Skills by risk · page 73

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.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Highest-trust agent skills”. Retrieved 30 Oct 2026. https://modelsatlas.com/skills/trusted/page/73
9,826 SAFE skills · page 73 of 410 · ranked by trust score, then stars
Sprint Status✓SAFE B

Donchitos/Claude-Code-Game-Studios

Fast, concise sprint snapshot — burndown and emerging risks for situational awareness. 'How is the sprint going?'

★ 26kGitHub starsCoding & review
Start✓SAFE B

Donchitos/Claude-Code-Game-Studios

First-time onboarding — asks where you are, then guides you to the right workflow.

★ 26kGitHub starsCoding & review
Story Done✓SAFE B

Donchitos/Claude-Code-Game-Studios

End-of-story completion review — verifies each acceptance criterion, checks GDD/ADR deviations, prompts code review, updates status.

★ 26kGitHub starsCoding & review
Story Readiness✓SAFE B

Donchitos/Claude-Code-Game-Studios

Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.

★ 26kGitHub starsCoding & review
Team Audio✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the audio team — audio-director, sound-designer, technical-artist, gameplay-programmer — direction through implementation.

★ 26kGitHub starsCoding & review
Team Combat✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the combat team — game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, qa-tester — design through implement and validate.

★ 26kGitHub starsCoding & review
Team Level✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the level team — level-designer, narrative-director, world-builder, art-director, systems-designer, qa-tester — for complete area creation.

★ 26kGitHub starsCoding & review
Team Live Ops✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the live-ops team — live-ops-designer, economy-designer, analytics-engineer, community-manager, writer — for a season or live event.

★ 26kGitHub starsCoding & review
Team Narrative✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the narrative team — narrative-director, writer, world-builder, level-designer — for story, world lore, narrative-driven levels.

★ 26kGitHub starsCoding & review
Team Polish✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.

★ 26kGitHub starsCoding & review
Team Qa✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the QA team through a full testing cycle — qa-lead strategy and test plan, qa-tester case writing, execution, sign-off.

★ 26kGitHub starsCoding & review
Team Release✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.

★ 26kGitHub starsCoding & review
Team Ui✓SAFE B

Donchitos/Claude-Code-Game-Studios

Orchestrate the UI team through the UX pipeline — authoring, visual design, implementation, review, polish. Uses /ux-design, /ux-review, studio templates.

★ 26kGitHub starsCoding & review
Tech Debt✓SAFE B

Donchitos/Claude-Code-Game-Studios

Track, categorize and prioritize technical debt across the codebase — scans for debt indicators, maintains a register.

★ 26kGitHub starsCoding & review
Test Evidence Review✓SAFE B

Donchitos/Claude-Code-Game-Studios

Quality review of test files and evidence — goes beyond existence, evaluates assertion coverage. ADEQUATE/INCOMPLETE/MISSING/NOT ASSESSED per story.

★ 26kGitHub starsCoding & review
Test Flakiness✓SAFE B

Donchitos/Claude-Code-Game-Studios

Find flaky tests from CI logs — aggregates pass rates, spots intermittent failures, recommends quarantine. After multiple runs.

★ 26kGitHub starsCoding & review
Test Helpers✓SAFE B

Donchitos/Claude-Code-Game-Studios

Generate engine-specific test helper libraries — assertion utilities, factory functions, mocks in the engine's test folder. Reduces boilerplate.

★ 26kGitHub starsCoding & review
Test Setup✓SAFE B

Donchitos/Claude-Code-Game-Studios

Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.

★ 26kGitHub starsCoding & review
Ux Review✓SAFE B

Donchitos/Claude-Code-Game-Studios

Validate a UX spec, HUD design or pattern library — accessibility, GDD alignment, readiness. APPROVED / NOT ASSESSED / NEEDS REVISION / MAJOR REVISION NEEDED.

★ 26kGitHub starsCoding & review
Vertical Slice✓SAFE B

Donchitos/Claude-Code-Game-Studios

Pre-production validation — end-to-end build to confirm the full loop is achievable before committing to Production. After GDDs, architecture, UX specs.

★ 26kGitHub starsCoding & review
Adopt✓SAFE B

Donchitos/Claude-Code-Game-Studios

Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /project-stage-detect, checks compliance not existence.

★ 26kGitHub starsCoding & review
Architecture Decision✓SAFE B

Donchitos/Claude-Code-Game-Studios

Create an ADR documenting a technical decision: context, alternatives considered, consequences.

★ 26kGitHub starsCoding & review
Architecture Review✓SAFE B

Donchitos/Claude-Code-Game-Studios

Traceability matrix mapping GDD requirements to ADRs. Finds gaps, cross-ADR conflicts, engine compatibility. PASS/CONCERNS/NOT ASSESSED/FAIL.

★ 26kGitHub starsCoding & review
Art Bible✓SAFE B

Donchitos/Claude-Code-Game-Studios

Author the Art Bible — visual identity gating asset production. Run before /map-systems.

★ 26kGitHub starsCoding & review