Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ihatesea69/HieuNghi-AI-Skills --skill hugging-face-trackiogit clone --depth 1 https://github.com/ihatesea69/HieuNghi-AI-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ihatesea69/hieunghi-ai-skills/hugging-face-trackio)<a href="https://agentmods.dev/skills/ihatesea69/hieunghi-ai-skills/hugging-face-trackio"><img src="https://agentmods.dev/badge/skills/ihatesea69/hieunghi-ai-skills/hugging-face-trackio/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ihatesea69/hieunghi-ai-skills/hugging-face-trackio"><img src="https://agentmods.dev/badge/skills/ihatesea69/hieunghi-ai-skills/hugging-face-trackio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00522 |
| Opus 5 | $0.00026 | $0.00261 |
| Sonnet 5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
hugging-face-trackio scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to hugging-face-trackio — 120 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Trackio - Experiment Tracking for ML Training
Trackio is an experiment tracking library for logging and visualizing ML training metrics. It syncs to Hugging Face Spaces for real-time monitoring dashboards.
Two Interfaces
| Task | Interface | Reference |
|---|---|---|
| Logging metrics during training | Python API | references/logging_metrics.md |
| Retrieving metrics after/during training | CLI | references/retrieving_metrics.md |
When to Use Each
Python API → Logging
Use import trackio in your training scripts to log metrics:
- Initialize tracking with
trackio.init() - Log metrics with
trackio.log()or use TRL'sreport_to="trackio" - Finalize with
trackio.finish()
Key concept: For remote/cloud training, pass space_id — metrics sync to a Space dashboard so they persist after the instance terminates.
→ See references/logging_metrics.md for setup, TRL integration, and configuration options.
CLI → Retrieving
Use the trackio command to query logged metrics:
trackio list projects/runs/metrics— discover what's availabletrackio get project/run/metric— retrieve summaries and valuestrackio show— launch the dashboardtrackio sync— sync to HF Space
Key concept: Add --json for programmatic output suitable for automation and LLM agents.
→ See references/retrieving_metrics.md for all commands, workflows, and JSON output formats.
Minimal Logging Setup
import trackio
trackio.init(project="my-project", space_id="username/trackio")
trackio.log({"loss": 0.1, "accuracy": 0.9})
trackio.log({"loss": 0.09, "accuracy": 0.91})
trackio.finish()
Minimal Retrieval
trackio list projects --json
trackio get metric --project my-project --run my-run --metric loss --json
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 61 lines · 52 tokens per session scan A da2f366b8181
hugging-face-trackio is a skill published in the GitHub repository ihatesea69/HieuNghi-AI-Skills (3 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 522 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hugging-face-trackio, differing in 120 lines, and is treated as a copy.
Other skills, from other repositories
sf-eval
Evaluate and benchmark Salesforce skill quality. Compares AI-generated code with vs without skill context, scores against a Salesforce-specific rubric (security, governor limits, bulkification, patterns, completeness), and produces a comparison report. Use to run benchmarks, verify skill value, or check Apex code…
pytorch-lightning
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
huggingface-accelerate
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, single launch command. HuggingFace ecosystem standard.
deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
pinecone-quickstart
Interactive Pinecone quickstart for new developers. Choose between two paths - Database (create an integrated index, upsert data, and query using Pinecone MCP + Python) or Assistant (create a Pinecone Assistant for document Q&A). Use when a user wants to get started with Pinecone for the first time or wants a guided…
pinecone-n8n
Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n.