steam-freebies
Skill2 starsChanged 7 days agoMITView on GitHub
Find new Steam free-to-keep games, DLC and third-party Steam key giveaways, then prepare a batch announcement. Use for a scheduled giveaway digest or a request to check current Steam freebies.
In this repositoryOne other file it gives its agents.
- read-the-roomSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Put offers ending within 24 hours first and flag their urgency.
- Distinctive: line 33
Use no opening or closing filler.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 freebies
Requires Node.js 20+ with network access. Run the bundled script relative to this skill's directory:
node bin/check.mjsOptions: --state <dir> selects persistent state outside the skill folder (default: $XDG_STATE_HOME/steam-freebies, or ~/.local/state/steam-freebies). --cc <country> defaults to tw; --lang <language> defaults to tchinese. These apply to every Steam request and link. Use the same state directory for checks and commits. The script keeps seen.json and one overwritten pending.json; seen offers expire after 30 days without appearing again.
Read the result
new: offers not announced before. Sources are Steam store 100% discounts and GamerPower Steam key giveaways; matching third-party titles are suppressed when the store has the same offer.already_pushed_still_active: count of active entries omitted fromnew, including same-title duplicates.errors: source or individual-item fetch failures. Report available new offers even if another source fails. Ifnewis empty, stay quiet unless both sources failed and no usable data could be fetched; then briefly report the failure.
Prepare one message per batch
Put offers ending within 24 hours first and flag their urgency. ends is already formatted in Taiwan time (Asia/Taipei); state that timezone, and treat a missing deadline or price as unknown.
For each item include:
- Title, game or DLC, base game for DLC, original price (
worth) and deadline (ends). - Two or three natural sentences in Taiwan Traditional Chinese about the genre, gameplay and distinctive features, using
introandgenres, orgp_descriptionwhen no intro is available. Explain the base game before describing DLC. Paraphrase rather than copying or translating word for word. - Claim instructions: Steam store offers are claimed directly on the store and kept permanently. Third-party offers require obtaining a key on another site and redeeming it on Steam; summarize
how_to_claim, including newsletter, points or other conditions. - Claim URL (
url); also includesteam_urlfor a third-party offer when available.
Use no opening or closing filler. Once the batch announcement is drafted and selected for delivery, before emitting the final reply, mark that pending batch as announced:
node bin/check.mjs --commitRepeat any custom --state argument. This returns { "committed": <count> } and clears the pending batch; it does not fetch offers. Commit only the batch being announced, and avoid another check between drafting and committing because it replaces pending.json. If commit fails, report the failure; a later run may repeat the offers.
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.

