Skills by risk · page 300
Highest-trust agent skills
7,952 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 29 Oct 2026. https://modelsatlas.com/skills/trusted/page/300
Maggy
alinaqi/maggy
Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing.
Mnemos
alinaqi/maggy
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies
Model Routing
alinaqi/maggy
9-tier model routing system with cascading classifier fallback and result auto-evaluation
Polyphony
alinaqi/maggy
Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches
Ticket Craft
alinaqi/maggy
Create Jira/Asana/Linear tickets optimized for Claude Code execution - AI-native ticket writing
Visual Validation
alinaqi/maggy
Autonomous screenshot verification — captures, compares, and AI-evaluates UI changes for visual regressions
Uncommonroute Release
CommonstackAI/UncommonRoute
Use when publishing UncommonRoute. A release is only complete after all required steps are done: version sync, validation, GitHub push/tag/release, PyPI publish, and npm publish.
Distill
samuelfaj/distill
Get FAR MORE done with FAR FEWER tokens 🔥
Artifact Naming
chekusu/wanman
Naming conventions for artifact kind and path, ensuring data can be aggregated and analyzed
Artifact Quality
chekusu/wanman
Quality standards for structured deliverables, ensuring data is verifiable and traceable
Cross Validation
chekusu/wanman
CEO checks consistency of agent outputs during post-completion review
Research Methodology
chekusu/wanman
Methodology for market research and data collection, ensuring data quality and source traceability
Wanman Cli
chekusu/wanman
wanman CLI command reference — inter-agent communication, task management, artifact storage
Workspace Conventions
chekusu/wanman
File and output conventions for agent workspaces
Api
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Bugfix
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Deepseekapi
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Docstring
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Fastapi
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Golang
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Java
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Mybatis
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Office Docx
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻
Office Pptx
val1813/kwcode
一个能持续增强本地开源模型的cli,专门为本地部署模型优化的coding窗口。目前仍然处于mvp未能大规模测试和端到端跑通,欢迎指正🙏🏻🙏🏻🙏🏻