Statistical Data Analysis
lingzhi227/agent-research-skills
Writes statistical analysis code for experimental data, runs it through a four-round review, and reports effect sizes, p-values and confidence intervals.
Queries the openFDA API from Python for drug, device, food and veterinary data: adverse events, recalls, labels, approvals, NDC and UNII lookups.
$ npx skills add davila7/claude-code-templates --skill fda-database -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install davila7/claude-code-templates fda-database --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/davila7/claude-code-templates.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-tool/components/skills/scientific/fda-database .claude/skills/fda-database && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "fda-database" agent skill from https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/scientific/fda-database into .claude/skills/fda-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fda-database", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/scientific/fda-databaseType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add davila7/claude-code-templates --skill fda-database -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install davila7/claude-code-templates fda-database --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davila7/claude-code-templates.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cli-tool/components/skills/scientific/fda-database .agents/skills/fda-database && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fda-database" agent skill from https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/scientific/fda-database into .agents/skills/fda-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fda-database", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add davila7/claude-code-templates --skill fda-database -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install davila7/claude-code-templates fda-database --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davila7/claude-code-templates.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cli-tool/components/skills/scientific/fda-database .cursor/skills/fda-database && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fda-database" agent skill from https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/scientific/fda-database into .cursor/skills/fda-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fda-database", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/scientific/fda-database--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add davila7/claude-code-templates --skill fda-database -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install davila7/claude-code-templates fda-database --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davila7/claude-code-templates.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cli-tool/components/skills/scientific/fda-database .gemini/skills/fda-database && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fda-database" agent skill from https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/scientific/fda-database into .gemini/skills/fda-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fda-database", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install davila7/claude-code-templates fda-databaseInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add davila7/claude-code-templates --skill fda-database -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/davila7/claude-code-templates.git skills-src && mkdir -p .github/skills && cp -r skills-src/cli-tool/components/skills/scientific/fda-database .github/skills/fda-database && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fda-database" agent skill from https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/scientific/fda-database into .github/skills/fda-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fda-database", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add davila7/claude-code-templates --skill fda-database -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install davila7/claude-code-templates fda-database --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/davila7/claude-code-templates.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cli-tool/components/skills/scientific/fda-database .opencode/skills/fda-database && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fda-database" agent skill from https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/scientific/fda-database into .opencode/skills/fda-database/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fda-database", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
fda-databaseQueries the openFDA API from Python for drug, device, food and veterinary data: adverse events, recalls, labels, approvals, NDC and UNII lookups.
The skill gives the agent a Python workflow for the public openFDA API, which covers drugs, medical devices, foods, animal and veterinary products, and substances. A `FDAQuery` helper in `scripts/fda_query.py` makes the requests, `scripts/fda_examples.py` shows worked examples, and separate reference files describe API basics and each product area.
Typical jobs include pulling adverse event reports, checking labeling and approvals, following recalls and enforcement actions, looking up National Drug Codes and UNII substance identifiers, and reviewing 510k and PMA device clearances. The API works without a key; registering one raises the daily limit from 1,000 to 120,000 requests while the per-minute limit stays at 240. The key is passed through the `FDA_API_KEY` environment variable.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4c82aba. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
open.fda.govgithub.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
FDA_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
openFDA Regulatory Data Queries loads about 3.6k tokens when it runs, and up to ~25k if it reads all its reference files. Until then it costs about 50 tokens; SKILL.md has 780 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from davila7/claude-code-templates at commit 4c82aba, republished under its MIT licence (© davila7). 780 words, ~3,589 tokens.
.claude/skills/fda-database/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.Access comprehensive FDA regulatory data through openFDA, the FDA's initiative to provide open APIs for public datasets. Query information about drugs, medical devices, foods, animal/veterinary products, and substances using Python with standardized interfaces.
Key capabilities:
This skill should be used when working with:
from scripts.fda_query import FDAQuery
# Initialize (API key optional but recommended)
fda = FDAQuery(api_key="YOUR_API_KEY")
# Query drug adverse events
events = fda.query_drug_events("aspirin", limit=100)
# Get drug labeling
label = fda.query_drug_label("Lipitor", brand=True)
# Search device recalls
recalls = fda.query("device", "enforcement",
search="classification:Class+I",
limit=50)While the API works without a key, registering provides higher rate limits:
Register at: https://open.fda.gov/apis/authentication/
Set as environment variable:
export FDA_API_KEY="your_key_here"# Run comprehensive examples
python scripts/fda_examples.py
# This demonstrates:
# - Drug safety profiles
# - Device surveillance
# - Food recall monitoring
# - Substance lookup
# - Comparative drug analysis
# - Veterinary drug analysisAccess 6 drug-related endpoints covering the full drug lifecycle from approval to post-market surveillance.
