Skills by risk · page 260
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/260
bevibing/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…
bevibing/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…
OpenRaiser/NanoResearch
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given…
OpenRaiser/NanoResearch
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config,…
OpenRaiser/NanoResearch
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
OpenRaiser/NanoResearch
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint…
OpenRaiser/NanoResearch
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry…
OpenRaiser/NanoResearch
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing…
OpenRaiser/NanoResearch
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR…
OpenRaiser/NanoResearch
Generate a Python code skeleton from an experiment blueprint
OpenRaiser/NanoResearch
Search academic literature and generate research hypotheses
OpenRaiser/NanoResearch
Produce an experiment blueprint from a research hypothesis
OpenRaiser/NanoResearch
Draft a LaTeX research paper from all previous stage outputs
OpenRaiser/NanoResearch
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or…
OpenRaiser/NanoResearch
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch…
utkusen/sast-skills
Perform codebase analysis and architecture mapping as the first phase of a security assessment. Explores the tech stack, frameworks, entry points, data flows, and trust boundaries. Outputs sast/architecture.md. Run this…
utkusen/sast-skills
Detect business logic vulnerabilities in a codebase using a three-phase approach: threat modeling (domain analysis and attack scenarios), batched verify (check exploitable gaps in parallel subagents, 3 scenarios each),…
utkusen/sast-skills
Detect insecure file upload vulnerabilities in a codebase using a three-phase approach: discovery (find all upload sites), batched verify (check extension bypass and related issues in parallel subagents, 3 sites each),…
utkusen/sast-skills
Detect GraphQL injection vulnerabilities in a codebase using a three-phase approach: recon (confirm GraphQL usage and find unsafe operation document assembly sites), batched verify (trace user input to those sites in…
utkusen/sast-skills
Detect Insecure Direct Object Reference (IDOR) vulnerabilities in a codebase using a three-phase approach: recon (find candidates), batched verify (check authorization in parallel subagents, 3 candidates each), and…
utkusen/sast-skills
Detect insecure JWT (JSON Web Token) implementations in a codebase using a two-phase approach: first map all JWT issuance and verification sites to understand the token lifecycle and signing configuration, then check…
utkusen/sast-skills
Detect path traversal vulnerabilities in a codebase using a three-phase approach: recon (find file-loading sinks with dynamic paths), batched verify (trace user input and mitigations in parallel subagents, 3 sinks…
utkusen/sast-skills
Detect Remote Code Execution (RCE) vulnerabilities in a codebase using a three-phase approach: recon (find dangerous execution sinks), batched verify (trace user input to sinks in parallel subagents, 3 sinks each), and…
utkusen/sast-skills
Consolidate all SAST vulnerability results from the sast/ folder into a single final report ranked by severity and confidentiality impact. Reads all *-results.md files and produces sast/final-report.md. Run after all…