Skills by risk · page 401
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/401
frankxai/awesome-hermes-agent-skills
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…
EversiusJade/cognitive-perspective-check
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…
drftrun/driftengine
Build games and real-time 3D or 2D scenes that run in a browser with DriftEngine, a TypeScript game engine that draws with WebGPU and falls back to WebGL2, with physics, animation, audio, input, networking and…
eatmoreduck/yaya-skills
Transcribes any audio or video file into speaker-labeled text entirely on the local machine — no cloud, no login, no API key. Outputs plain text, SRT subtitles, an A/B dialogue transcript, and structured JSON. Use when…
rankcontrol/rankcontrol
Operate the user's RankControl workspace (rctrl.com) from the command line - AI search visibility and citations (ChatGPT, Perplexity, Claude, Gemini, Grok, Google AI Mode), SEO content planning, article generation and…
rueca/rueca
Build the design-tool harness around an interactive visual prototype — inspector of sliders and knobs, timeline, layers, presets, undo, share link, export. Use when someone wants to tweak, tune, scrub, dial in or play…
GangJaeYu/harness_loop_full_korean
docs/PRD.md와 docs/TRD.md를 읽고 프로젝트 전체 아키텍처를 docs/ARCHITECTURE/ 아래에 작성한다. overview.md에 시스템 구성·경계·핵심 흐름을 담고, frontend.md·backend.md·database.md·auth.md·security.md 등 영역별 문서로 나눠 기록하며, 무엇보다 PRD·TRD와 충돌하는 설계가 있는지 검토해 봉합하지 않고…
milanglacier/pi-multi-agent-skill
Start other pi agents and delegate work to them. Use it when a task benefits from a multi-agent workflow, such as splitting work across agents, running it in parallel or in the background, or keeping a side task out of…
jeanpfs/stock-images
Search and download stock photos from Pexels, Unsplash, and Pixabay for projects, landing pages, UI mockups, and content. Use when users explicitly ask to find stock photos, need a hero/profile/content image, or want to…
codezeroexe/levels
Conduct the connected level skills as one workflow. Asks the user what they want to do with a multi-select prompt, sets a target level per chosen skill, then runs the skills in a fixed safe order with a gate before each…
IvMisticos/misticos.Claude
Where the `queue` command exists, run every benchmark, profiler run, load test or other timing measurement as `queue bench --` followed by the command in the background, never directly. Run builds and tests through…
NarenDawar/narens-claude-toolkit
__DESCRIPTION__
zoo3323/paper-summary
현재 폴더의 PDF 논문을 읽어 한국어로 (1) 전체 번역본 HTML 과 (2) 핵심 요약본 HTML 두 개를 만든다. 그림·표·수식·그래프를 그대로 가져오고, 두 문서는 서로 클릭 이동할 수 있다. 사용자가 /paper-summary 라고 하거나 "논문 번역/요약 html 만들어줘"라고 할 때 사용. (용어/약어 사전을 따로 만들려면 paper-summary-word 스킬을 쓴다.)
ssheleg/seo-aeo-audit
Use when auditing a website for search and answer-engine visibility, diagnosing traffic or ranking loss, planning what to change, or extracting link-building targets and keywords - "SEO audit" / "сделай SEO-аудит",…
genfeedai/skills
Create paid ad copy for Meta, Google, LinkedIn, TikTok, and X using direct-response frameworks, platform limits, variants, and test plans. Triggers on ad headlines, ad creative, paid social ads, Google ads, and ad…
Orfi/trackbed
The user-facing front door for Trackbed — plan and orchestrate a roadmap of phases for either a Jira EPIC or a standalone PROJECT (a small app with no epic). Use whenever the user wants to plan, roadmap, orchestrate, or…
Liu-2026/AIBoot
An engineering playbook for AI coding agents. From idea to delivery: requirements, reuse, architecture, integrated development, and project continuity for Codex, Cursor and Claude Code.
Alexandre-LPZ/avant-garde
Use whenever the user wants to create, start or prototype a website, web application or SaaS (vibe coding), or asks for code for a new web project. Establishes the 6 foundation documents and the security gate before any…
ALVIN-YANG/ay-skills
Design service and transport contracts before implementation. Use when the primary deliverable is a REST, GraphQL, gRPC, event, webhook, SDK, or internal service interface, including 接口设计, API文档, OpenAPI, 错误码, 鉴权, or…
cckyros/goal-acceptance
Acceptance-criteria-driven goal completion for the goal-acceptance plugin — lock criteria before implementing, track task status, validate with real evidence, and confirm by an independent reviewer. Trigger words:…
jojaden/jobhunt
Korean developer job search, end to end — finds postings (Wanted, Jumpit, LinkedIn, Saramin, JobKorea, company career sites), scores them against the user's experience, builds a tailored resume A4 PDF, writes…
jrodrigopuca/local-agents
Reviewing Swift/SwiftUI code as mentor: the severity system, the Apple-specific defect checklist, and review-as-teaching. Trigger: load when the user shares Swift, SwiftUI, UIKit, or AppKit code for review, feedback, or…
Windsland52/MaaTutorial
编写、注册与调试 MaaFramework Custom 识别/动作——何时上 Custom 的判据、宿主与注册路径、binding 实现与注册、参数解析与校验、复用 pipeline 节点、Agent 子进程模式与工程规范。Use when implementing MaaFW custom recognition or action logic, deciding registration path for your host,…
judefluen-coder/plan-and-maintain-trips
Plan, research, revise, audit, and publish executable trips for any destination. Use when Codex needs to design a single-city or multi-city itinerary, compare lodging or transport, manage fixed bookings and changing…