Menu
SkillsMP has collected 20 skills from KonH/GlobalStrategy. Open a skill to review its source and details.
Showing 20 of 20 collected skills.
Generate a milestone-completion report (summary.md, stats_code.md, stats_dev.md) under Docs/Milestones/<zero-padded-major>_<version-name>/, comparing code LoC and Docs/Specs/*/usage.csv dev stats against the previous milestone, then (with the user's sign-off)…
Merge the repo's default branch (main) into the current feature branch, auto-resolving the two known version-bump conflict spots (bundleVersion in ProjectSettings.asset, "version" in game_settings.json) and stopping to report anything else that needs manual…
Create a repository commit using GlobalStrategy's required workflow. Use when the user asks to commit staged or current changes in the GlobalStrategy repository.
Implement a plan via /implement for GlobalStrategy. When processing a GitHub issue/PR automation item, set ai-implement before starting; finish with ai-complete only.
Create a plan via /plan for GlobalStrategy. When processing a GitHub issue/PR automation item, set ai-plan before starting.
Capture feature intent via /specify for GlobalStrategy. When processing a GitHub issue/PR automation item, set ai-specify before starting.
Execute the repo owner's prompt from `codex`-labeled GitHub issues and PRs. Use when processing a `codex`-labeled item manually or from `scripts/automation/codex/handle_issues.py`.
Reference for scripts/automation/claude/handle_issues.py (and the codex/common equivalents) — the cron-driven, label-driven "execute the prompt from a GitHub issue/PR" automation. Load when working on, debugging, or extending that automation, or its…
Run the calibrate-end-game console-runner CLI verb to derive the end-game comparison score thresholds for Assets/Configs/game_settings.json's endGameComparisons, and to re-derive them when config or score rules change.
Build .NET solutions or projects from a repository root with captured output and clear compiler-error reporting. Use when the user asks to run, verify, or troubleshoot `dotnet build`, including Debug or Release builds.
Run and diagnose .NET tests from a repository root, including targeted test filters, captured output, and concise pass/fail reporting. Use when the user asks to run, verify, or troubleshoot `dotnet test` for a solution or project.
Generate character portraits and other art via the local ComfyUI + FLUX pipeline (scripts/utils/generate_image.py / generate_images_batch.py). Load when creating character portraits or other generated images for Assets/Textures.
Add new locale keys with real Russian translations instead of English placeholders — spawns a lightweight Haiku subagent to translate new en.asset entries into proper ru.asset entries. Load whenever adding, renaming, or changing user-facing text keys in…
Add or change an ICommand type so the Game.WebClient debug terminal keeps working with zero web-client code changes — mandates ParamSuggestionAttribute annotations on domain-id parameters and the matching provider for genuinely new id kinds.
Add or troubleshoot country flag and org image assets (Assets/Textures/Flags/Countries and Orgs) sourced from Wikimedia Commons, including the download_flags.py/check_flags.py/svg_to_png.py scripts and CountryVisualConfig/OrgVisualConfig wiring. Load when…
Finish a Ralph run by committing remaining work, opening or updating its pull request, then clearing the Ralph run artifacts in a separate follow-up commit.
Generate project-bound raster assets with this repository's local ComfyUI and FLUX setup. Use when asked to create game icons, character portraits, card art, map thumbnails, or other PNG assets that should be saved in the Unity project rather than merely…
Run the Game.Benchmarks harness (--compare/--update-baseline) from the project root without `cd`, logging output to a single file and checking exit code + a targeted grep instead of reading the full (very verbose) BenchmarkDotNet log.
Build a .NET solution from the project root without `cd`, logging output to a single file that gets read once instead of piped through repeated Bash calls.
Test a .NET solution from the project root without `cd`, logging output to a single file that gets read once instead of piped through repeated Bash calls.