Skills by risk · page 322

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.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Highest-trust agent skills”. Retrieved 29 Oct 2026. https://modelsatlas.com/skills/trusted/page/322
7,952 SAFE skills · page 322 of 332 · ranked by trust score, then stars

Store Policies

foxminchan/BookWorm

✓SAFE B

Answer questions about BookWorm bookstore policies, shipping, returns, account management, loyalty programs, gift cards, and other non-book-specific services. Use when customers ask about store operations or services.

★ 50689/100

Turborepo

foxminchan/BookWorm

✓SAFE B

Configure and troubleshoot Turborepo repositories. Use when working with turbo.json, task pipelines, caching, Remote Cache, the turbo CLI, filtering, environment variables, package boundaries, monorepo structure, or CI…

★ 50689/100

Vercel React Best Practices

foxminchan/BookWorm

✓SAFE B

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on…

★ 50689/100

operator-memory

aerovato/operator-memory

✓SAFE B

Build or refresh the Operator Project Index.

★ 42689/100

unifly

hyperb1iss/unifly

✓SAFE B

This skill should be used when the user asks to "manage UniFi devices", "configure UniFi networks", "create a VLAN", "provision an SSID", "create firewall rules", "reorder firewall policies", "create a NAT rule", "set…

★ 26889/100

Domain Authority Auditor

aaron-he-zhu/seo-geo-claude-skills

✓SAFE B

Signpost → the 16 SEO/GEO agent skills live in aaron-marketing-skills; this repo's standalone 20-skill line is preserved at tag v9.9.12. Install: npx skills add aaron-he-zhu/aaron-marketing-skills

★ 21589/100

Entity Optimizer

aaron-he-zhu/seo-geo-claude-skills

✓SAFE B

Signpost → the 16 SEO/GEO agent skills live in aaron-marketing-skills; this repo's standalone 20-skill line is preserved at tag v9.9.12. Install: npx skills add aaron-he-zhu/aaron-marketing-skills

★ 21589/100

deep-skill-finder

wheelry/deep-skill-finder

✓SAFE B

最好的找Skill的方式,能够基于你的任务,去寻找最匹配的高质量Skill。以下三种情况下都应使用本技能:1 用户主动要找 Skill,或者需要借助他人经验时——当用户说"找个 xxx 技能""股票分析别人怎么做的""找一找有没有现成的技能"等表达寻找意图时;2 Agent 自主判断需要外部 Skill 辅助——遇到不熟悉的任务,或对当前任务已经做过一些尝试仍无法解决、缺少合适工具时,可主动调用本技能查询实战经验并检索匹配的…

★ 17289/100

architecture-diagram-skill

konraddzbik/architecture-diagram-skill

✓SAFE B

Build interactive, click-through architecture diagrams for software systems — a self-contained single HTML file with animated step-by-step flows, mode toggles (dev/prod, offline/online, v1/v2), dark/light theme, and a…

★ 11589/100

marketing-skills

hyperfx-ai/marketing-skills

✓SAFE B

Generate on-brand ad creatives — visuals + copy — for Google, Meta (Facebook / Instagram), and other paid platforms via the Hyper MCP. Extracts brand identity from a website, writes ad copy variants, and produces…

★ 10289/100

awesome-weread

BENZEMA216/awesome-weread

✓SAFE B

微信读书读后感写作助手。帮助用户基于某本书或某个章节,生成一篇带有个人见解的读后感,正文严格控制原文摘抄,附录完整保留所有划线内容及即时感想。底层依赖 weread-skills(微信读书原子 API)和 huashu-weread-advisor(微信读书高阶顾问工作流)。当用户说「写一篇读后感」「帮我整理笔记写感想」「这本书/这章我想写篇公众号文章」时触发。

★ 6689/100

grounded-copy

HiroHyun/grounded-copy

✓SAFE B

Write clearly and get to the point. Use when writing, editing, translating, reviewing, or checking text people read, such as chat replies, documents, and product copy.

★ 2389/100

github-repository-bootstrap

egdev6/github-repository-bootstrap

✓SAFE B

Trigger: GitHub repository bootstrap, labels, milestones, issue templates, PR templates, Projects v2, project fields, project views. Plan and apply reusable repository bootstrap safely.

★ 2289/100

agent-graph

context4ai/agent-graph

✓SAFE B

Resolve a shared Agent Graph provider through the host registry.

★ 1689/100

ontology-driven-ai-data-management-skills

SuperChason/ontology-driven-ai-data-management-skills

✓SAFE B

用于需要把一个业务动作封装成Agent可调用工具、要设计动作执行前校验、重试和降级,用户出现“帮我定义Action契约”“这个动作失败后怎么办”或 action contract, pre-check, retry and fallback 等信号时调用。控制模式未定时可生成候选契约及模式选项,实际执行前落实授权与控制条件。

★ 1589/100

skills

magichourhq/skills

✓SAFE B

Inspect generated images, video and audio before delivery using deterministic metadata, contact-sheet, black-frame and silence checks plus visual and listening review. Use to accept, reject or repair Magic Hour media…

★ 1089/100

genpark-hub

alphaparkinc/genpark-hub

✓SAFE B

Runtime active hallucination interceptor and PII data leakage shield for GenPark & OpenClaw. Inspects planned tool calls in-flight, suppresses latent model hallucinations before execution, and redacts sensitive…

★ 989/100

claquete

dantaspaulo/claquete

✓SAFE B

Entry point for Claquete.ai, the video studio Claude operates. It reads the person's brand, asks in a single round for the video type, the duration, the audience and the format (landscape, vertical or both), hands the…

★ 889/100

context

context4ai/context

✓SAFE B

Use when the user explicitly invokes Context, asks to reorganize an existing Context knowledge map or website navigation, or continues a Context workflow to build, inspect, update, recover or package knowledge. Do not…

★ 889/100

drillr-mcp-server

Little-Grebe-Inc/drillr-mcp-server

✓SAFE B

drillr — the financial data and research MCP for AI agents: filings with full-text and fact search, statements as reported, earnings, ownership, corporate events, executives, analyst data, company discovery and research…

★ 889/100

KingdeeDataExporter

LittleBeaverStudio/KingdeeDataExporter

✓SAFE B

金蝶云星空经营数据导出技能。仅当用户明确要求从金蝶云星空或 K3 Cloud 查询、导出经营数据时使用;支持配置账号、自动发现账套、连接自检、查询组织与可用单据/报表,按期间、组织及单据或报表类型导出多工作表 Excel,也支持追加官方字段、全组织导出、字段核对与结果二次筛选。

★ 789/100

skills

Cogniac/skills

✓SAFE B

Query and manage the Cogniac computer vision platform. Use when working with Cogniac tenants, applications, subjects, media, EdgeFlow/CloudFlow appliances, cameras, deployments, or workflows — including uploading media,…

★ 789/100

awesome-hermes-agent-skills

frankxai/awesome-hermes-agent-skills

✓SAFE B

Use when orchestrating multiple coding agent CLIs (Claude Code, Codex, OpenCode, Grok CLI, Antigravity). Discovery, comparison, structured prompting, and multi-agent handoff patterns. Portable free pack — no…

★ 689/100

cognitive-perspective-check

EversiusJade/cognitive-perspective-check

✓SAFE B

Check user and AI assumptions to reduce premature cognitive narrowing in early project, design, and decision discussions. Understand pivotal background with few questions, compare materially different perspectives and…

★ 689/100