Find and fix the slow, memory-hungry parts of your pandas code
Paste your pandas script and get a performance audit — which operations are slow, what's eating memory, where you're using apply() when vectorized ops would be much faster, and where you should switch to Polars or DuckDB.
Create a skill called "Pandas Pit Stop". When I paste Python code that uses pandas, analyze it for performance and memory issues. Specifically check for: (1) apply(), iterrows(), or itertuples() calls that could be vectorized — show the vectorized alternative. (2) Memory waste from suboptimal dtypes (object columns that should be category, int64 that could be int32, etc.) — show the optimized read_csv() call. (3) Operations that will blow up memory on large data (merge creating cartesian products, concat without cleanup). (4) SettingWithCopyWarning risks — show the .loc[] or .copy() fix. (5) Chained operations that are hard to debug — insert intermediate shape checks. (6) Cases where Polars or DuckDB would be significantly better — provide the translated code. Always estimate the speedup and memory savings for each suggestion.
Pandas code that works fine on 10,000 rows chokes on 1 million. apply()
loops are secretly Python-speed. merge() duplicates memory. read_csv()
picks the worst dtypes. This skill profiles your code and tells you
exactly what to fix.
Diagnose and fix slow SQL without being a DBA
Paste a slow query and get back a diagnosis in plain English — what's slow, why it's slow, and which fixes are most likely to help. Reads EXPLAIN plans so you don't have to. Suggests indexes, rewrites, and pre-aggregation strategies.
Fix slow Looker Studio dashboards without losing critical signal
Looker Studio dashboards can become painfully slow as complexity and blended sources grow. This recipe diagnoses likely causes (too many charts, heavy sources, blends/joins, formatting) and produces a performance-first redesign plan (including caching and pre-aggregation strategies).
Auto-generate proxies the moment footage lands
Choppy playback, laggy scrubbing, and unusable timelines — even on strong machines — often comes down to editing long-GOP or heavy codecs at high resolution without proxies. This recipe generates proxies automatically whenever new camera originals appear, so every project starts edit-ready instead of debug-ready.
Keep media caches from eating your SSD and slowing your apps
Media cache and disk caches balloon over time, causing storage emergencies and performance regressions. This recipe turns cache cleanup from a panic action into a controlled, scheduled maintenance job — for Adobe Premiere Pro, After Effects, and similar tools.