Agent skill

Rgsm Gui Acceptance

by mcthesw in mcthesw/game-save-manager

Prepare change-specific RGSM GUI acceptance environments and short manual scenarios when the user wants to try a change locally.

AGPL-3.0Auto-check passed

Install Rgsm Gui Acceptance

skills CLI
$ npx skills add mcthesw/game-save-manager --skill rgsm-gui-acceptance -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mcthesw/game-save-manager rgsm-gui-acceptance --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mcthesw/game-save-manager.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/rgsm-gui-acceptance .claude/skills/rgsm-gui-acceptance && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
rgsm-gui-acceptance
GitHub stars
1.1k
Token cost
~1.1k tokens
SKILL.md length
583 words
Files
6 (incl. scripts, references, assets)
Skills in repo
2
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Prepare change-specific RGSM GUI acceptance environments and short manual scenarios when the user wants to try a change locally.

  • Wants to try a change locally
  • SKILL.md covers Select the scenarios, Prepare an isolated packet, Verify before handing over and Hand over and close
  • Runs JavaScript scripts from its folder

What it does

Rgsm Gui Acceptance is an agent skill from mcthesw/game-save-manager. Prepare change-specific RGSM GUI acceptance environments and short manual scenarios when the user wants to try a change locally. Uses isolated saves and the real Rust backend; not a mandatory gate for every PR or a replacement for automated tests.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/scenario.md` and `references/environment.md`).

It works with Rust, Vue.js, Tauri and TypeScript. The licence is AGPL-3.0.

When your agent uses it

  • Wants to try a change locally

Example prompts

  • “/rgsm-gui-acceptance”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit fe55cb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (JavaScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Rgsm Gui Acceptance loads about 1.1k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 583 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mcthesw/game-save-manager at commit fe55cb7, republished under its AGPL-3.0 licence (© mcthesw). 583 words, ~1,091 tokens.

Download SKILL.mdSave it as .claude/skills/rgsm-gui-acceptance/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
rgsm-gui-acceptance
description
Prepare change-specific RGSM GUI acceptance environments and short manual scenarios when the user wants to try a change locally. Uses isolated saves and the real Rust backend; not a mandatory gate for every PR or a replacement for automated tests.

RGSM GUI acceptance

Deliver working GUI links, a small set of numbered scenarios, and a clear way to stop the owned services. The user performs acceptance; preparing fixtures or passing an automated smoke is not their approval.

Select the scenarios

Read the relevant diff, current API, locale labels, and existing tests. Pin the tested revision, including any local combination of unmerged PRs. Preserve the user's checkout and other running environments.

Aim for at most five short scenarios unless the user asks for more. Cover the changed behavior and its next useful action: for example, retaining a local game after joining a library is incomplete coverage unless the user can subsequently enable its sync and transfer a snapshot.

Use real files or fixture generators for save state. Markdown describes that state and references its files; it does not serialize archives, registry data, or an execution graph. Start from the scenario card, adapting or removing fields that do not help this review.

Prepare an isolated packet

Put generated scenario code, data, logs, and evidence under .rgsm-dev/acceptance/<task>/. Reuse helpers under apps/rgsm-gui/e2e/support/, especially local-fixture.ts, cloud-fixture.ts, and process.ts, rather than copying product schemas. Use current APIs for subsequent mutations. Never seed real save paths or cloud credentials.

Choose the lightest environment that exercises the behavior:

  • For frontend/business flows, build the frontend once and use the real HTTP-only host. The thin device launcher serves the built GUI, injects runtime authentication, and owns one isolated host. It does not seed data, run scenarios, or rebuild on startup
  • For tray, hotkeys, window lifecycle, WebView, or installer changes, request or prepare the actual desktop environment instead; browser success cannot prove those behaviors
  • For cloud flows, use isolated local test storage. A mock WebDAV transport is suitable for join/metadata UX but does not prove remote provider compatibility

Read launcher usage before using the helper. Keep test-specific setup and controls local to the packet. Do not grow a YAML DSL, scenario registry, generic fault engine, or permanent fixture catalog from one acceptance request.

Do not open visible windows automatically. Respect existing ports and services. Limit concurrent builds/hosts, reuse valid build artifacts, and disable notifications and sounds in test configs. Keep cloud credentials, join codes, and API tokens out of console output and screenshots.

Show full SKILL.md (211 more words)Show less

Verify before handing over

Exercise the numbered operations in an owned browser context. Inspect current accessibility labels before choosing selectors. Wait for actual responses and refreshed state, not incidental sleeps. Check real save contents and effective configuration, not only success notifications.

For partial failures, show which user-visible outcome succeeded and which failed. A real isolated fault is preferable when safe and repeatable; disclose any mocked failure. Record unexpected behavior instead of hiding it behind an altered scenario.

Use a separate smoke dataset from the user dataset. Do not reset or modify an environment the user has started accepting without permission. Verify stop/restart behavior, distinguishing a device restart from recreating an ephemeral cloud fixture.

Hand over and close

Provide the entry links, numbered actions and expected results, tested revision, and any relevant known limits. Distinguish automated smoke, pending human acceptance, and untested platforms. A small landing page with state inspection is useful when file effects are otherwise hard to see, but is optional.

