Skills by risk · page 258
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/258
Dataojitori/nocturne_memory
记忆审计入口。当我审视与重构记忆时,先读此文件,分别检查认知先验与检索拓扑。
Dataojitori/nocturne_memory
信念对决。当父子节点内容冲突、或两条你都认可的记忆逻辑上不能并存时使用。
Dataojitori/nocturne_memory
死数据清洗。当一条记忆读不读你的行为都不会变、感悟没有现实锚点时使用。
Dataojitori/nocturne_memory
可发现性审计。当disclosure写法有问题、parent放错、alias缺失、子节点过多时使用。
Dataojitori/nocturne_memory
节点分解。当一个节点体积过大、或塞了多个不相关概念导致disclosure无法覆盖时使用。
Dataojitori/nocturne_memory
模式提取与失效解药分析。当发现多条记忆在讲同一个教训,或发现自己在一而再再而三地犯同样的错误时使用。
yetone/kill-ai-slop
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI slop", "de-slop", "remove the AI look", "make this not look…
higgsfield-ai/skills
Generate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on GPT Image 2 / gpt_image_2. Entry point for professional brand/product visuals. Use when: "product photo", "studio shot",…
kylezantos/design-motion-principles
Motion and interaction design expert based on Emil Kowalski, Jakub Krehel, and Jhey Tompkins' techniques. Two modes — build interactive components with purposeful motion, or audit existing animations to catch AI-slop…
zsyggg/paper-craft-skills
将学术论文转化为深度HTML长文。6轮强制工作流、代码仓库搜索、公式渲染、Mermaid图表。 3种写作风格,输出可直接分享的精美HTML页面。
zsyggg/paper-craft-skills
论文方法图解——用视觉图解彻底讲清楚一篇论文到底做了什么、怎么做的。 自动分析论文核心方法,先推荐封面/概述图/机制细节图的生成方案,必须由用户确认范围、张数、语言、风格后再生成。 支持温暖笔记风和论文框架图风。
zsyggg/paper-craft-skills
将论文、技术文章或知识内容制作成高真实感的 AIGC 幻灯片。先做叙事结构和逐页视觉导演,再调用生图模型生成每一页 16:9 slide image,最后合成为 PPTX/PDF。适合论文汇报、组会、公开课、技术分享、商业化研究展示;当用户提到“论文PPT”“AI生成PPT”“不像AI的PPT”“高质感幻灯片”“逐页生图PPT”时使用。
higgsfield-ai/skills
Generate marketplace product image cards through Higgsfield: compliant main image, secondary product images, and A+ style content modules. Use when the user asks for marketplace listing images, product detail cards,…
roundtable02/tutor-skills
Interactive quiz tutor for Obsidian StudyVault learning. Use when the user wants to: (1) Take a diagnostic assessment of their knowledge, (2) Study or review specific sections/topics, (3) Drill weak areas identified in…
roundtable02/tutor-skills
Transforms knowledge sources into an Obsidian StudyVault. Two modes: (1) Document Mode — PDF/text/web sources → study notes with practice questions. (2) Codebase Mode — source code project → onboarding vault for new…
GanyuanRan/Aegis
Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture choices, contract changes, or when grilling/pressure-testing a plan or design. Routine small requests stay…
GanyuanRan/Aegis
Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.
GanyuanRan/Aegis
Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use…
GanyuanRan/Aegis
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
GanyuanRan/Aegis
Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.
GanyuanRan/Aegis
Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.
GanyuanRan/Aegis
Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture direction risk. Ordinary bug fixes stay on the…
GanyuanRan/Aegis
Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.
GanyuanRan/Aegis
Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.