Updated today
by HYClub
deepseek-harness-game-studios
DeepSeek Harness port of Claude Code Game Studios (CCGS v1.1.2, MIT) — 83 skills, 49 agents, 14 rules, 19 hooks, studio status line, self-installing payload, and a playable one-shot pipeline.
22 GitHub stars (22)
+12 in 8 days
| Period | New stars |
|---|---|
| Nov 4 | 0 |
| Nov 5 | +2 |
| Nov 6 | 0 |
| Nov 7 | +4 |
| Nov 8 | 0 |
| Nov 9 | +2 |
| Nov 10 | +1 |
| Nov 11 | +3 |
- 30 skills (30 skills found in its SKILL.md files)
- 0 forks (0 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add HYClub/deepseek-harness-game-studios
Asks which skills and agents to install. Just one: npx skills add HYClub/deepseek-harness-game-studios --skill adopt — add -g for every project.
Claude Code
git clone https://github.com/HYClub/deepseek-harness-game-studioscp -r "deepseek-harness-game-studios/payload/.claude/skills/adopt" ~/.claude/skills/
Copies the adopt skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add HYClub/deepseek-harness-game-studios
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 158 files.
-
adopt
Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /project-stage-detect, checks compliance not existence.
payload/.claude/ on GitHub (opens in a new tab)skills/ adopt/ SKILL.md -
architecture-decision
Create an ADR documenting a technical decision: context, alternatives considered, consequences.
payload/.claude/ on GitHub (opens in a new tab)skills/ architecture-decision/ SKILL.md -
architecture-review
Traceability matrix mapping GDD requirements to ADRs. Finds gaps, cross-ADR conflicts, engine compatibility. PASS/CONCERNS/NOT ASSESSED/FAIL.
payload/.claude/ on GitHub (opens in a new tab)skills/ architecture-review/ SKILL.md -
art-bible
Author the Art Bible — visual identity gating asset production. Run before /map-systems.
payload/.claude/ on GitHub (opens in a new tab)skills/ art-bible/ SKILL.md -
asset-audit
Audit assets against naming conventions, file size budgets, format standards. Finds orphaned assets, missing references.
payload/.claude/ on GitHub (opens in a new tab)skills/ asset-audit/ SKILL.md -
asset-spec
Per-asset visual specs plus AI generation prompts from GDDs and character profiles. After the art bible.
payload/.claude/ on GitHub (opens in a new tab)skills/ asset-spec/ SKILL.md -
balance-check
Find balance outliers, broken progressions, degenerate strategies, economy imbalances in formulas and data. 'Check game balance'.
payload/.claude/ on GitHub (opens in a new tab)skills/ balance-check/ SKILL.md -
brainstorm
Guided concept ideation using professional studio techniques, player psychology, creative exploration.
payload/.claude/ on GitHub (opens in a new tab)skills/ brainstorm/ SKILL.md -
bug-report
Structured bug report from a description, or analyze code for potential bugs. Reproduction steps, severity.
payload/.claude/ on GitHub (opens in a new tab)skills/ bug-report/ SKILL.md -
bug-triage
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.
payload/.claude/ on GitHub (opens in a new tab)skills/ bug-triage/ SKILL.md -
changelog
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
payload/.claude/ on GitHub (opens in a new tab)skills/ changelog/ SKILL.md -
code-review
Architectural code review — coding standards, SOLID, testability, performance concerns.
payload/.claude/ on GitHub (opens in a new tab)skills/ code-review/ SKILL.md -
consistency-check
Scan GDDs against the entity registry for cross-document conflicts. Grep-first approach targets conflicting sections, different stats.
payload/.claude/ on GitHub (opens in a new tab)skills/ consistency-check/ SKILL.md -
content-audit
Audit GDD content counts against what's implemented — planned vs built.
payload/.claude/ on GitHub (opens in a new tab)skills/ content-audit/ SKILL.md -
create-architecture
Author the architecture blueprint before code is written. Validates decisions against the pinned engine, flags knowledge gaps.
payload/.claude/ on GitHub (opens in a new tab)skills/ create-architecture/ SKILL.md -
create-control-manifest
Flat must-do/never-do rules sheet per system and layer, extracted from Accepted ADRs. ADRs explain why; this is actionable.
payload/.claude/ on GitHub (opens in a new tab)skills/ create-control-manifest/ SKILL.md -
create-epics
Turn GDDs plus architecture into epics — one per architectural module, with untraced requirements. Then /create-stories [epic-slug].
payload/.claude/ on GitHub (opens in a new tab)skills/ create-epics/ SKILL.md -
create-stories
Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria. Reads the control manifest. After /create-epics.
payload/.claude/ on GitHub (opens in a new tab)skills/ create-stories/ SKILL.md -
day-one-patch
Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.
payload/.claude/ on GitHub (opens in a new tab)skills/ day-one-patch/ SKILL.md -
design-review
Reviews one design document for completeness, internal consistency, implementability, and design standards. Before handing to programmers.
payload/.claude/ on GitHub (opens in a new tab)skills/ design-review/ SKILL.md -
design-system
Section-by-section GDD authoring for one system — walks through each required section, cross-references dependencies.
payload/.claude/ on GitHub (opens in a new tab)skills/ design-system/ SKILL.md -
dev-story
Implement a story: ADR guidelines, right programmer agent, code plus test. Then /story-done (/story-readiness before, /code-review after, at standard/full).
payload/.claude/ on GitHub (opens in a new tab)skills/ dev-story/ SKILL.md -
estimate
Estimate task effort from complexity, dependencies, velocity, risk. Structured estimate with confidence levels.
payload/.claude/ on GitHub (opens in a new tab)skills/ estimate/ SKILL.md -
gate-check
Ready to advance between development phases? PASS/CONCERNS/NOT ASSESSED/FAIL with blockers and required artifacts. 'Can we move to production?'
payload/.claude/ on GitHub (opens in a new tab)skills/ gate-check/ SKILL.md -
help
What should I do next? Use when stuck or you don't know what to do.
payload/.claude/ on GitHub (opens in a new tab)skills/ help/ SKILL.md -
hotfix
Emergency fix bypassing normal sprint process — hotfix branch, approvals tracked, backport verified, full audit trail.
payload/.claude/ on GitHub (opens in a new tab)skills/ hotfix/ SKILL.md -
launch-checklist
Launch readiness across every department: code, content, store, marketing, community, infrastructure, legal, go/no-go sign-offs.
payload/.claude/ on GitHub (opens in a new tab)skills/ launch-checklist/ SKILL.md -
localize
Localization pipeline — find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze.
payload/.claude/ on GitHub (opens in a new tab)skills/ localize/ SKILL.md -
map-systems
Decompose a concept into individual systems, map dependencies, prioritize design order, create the systems index.
payload/.claude/ on GitHub (opens in a new tab)skills/ map-systems/ SKILL.md -
milestone-review
Milestone progress review — completeness, quality metrics, risk, go/no-go recommendation. At checkpoints or before a deadline.
payload/.claude/ on GitHub (opens in a new tab)skills/ milestone-review/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.