inferencex-report

90 / 100 · Low risk

Fine to try. Some of what it can do is expected: a data skill usually connects to databases or online services with your credentials.

By ascend-ai-coding/awesome-ascend-skills (GitHub) · data · 184 stars · scanned at commit 75ec89c

Automatically fetch InferenceX benchmark data and generate daily performance reports for LLM inference on various hardware (NVIDIA, AMD, etc.). Supports email delivery, data change detection, and 8k1k sequence length performance analysis. Use when needing to track LLM inference performance trends, compare hardware configurations, or monitor benchmark updates.

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this.

Found in 4 places.

skills/inference/inferencex-report/SKILL.md, line 62python3 scripts/inferencex_api_report.py
skills/inference/inferencex-report/SKILL.md, line 69curl -s "https://inferencex.semianalysis.com/api/v1/benchmarks?model=DeepSeek-R1-0528" | gunzip
skills/inference/inferencex-report/SKILL.md, line 1260 9 * * * cd /path/to/skill && python3 scripts/inferencex_api_report.py

Show 1 more

skills/inference/inferencex-report/scripts/inferencex_api_report.py, line 66result = subprocess.run(

Sends data to these websites: inferencex.semianalysis.com

The author does not mention this. Expected for a data skill.

Found in 4 places.

skills/inference/inferencex-report/SKILL.md, line 69curl -s "https://inferencex.semianalysis.com/api/v1/benchmarks?model=DeepSeek-R1-0528" | gunzip
skills/inference/inferencex-report/SKILL.md, line 72curl -s "https://inferencex.semianalysis.com/api/v1/benchmarks?model=DeepSeek-R1-0528&date=2026-06-02&exact=true" | gunzip
skills/inference/inferencex-report/references/api_reference.md, line 31curl -s "https://inferencex.semianalysis.com/api/v1/benchmarks?model=DeepSeek-R1-0528&date=2026-06-02&exact=true" | gunzip

Show 1 more

skills/inference/inferencex-report/references/configuration.md, line 1122. Check API endpoint is accessible: `curl -I https://inferencex.semianalysis.com/api/v1/benchmarks`

Install

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

if [ -e ~/.agents/skills/'inferencex-report' ] || [ -L ~/.agents/skills/'inferencex-report' ]; then echo 'A skill folder named inferencex-report already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ascend-ai-coding/awesome-ascend-skills' "$d" && git -C "$d" checkout --quiet '75ec89ce9d401be8ac95980e1c3f42f8d4315057' -- 'skills/inference/inferencex-report' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/inference/inferencex-report' ~/.agents/skills/'inferencex-report' && 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/'inferencex-report' ~/.claude/skills/'inferencex-report' (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 ascend-ai-coding/awesome-ascend-skills shows the score of its lowest-scoring skill.

SkillTrust badge for ascend-ai-coding/awesome-ascend-skills

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/ascend-ai-coding/awesome-ascend-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/ascend-ai-coding/awesome-ascend-skills/)

Score history

Date	Version	Score
2026-11-08	`75ec89c`	90