steam-page-wishlist
Skill1 starsChanged 2 days agoMITView on GitHub
Plans a Steam release and grows wishlists - Coming Soon page timing, store page audit (capsule art, tags, description, screenshots, trailer), demo and Next Fest strategy, Personal Calendar, festivals and mailing list. Includes a script that checks capsule image sizes. Use when the user mentions Steam, wishlists, a Steam store page, capsule art, Next Fest, a demo, or asks "how do I launch on Steam" or "làm trang Steam".
In this repository5 other files it gives its agents.
- ai-disclosureSkill
- community-launcherSkill
- game-contextSkill
- hook-finderSkill
- platform-pickerSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Read .agents/game-context.md (run game-context first if missing).
- Distinctive: line 18
No Steamworks account yet → *Timeline*
- Very specific: line 21
Use references/steam.md for every number.
- Distinctive: line 64
Never promise a wishlist number or revenue.
- Distinctive: line 66
Don't advise buying wishlists, review manipulation, or keys-for-reviews.
- Very specific: line 67
If a requested fact is not in references/steam.md, say so and point to the Steamworks documentation.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Steam Page & Wishlists
On Steam, wishlists gathered before launch decide how much the store shows a game. This skill gets the page up early, makes it read clearly as its genre, and plans how wishlists will grow month by month.
Language
Answer in the user's language. Store page copy is written in English first (Steam's largest audience), then in other languages the game supports.
Workflow
- Read
.agents/game-context.md(rungame-contextfirst if missing). You need genre, comparable games, state, AI usage. - Figure out where the user is and jump to the matching section:
- No Steamworks account yet → Timeline
- Page exists → Store page audit
- Page live, planning launch → Wishlist plan and Next Fest & demo
- Use
references/steam.mdfor every number. Show itslast_checkeddate and remind the user that Valve changes rules; link the official Steamworks page for anything binding. - End with a dated action list (this week / this month / before launch).
Timeline (work backwards from the launch date)
- Steam Direct fee and paperwork first; tax/identity checks and a waiting period after paying the fee take weeks.
- Submit the store page for review well before you want it public (plan at least 7 business days).
- Coming Soon page: public at least 2 weeks before release is the minimum; aim for months. Recommend going public as soon as there are 5+ good screenshots and a short trailer.
- Pick a release date about 2 months out and keep it, so the game can appear in players' Personal Calendar for the full window.
- Never shadow drop (release with no page and no lead time).
Store page audit
Score each item ✅ / ⚠️ / ❌ and give one concrete fix per ⚠️/❌:
- Capsule art reads at thumbnail size: title legible at the small capsule's tiny auto-generated size; art says the genre instantly; no text beyond the game's title. Run
scripts/check_capsules.pyon the asset folder to verify exact sizes. - Genre clarity: a stranger can name the genre in 3 seconds from the capsule plus first screenshot. Store recommendations are increasingly personalized, so looking like the genre matters more than looking unique.
- Tags: the top tags are the most specific, accurate genre/feature tags (e.g. "Farming Sim", "Cozy", "First-Person", "Relaxing"), not broad ones like "Indie" or "Casual" first.
- Short description: one sentence with the player's verb and the hook, no vague claims ("unique", "immersive").
- First screenshots / GIF: gameplay, not menus or logos; the first one shows the core loop.
- Trailer: gameplay in the first seconds (reuse
hook-finderclips). - Long description: short paragraphs, animated GIFs of features, bullet list of what you do.
- AI disclosure filled in truthfully (use
ai-disclosure). Flag AI-generated capsule art as the highest backlash risk.
Wishlist plan
Build a month-by-month table from now until launch + 1 month:
| Month | Push | Channel | Expected effect |
Typical pushes: Coming Soon announcement, short-video series (hook-finder), community posts (community-launcher), a festival entry, demo release, Next Fest, creator outreach, launch-date announcement ~2 months out. Use the benchmark ranges in references/steam.md and say clearly that results vary widely.
Also recommend a mailing list or Discord from day one: Steam's launch notification does not reach every wishlister.
Next Fest & demo
- A game can enter Next Fest once, so time it for when the demo is polished and the page already has wishlists. The strongest predictor of Next Fest results is wishlists before the fest.
- Demo: short (15–30 min), ends on a high point, has a wishlist call-to-action on the last screen.
- Release the demo early (before Next Fest) to gather feedback and wishlists.
Rules
- Never promise a wishlist number or revenue. Present benchmarks as ranges from named sources.
- Flag estimates (Personal Calendar thresholds, revenue figures) as estimates.
- Don't advise buying wishlists, review manipulation, or keys-for-reviews. These break Steam rules.
- If a requested fact is not in
references/steam.md, say so and point to the Steamworks documentation.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

