← All skills

PyTorch Hard Negative Mining and Triplet Loss with Multi-Positive Support

100 / 100 · Low risk

Fine to try.

By ECNU-ICALK/AutoSkill (GitHub) · other · 613 stars · scanned at commit 94c47ca

Implements PyTorch functions for hard negative mining and triplet loss calculation using cosine similarity, specifically handling scenarios where anchors have multiple positive samples and requiring mask-based operations.

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'pytorch-hard-negative-mining-and-triplet-loss-with-multi-positiv' ] || [ -L ~/.agents/skills/'pytorch-hard-negative-mining-and-triplet-loss-with-multi-positiv' ]; then echo 'A skill folder named pytorch-hard-negative-mining-and-triplet-loss-with-multi-positiv already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ECNU-ICALK/AutoSkill' "$d" && git -C "$d" checkout --quiet '94c47ca488d4ba4117d20272e66d49b9877e68cf' -- 'SkillBank/ConvSkill/english_gpt4_8_GLM4.7/pytorch-hard-negative-mining-and-triplet-loss-with-multi-positiv' && mkdir -p ~/.agents/skills && cp -R "$d"/'SkillBank/ConvSkill/english_gpt4_8_GLM4.7/pytorch-hard-negative-mining-and-triplet-loss-with-multi-positiv' ~/.agents/skills/'pytorch-hard-negative-mining-and-triplet-loss-with-multi-positiv' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'pytorch-hard-negative-mining-and-triplet-loss-with-multi-positiv' ~/.claude/skills/'pytorch-hard-negative-mining-and-triplet-loss-with-multi-positiv' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for ECNU-ICALK/AutoSkill shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/ECNU-ICALK/AutoSkill.svg)](https://zalavijaysinh.github.io/skilltrust/repos/ECNU-ICALK/AutoSkill/)

Score history