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 PatrickGallucci/fabric-skills --skill fabric-pandas-perf-remediategit clone --depth 1 https://github.com/PatrickGallucci/fabric-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/patrickgallucci/fabric-skills/fabric-pandas-perf-remediate)<a href="https://agentmods.dev/skills/patrickgallucci/fabric-skills/fabric-pandas-perf-remediate"><img src="https://agentmods.dev/badge/skills/patrickgallucci/fabric-skills/fabric-pandas-perf-remediate/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/patrickgallucci/fabric-skills/fabric-pandas-perf-remediate"><img src="https://agentmods.dev/badge/skills/patrickgallucci/fabric-skills/fabric-pandas-perf-remediate.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 | $0.00107 | $0.03355 |
| Opus 5 | $0.00053 | $0.01677 |
| Sonnet 5 | $0.00021 | $0.00671 |
| Haiku 4.5 | $0.00011 | $0.00335 |
Grade A, and why
fabric-pandas-perf-remediate 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabric Pandas Performance Troubleshooting
Diagnose and resolve pandas-related performance issues in Microsoft Fabric Spark notebooks, including memory exhaustion, slow conversions, and suboptimal pandas API on Spark usage.
When to Use This Skill
- Notebook cells hang or timeout during pandas operations
toPandas()fails with OutOfMemoryError or Java heap space errorscollect()crashes the driver node- Pandas API on Spark (
pyspark.pandas/ps) runs slower than expected - DataFrame conversion between Spark and pandas causes memory spikes
- Notebook kernel restarts unexpectedly during data processing
- Large dataset operations exhaust driver memory on Fabric capacity
- Need to choose between pandas, Spark DataFrame, or pandas API on Spark
Prerequisites
- Microsoft Fabric workspace with Data Engineering experience
- Fabric capacity F2 or higher (F64+ recommended for large datasets)
- PySpark notebook with Spark session active
- Basic familiarity with pandas and PySpark DataFrames
Quick Diagnosis
Symptom-to-Solution Map
| Symptom | Likely Cause | Jump To |
|---|---|---|
toPandas() OOM error |
Dataset too large for driver | toPandas Optimization |
| Kernel restart during pandas op | Driver memory exhausted | Driver Memory Tuning |
pyspark.pandas slower than native pandas |
Spark overhead on small data | Right-Size Your Approach |
| Slow groupby/merge in pandas API on Spark | Excessive shuffling | Shuffle Optimization |
| Cell timeout on DataFrame conversion | Large collect to driver | Incremental Processing |
ArrowInvalid or conversion errors |
Schema mismatch / nulls | Arrow Conversion Fixes |
| High memory but slow pandas operations | GC pressure / fragmentation | Memory Profiling |
Right-Size Your Approach
Critical Decision: Choose the right DataFrame API for your data size and workload.
What ships with it
4 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.
- 13d ago First seen · 375 lines · 107 tokens per session scan A 364b9144afa2
fabric-pandas-perf-remediate is a skill published in the GitHub repository PatrickGallucci/fabric-skills (16 stars, last pushed 3mo ago), licensed MIT. It adds 107 tokens to every session and 3,355 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dask
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed…
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
python-pipeline
Python data pipelines with modular architecture. Use for content workflows, batch jobs, or Google Sheets/Drive integration.
datarobot-setup
Sets up DataRobot for local development including Python SDK, dr-cli, Agent Assist, and all required dependencies. Use when the user has not yet worked with DataRobot on this machine, OR when any DataRobot task fails due to missing or invalid credentials. Covers first-time setup, re-authentication, and credential…
leiloeiro-edital-ranbot-ai
Analise e auditoria de editais de leilao judicial e extrajudicial. Riscos ocultos, clausulas perigosas, debitos, ocupante e classificacao da oportunidade.
mloda-plugins
Guide an AI agent through building mloda (https://github.com/mloda-ai/mloda) plugins: FeatureGroup, ComputeFramework, and Extender classes. Use to check the mloda-registry index for an existing plugin before writing one, when writing or reviewing a FeatureGroup/ComputeFramework/Extender implementation, or when…