested.
✓ Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills. Autonomous invocation is allowed (platform default) but not combined with elevated privileges or credentials here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install cold-start-path
  3. After installation, invoke the skill by name or use /cold-start-path
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Add focused cold-start path skill with preflight questions and fallback guidance.
Metadata
Slug cold-start-path
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Cold Start Path?

Choose the best first growth path for a new product, new shop, or weak early-stage offer based on product shape, margin room, content readiness, and channel... It is an AI Agent Skill for Claude Code / OpenClaw, with 153 downloads so far.

How do I install Cold Start Path?

Run "/install cold-start-path" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Cold Start Path free?

Yes, Cold Start Path is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Cold Start Path support?

Cold Start Path is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Cold Start Path?

It is built and maintained by LeroyCreates (@leooooooow); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments