Daily Game Opportunity Decisions with a 10-Step Checklist

Where this fits

Imagine you're an agent that wakes up every morning to decide which mini-game ideas deserve research, development, or a quiet pass. Instead of manually scanning search trends, keyword volumes, and competitor supply, you can now run a structured decision checklist. This skill turns that daily ritual into a repeatable, evidence-driven process that writes findings to .rankup/ for audit and review.

Why agents benefit

• Executes a 10-step checklist that forces you to verify data completeness, deduplicate keywords, and confirm playable supply before any conclusion.
• Queries global and per-country search volumes, KD (keyword difficulty), intent, and independent demand to produce a defensible recommendation.
• Automatically writes evidence to .rankup/ so every decision is traceable and comparable across days.
• Enforces a hard gate: unless the final ok flag is true, the agent must iterate and fix failing checks.
• Supports explicit "wait" conclusions, so the agent can deliberately choose inaction without feeling incomplete.

Practical scenarios

Morning market scan for a solo developer

Every day at 8 AM, your agent runs the checklist against fresh search data. It selects at most six real games for deep dive, checks their accessibility, and outputs a JSON + Markdown report. You review the conclusion before planning the day's build.

Filtering game ideas for a weekend jam

During a hackathon, you need to quickly decide which concept has low KD and high independent demand. The agent runs the checklist, marks D07 for playable supply, and rejects any game that fails the hard thresholds—saving you from wasted hours.

Monitoring trends for a small game studio

A studio uses the skill in a cron job to track shifts in search intent across countries. The evidence files allow you to spot regional demand changes and pivot research priorities without manual spreadsheet work.

Add it to your agent workflow

Install the skill directly:

npx skills add yan-labs/yan-skills --skill game-opportunity-decision

Then run the decision checklist at the root of your game opportunity repo:

node game-opportunity/scripts/game-opportunity.mjs decision-checklist

The skill will generate latest-decision-checklist.json and a Markdown report under .rankup/demand/game-review/. If a check fails, read game-opportunity/SKILL.md for guidance on fixing the missing evidence.

Compare before adopting

Before wiring this into your pipeline, evaluate it against alternatives. Check the quality of the evidence produced—does it actually include global and country-level search volumes, KD, and intent? Verify the freshness of the checklist methodology; a stale checklist can mislead your agent. Consider simpler scripts you might already have, and whether this 10-step rigor is worth the overhead. Finally, ensure the workflow fits your repo structure: the skill expects a specific .rankup/ layout.

Why it is worth tracking

With 128 stars and an active author (yan-labs), this skill shows real community interest in structured opportunity decisions. The strict ok gate and evidence-trail design make it easy to test and trust in a cron job. Check its GitHub for recent commits after you install it; if the author keeps refining the checklist against new market signals, it becomes a solid foundation for your daily agent routine. For a deeper look, see the skill page on OpenAgentSkill.