Skills by risk · page 74
Highest-trust agent skills
9,826 skills rated SAFE with grade A or B, best score first. All are grade B today: grade A needs a sandboxed run we do not do for skills yet. Ties are broken by stars, so a repository with many skills can fill a page.
Cite
Cite this page
ModelsAtlas. “Highest-trust agent skills”. Retrieved 30 Oct 2026. https://modelsatlas.com/skills/trusted/page/74
Donchitos/Claude-Code-Game-Studios
Audit assets against naming conventions, file size budgets, format standards. Finds orphaned assets, missing references.
Donchitos/Claude-Code-Game-Studios
Per-asset visual specs plus AI generation prompts from GDDs and character profiles. After the art bible.
Donchitos/Claude-Code-Game-Studios
Guided concept ideation using professional studio techniques, player psychology, creative exploration.
Donchitos/Claude-Code-Game-Studios
Structured bug report from a description, or analyze code for potential bugs. Reproduction steps, severity.
Donchitos/Claude-Code-Game-Studios
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.
Donchitos/Claude-Code-Game-Studios
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
Donchitos/Claude-Code-Game-Studios
Architectural code review — coding standards, SOLID, testability, performance concerns.
Donchitos/Claude-Code-Game-Studios
Scan GDDs against the entity registry for cross-document conflicts. Grep-first approach targets conflicting sections, different stats.
Donchitos/Claude-Code-Game-Studios
Audit GDD content counts against what's implemented — planned vs built.
Donchitos/Claude-Code-Game-Studios
Author the architecture blueprint before code is written. Validates decisions against the pinned engine, flags knowledge gaps.
Donchitos/Claude-Code-Game-Studios
Flat must-do/never-do rules sheet per system and layer, extracted from Accepted ADRs. ADRs explain why; this is actionable.
Donchitos/Claude-Code-Game-Studios
Turn GDDs plus architecture into epics — one per architectural module, with untraced requirements. Then /create-stories [epic-slug].
Donchitos/Claude-Code-Game-Studios
Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria. Reads the control manifest. After /create-epics.
Donchitos/Claude-Code-Game-Studios
Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.
Donchitos/Claude-Code-Game-Studios
Reviews one design document for completeness, internal consistency, implementability, and design standards. Before handing to programmers.
Donchitos/Claude-Code-Game-Studios
Section-by-section GDD authoring for one system — walks through each required section, cross-references dependencies.
Donchitos/Claude-Code-Game-Studios
Implement a story: ADR guidelines, right programmer agent, code plus test. Then /story-done (/story-readiness before, /code-review after, at standard/full).
Donchitos/Claude-Code-Game-Studios
Estimate task effort from complexity, dependencies, velocity, risk. Structured estimate with confidence levels.
Donchitos/Claude-Code-Game-Studios
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Donchitos/Claude-Code-Game-Studios
Ready to advance between development phases? PASS/CONCERNS/NOT ASSESSED/FAIL with blockers and required artifacts. 'Can we move to production?'
Donchitos/Claude-Code-Game-Studios
What should I do next? Use when stuck or you don't know what to do.
Donchitos/Claude-Code-Game-Studios
Emergency fix bypassing normal sprint process — hotfix branch, approvals tracked, backport verified, full audit trail.
Donchitos/Claude-Code-Game-Studios
Launch readiness across every department: code, content, store, marketing, community, infrastructure, legal, go/no-go sign-offs.
Donchitos/Claude-Code-Game-Studios
Localization pipeline — find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze.