Skills by risk · page 75

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/75
9,826 SAFE skills · page 75 of 410 · ranked by trust score, then stars
Map Systems✓SAFE B

Donchitos/Claude-Code-Game-Studios

Decompose a concept into individual systems, map dependencies, prioritize design order, create the systems index.

★ 26kGitHub starsCoding & review
Milestone Review✓SAFE B

Donchitos/Claude-Code-Game-Studios

Milestone progress review — completeness, quality metrics, risk, go/no-go recommendation. At checkpoints or before a deadline.

★ 26kGitHub starsCoding & review
Onboard✓SAFE B

Donchitos/Claude-Code-Game-Studios

Onboarding doc for a new contributor or agent — project state, conventions, priorities relevant to the specified role.

★ 26kGitHub starsCoding & review
Patch Notes✓SAFE B

Donchitos/Claude-Code-Game-Studios

Player-facing patch notes from git history and changelogs. Translates developer language into player communication.

★ 26kGitHub starsCoding & review
Perf Profile✓SAFE B

Donchitos/Claude-Code-Game-Studios

Performance profiling — find bottlenecks, measure against budgets, produce ranked optimization recommendations.

★ 26kGitHub starsCoding & review
Playtest Report✓SAFE B

Donchitos/Claude-Code-Game-Studios

Structured playtest report template, or turn existing playtest notes into structured feedback.

★ 26kGitHub starsCoding & review
Project Stage Detect✓SAFE B

Donchitos/Claude-Code-Game-Studios

Analyze project state, detect stage, identify gaps, recommend next steps. 'Where are we in development?'

★ 26kGitHub starsCoding & review
Propagate Design Change✓SAFE B

Donchitos/Claude-Code-Game-Studios

A GDD changed — scan ADRs and the traceability index for now-stale architectural decisions. Impact report, guides resolution.

★ 26kGitHub starsCoding & review
Prototype✓SAFE B

Donchitos/Claude-Code-Game-Studios

Concept prototype before GDDs — throwaway HTML, Engine or Paper build, PROCEED/PIVOT/KILL/NOT ASSESSED. After /brainstorm and /setup-engine.

★ 26kGitHub starsCoding & review
Qa Plan✓SAFE B

Donchitos/Claude-Code-Game-Studios

QA test plan for a sprint — classifies stories by Logic/Integration/Visual/UI, covers automated tests, manual cases, smoke scope.

★ 26kGitHub starsCoding & review
Quick Design✓SAFE B

Donchitos/Claude-Code-Game-Studios

Lightweight spec for small changes — tuning adjustments, minor mechanics. Embeds directly into stories; skips full GDD.

★ 26kGitHub starsCoding & review
Regression Suite✓SAFE B

Donchitos/Claude-Code-Game-Studios

Map test coverage to GDD critical paths, find fixed bugs lacking regression tests, flag drift from new features.

★ 26kGitHub starsCoding & review
Release Checklist✓SAFE B

Donchitos/Claude-Code-Game-Studios

Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.

★ 26kGitHub starsCoding & review
Retrospective✓SAFE B

Donchitos/Claude-Code-Game-Studios

Sprint or milestone retrospective from completed work, velocity, blockers. Actionable insights for the next iteration.

★ 26kGitHub starsCoding & review
Reverse Document✓SAFE B

Donchitos/Claude-Code-Game-Studios

Generate missing design or architecture docs from existing implementation — works backwards from code and prototypes.

★ 26kGitHub starsCoding & review
Review All Gdds✓SAFE B

Donchitos/Claude-Code-Game-Studios

Holistic cross-GDD review — contradictions between systems, dominant strategies, economic imbalance, cognitive overload, pillar drift.

★ 26kGitHub starsCoding & review
Scope Check✓SAFE B

Donchitos/Claude-Code-Game-Studios

Scope creep check — current scope versus the original plan. Flags additions, quantifies bloat, recommends cuts. 'Any scope creep?'

★ 26kGitHub starsCoding & review
Security Audit✓SAFE B

Donchitos/Claude-Code-Game-Studios

Security audit — save tampering, cheat vectors, network exploits, data exposure, input validation. Before public or multiplayer release.

★ 26kGitHub starsCoding & review
Context Mode✓SAFE B

mksglu/context-mode

Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors",…

★ 26kGitHub stars
Ctx Doctor✓SAFE B

mksglu/context-mode

Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor

★ 26kGitHub stars
Ctx Insight✓SAFE B

mksglu/context-mode

Open the context-mode Insight dashboard in your default browser. Insight is the hosted analytics layer for AI-assisted engineering teams — per-engineer productive rate, retry waste, blocker detection, role-narrowed…

★ 26kGitHub stars
Ctx Purge✓SAFE B

mksglu/context-mode

Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge

★ 26kGitHub stars
Ctx Stats✓SAFE B

mksglu/context-mode

Show how much context window context-mode saved this session. Displays token consumption, context savings ratio, and per-tool breakdown. Read-only — shows stats only, no reset capability. To wipe the knowledge base…

★ 26kGitHub stars
Ctx Upgrade✓SAFE B

mksglu/context-mode

Update context-mode from GitHub and fix hooks/settings. Pulls latest, builds, installs, updates npm global, configures hooks. Trigger: /context-mode:ctx-upgrade

★ 26kGitHub stars