drugs_com_reviews

Name: drugs_com_reviews
Author: QSong-github

132stars4forks

How to install drugs_com_reviews?

qsong-github/drugclaw/drugs_com_reviews

$npx -y skills add QSong-github/DrugClaw --skill drugs_com_reviews

Installs into the current project.

Summary

Query the DrugLib.com Drug Review Dataset (UCI #461). Use whenever the user asks about patient drug reviews, drug effectiveness ratings, side-effect profiles, or condition-specific treatment experiences from DrugLib.com.

Files · 1

View on GitHub

SKILL.md

1	# DrugLib Reviews Query Skill
2
3	Search patient drug reviews by drug name or medical condition. Auto-detects
4	entity type and routes to the appropriate field.
5
6	\| Input Pattern \| Detected As \| Match Logic \|
7	\|---\|---\|---\|
8	\| single/two-word term (e.g. `lamictal`) \| drug name \| substring on `urlDrugName` \|
9	\| multi-word or medical keyword (e.g. `bipolar disorder`) \| condition \| substring on `condition` \|
10
11	Condition keywords that trigger condition routing: disease, disorder, syndrome,
12	infection, pain, cancer, diabetes, hypertension, depression, anxiety, asthma,
13	arthritis, migraine, allergy, insomnia, nausea, obesity, acne, gerd, copd.
14
15	## API
16
17	\| Function \| Input \| Returns \|
18	\|---\|---\|---\|
19	\| `load_reviews()` \| — \| list[dict] (cached) \|
20	\| `search(entity)` \| single entity string \| list[dict] \|
21	\| `search_batch(entities)` \| list of entity strings \| dict[str, list[dict]] \|
22	\| `summarize(hits, entity)` \| list[dict] + label \| compact LLM-readable text \|
23	\| `to_json(hits)` \| list[dict] \| list[dict] (JSON-serialisable) \|
24
25	## Usage
26
27	See `if __name__ == "__main__"` block in `16_DRUGLIB_REVIEWS.py` for runnable
28	examples covering: drug name search, condition search, batch search, and JSON
29	output.
30
31	## Data
32
33	- Source: Drug Review Dataset (Druglib.com), UCI ML Repository #461
34	- Citation: Kallumadi, S. & Gräßer, F. (2018). Drug Reviews (Druglib.com) [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C55G6J
35	- License: CC BY 4.0
36	- Files: `drugLibTrain_raw.tsv`, `drugLibTest_raw.tsv` (TSV, merged at load)
37	- Path: `DATA_DIR` variable in `16_DRUGLIB_REVIEWS.py`
38	- Columns:
39
40	\| Column \| Type \| Description \|
41	\|---\|---\|---\|
42	\| `urlDrugName` \| str \| Drug name (lowercase, URL-style) \|
43	\| `rating` \| int 0–9 \| Overall patient satisfaction \|
44	\| `effectiveness` \| str \| Highly / Considerably / Moderately / Marginally Effective, Ineffective \|
45	\| `sideEffects` \| str \| No / Mild / Moderate / Severe / Extremely Severe Side Effects \|
46	\| `condition` \| str \| Medical condition being treated \|
47	\| `benefitsReview` \| str \| Free-text review of benefits \|
48	\| `sideEffectsReview` \| str \| Free-text review of side effects \|
49	\| `commentsReview` \| str \| Free-text general comments \|

People who liked this also viewed

6 picks

Type

drugs_com_reviews

132stars4forks

View on GitHub

How to install drugs_com_reviews?

qsong-github/drugclaw/drugs_com_reviews

$npx -y skills add QSong-github/DrugClaw --skill drugs_com_reviews

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DrugLib Reviews Query Skill
2
3	Search patient drug reviews by drug name or medical condition. Auto-detects
4	entity type and routes to the appropriate field.
5
6	\| Input Pattern \| Detected As \| Match Logic \|
7	\|---\|---\|---\|
8	\| single/two-word term (e.g. `lamictal`) \| drug name \| substring on `urlDrugName` \|
9	\| multi-word or medical keyword (e.g. `bipolar disorder`) \| condition \| substring on `condition` \|
10
11	Condition keywords that trigger condition routing: disease, disorder, syndrome,
12	infection, pain, cancer, diabetes, hypertension, depression, anxiety, asthma,
13	arthritis, migraine, allergy, insomnia, nausea, obesity, acne, gerd, copd.
14
15	## API
16
17	\| Function \| Input \| Returns \|
18	\|---\|---\|---\|
19	\| `load_reviews()` \| — \| list[dict] (cached) \|
20	\| `search(entity)` \| single entity string \| list[dict] \|
21	\| `search_batch(entities)` \| list of entity strings \| dict[str, list[dict]] \|
22	\| `summarize(hits, entity)` \| list[dict] + label \| compact LLM-readable text \|
23	\| `to_json(hits)` \| list[dict] \| list[dict] (JSON-serialisable) \|
24
25	## Usage
26
27	See `if __name__ == "__main__"` block in `16_DRUGLIB_REVIEWS.py` for runnable
28	examples covering: drug name search, condition search, batch search, and JSON
29	output.
30
31	## Data
32
33	- Source: Drug Review Dataset (Druglib.com), UCI ML Repository #461
34	- Citation: Kallumadi, S. & Gräßer, F. (2018). Drug Reviews (Druglib.com) [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C55G6J
35	- License: CC BY 4.0
36	- Files: `drugLibTrain_raw.tsv`, `drugLibTest_raw.tsv` (TSV, merged at load)
37	- Path: `DATA_DIR` variable in `16_DRUGLIB_REVIEWS.py`
38	- Columns:
39
40	\| Column \| Type \| Description \|
41	\|---\|---\|---\|
42	\| `urlDrugName` \| str \| Drug name (lowercase, URL-style) \|
43	\| `rating` \| int 0–9 \| Overall patient satisfaction \|
44	\| `effectiveness` \| str \| Highly / Considerably / Moderately / Marginally Effective, Ineffective \|
45	\| `sideEffects` \| str \| No / Mild / Moderate / Severe / Extremely Severe Side Effects \|
46	\| `condition` \| str \| Medical condition being treated \|
47	\| `benefitsReview` \| str \| Free-text review of benefits \|
48	\| `sideEffectsReview` \| str \| Free-text review of side effects \|
49	\| `commentsReview` \| str \| Free-text general comments \|

People who liked this also viewed

6 picks

Type