Keep the environment available until the user finishes or asks to stop. Closing a browser tab does not stop the host. Report exactly which owned services were stopped; only delete task data when requested, after validating the targets. Do not merge PRs or close issues merely because acceptance passed.

© mcthesw, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references, assets) in .agents/skills/rgsm-gui-acceptance of mcthesw/game-save-manager.

  • SKILL.md
  • agents/openai.yaml
  • assets/scenario.md
  • references/environment.md
  • scripts/device.mjs
  • scripts/device.test.mjs

Open the folder on GitHubat commit fe55cb7

Compare with similar skills

Rgsm Gui Acceptance next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Rgsm Gui Acceptance compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rgsm Gui Acceptance this skillmcthesw/game-save-manager1.1k—~1.1kAutomated safety check: PassAGPL-3.0
Tauri Config Ipcifer47/markeron1.2k—~1kAutomated safety check: PassMIT
Tv Remote UIventic/ventic174—~4.2kAutomated safety check: PassMIT
Add Tauri Commanddevlint/GitWand180—~1.5kAutomated safety check: PassMIT
Pnpm Engineteambit/bit18k—~1.9kAutomated safety check: PassCustom licence
Update TranslationsRaicuparta/rai-pal735—~839Automated safety check: PassGPL-3.0

Similar skills

  • Tauri Config Ipc

    ifer47/markeron

    Extend MarkerOn settings, persisted config, or Tauri IPC commands.

    1.2k GitHub stars~1k tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Tv Remote UI

    ventic/ventic

    How this app stays usable from a TV remote (Android TV / Google TV).

    174 GitHub stars~4.2k tokensUpdated 6 days ago
    Frontend & DesignAuto-check passed
  • Add Tauri Command

    devlint/GitWand

    A skill your agent uses when the user wants to expose a Rust feature to the Vue frontend, add a Tauri IPC command, invoke something from a Vue component, or wire up any backend/frontend…

    180 GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Pnpm Engine

    teambit/bit

    Work on the pnpm Rust engine (@pnpm/napi, the pacquet crates) that bit install runs through.

    18k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Update Translations

    Raicuparta/rai-pal

    A skill your agent uses when asked to update translations, localize strings, add new languages, fix missing translation keys, or sync language files in this project.

    735 GitHub stars~839 tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Cross-platform UI styling for MarkerOn Tauri app (macOS WKWebView vs Windows WebView2).

    1.2k GitHub stars~2k tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed

More from mcthesw/game-save-manager

  • Rgsm Gui Debug

    mcthesw/game-save-manager

    Debug the RGSM frontend against the real Rust backend in a normal browser, without Tauri IPC or WebView tooling.

    1.1k GitHub stars~267 tokensUpdated today
    Auto-check passed

Questions about Rgsm Gui Acceptance

What does Rgsm Gui Acceptance do?

Prepare change-specific RGSM GUI acceptance environments and short manual scenarios when the user wants to try a change locally. Rgsm Gui Acceptance is an agent skill from mcthesw/game-save-manager. Prepare change-specific RGSM GUI acceptance environments and short manual scenarios when the user wants to try a change locally.

When should I use Rgsm Gui Acceptance?

Rgsm Gui Acceptance fits situations like: wants to try a change locally.

How do I install Rgsm Gui Acceptance in Claude Code?

Run `npx skills add mcthesw/game-save-manager --skill rgsm-gui-acceptance -a claude-code`. Or copy the skill folder (.agents/skills/rgsm-gui-acceptance in mcthesw/game-save-manager) into .claude/skills/rgsm-gui-acceptance in your project. Claude Code loads it when a task matches its description.

How do I install Rgsm Gui Acceptance in Codex?

Run `npx skills add mcthesw/game-save-manager --skill rgsm-gui-acceptance -a codex`. Or copy the skill folder (.agents/skills/rgsm-gui-acceptance in mcthesw/game-save-manager) into .agents/skills/rgsm-gui-acceptance in your project. Codex loads it when a task matches its description.

Can I use Rgsm Gui Acceptance in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mcthesw/game-save-manager --skill rgsm-gui-acceptance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rgsm-gui-acceptance, .gemini/skills/rgsm-gui-acceptance, .github/skills/rgsm-gui-acceptance and .opencode/skills/rgsm-gui-acceptance in your project.

What does Rgsm Gui Acceptance need to run?

Going by SKILL.md and its folder, Rgsm Gui Acceptance needs JavaScript for the scripts in its folder. Our summary lists: Node.js.

Does Rgsm Gui Acceptance access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Rgsm Gui Acceptance safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Rgsm Gui Acceptance use?

Rgsm Gui Acceptance is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Rgsm Gui Acceptance use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 716 tokens, read only when the agent opens those files.

What are the alternatives to Rgsm Gui Acceptance?

Skills that share tags, products or a category with Rgsm Gui Acceptance: Tauri Config Ipc (ifer47/markeron, 1.2k stars), Tv Remote UI (ventic/ventic, 174 stars), Add Tauri Command (devlint/GitWand, 180 stars) and Pnpm Engine (teambit/bit, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rgsm Gui Acceptance?

mcthesw (a GitHub user) maintains it in mcthesw/game-save-manager, which has 1,147 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 10, 2026.

Source: mcthesw/game-save-manager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.