Endpoints:
Common use cases:
# Safety signal detection
fda.count_by_field("drug", "event",
search="patient.drug.medicinalproduct:metformin",
field="patient.reaction.reactionmeddrapt")
# Get prescribing information
label = fda.query_drug_label("Keytruda", brand=True)
# Check for recalls
recalls = fda.query_drug_recalls(drug_name="metformin")
# Monitor shortages
shortages = fda.query("drug", "drugshortages",
search="status:Currently+in+Shortage")Reference: See references/drugs.md for detailed documentation
Access 9 device-related endpoints covering medical device safety, approvals, and registrations.
Endpoints:
Common use cases:
# Monitor device safety
events = fda.query_device_events("pacemaker", limit=100)
# Look up device classification
classification = fda.query_device_classification("DQY")
# Find 510(k) clearances
clearances = fda.query_device_510k(applicant="Medtronic")
# Search by UDI
device_info = fda.query("device", "udi",
search="identifiers.id:00884838003019")Reference: See references/devices.md for detailed documentation
Access 2 food-related endpoints for safety monitoring and recalls.
Endpoints:
Common use cases:
# Monitor allergen recalls
recalls = fda.query_food_recalls(reason="undeclared peanut")
# Track dietary supplement events
events = fda.query_food_events(
industry="Dietary Supplements")
# Find contamination recalls
listeria = fda.query_food_recalls(
reason="listeria",
classification="I")Reference: See references/foods.md for detailed documentation
Access veterinary drug adverse event data with species-specific information.
Endpoint:
Common use cases:
# Species-specific events
dog_events = fda.query_animal_events(
species="Dog",
drug_name="flea collar")
# Breed predisposition analysis
breed_query = fda.query("animalandveterinary", "event",
search="reaction.veddra_term_name:*seizure*+AND+"
"animal.breed.breed_component:*Labrador*")Reference: See references/animal_veterinary.md for detailed documentation
Access molecular-level substance data with UNII codes, chemical structures, and relationships.
Endpoints:
Common use cases:
# UNII to CAS mapping
substance = fda.query_substance_by_unii("R16CO5Y76E")
# Search by name
results = fda.query_substance_by_name("acetaminophen")
# Get chemical structure
structure = fda.query("other", "substance",
search="names.name:ibuprofen+AND+substanceClass:chemical")Reference: See references/other.md for detailed documentation
Create comprehensive safety profiles combining multiple data sources:
def drug_safety_profile(fda, drug_name):
"""Generate complete safety profile."""
# 1. Total adverse events
events = fda.query_drug_events(drug_name, limit=1)
total = events["meta"]["results"]["total"]
# 2. Most common reactions
reactions = fda.count_by_field(
"drug", "event",
search=f"patient.drug.medicinalproduct:*{drug_name}*",
field="patient.reaction.reactionmeddrapt",
exact=True
)
# 3. Serious events
serious = fda.query("drug", "event",
search=f"patient.drug.medicinalproduct:*{drug_name}*+AND+serious:1",
limit=1)
# 4. Recent recalls
recalls = fda.query_drug_recalls(drug_name=drug_name)
return {
"total_events": total,
"top_reactions": reactions["results"][:10],
"serious_events": serious["meta"]["results"]["total"],
"recalls": recalls["results"]
}Analyze trends over time using date ranges:
from datetime import datetime, timedelta
def get_monthly_trends(fda, drug_name, months=12):
"""Get monthly adverse event trends."""
trends = []
for i in range(months):
end = datetime.now() - timedelta(days=30*i)
start = end - timedelta(days=30)
date_range = f"[{start.strftime('%Y%m%d')}+TO+{end.strftime('%Y%m%d')}]"
search = f"patient.drug.medicinalproduct:*{drug_name}*+AND+receivedate:{date_range}"
result = fda.query("drug", "event", search=search, limit=1)
count = result["meta"]["results"]["total"] if "meta" in result else 0
trends.append({
"month": start.strftime("%Y-%m"),
"events": count
})
return trendsCompare multiple products side-by-side:
def compare_drugs(fda, drug_list):
"""Compare safety profiles of multiple drugs."""
comparison = {}
for drug in drug_list:
# Total events
events = fda.query_drug_events(drug, limit=1)
total = events["meta"]["results"]["total"] if "meta" in events else 0
# Serious events
serious = fda.query("drug", "event",
search=f"patient.drug.medicinalproduct:*{drug}*+AND+serious:1",
limit=1)
serious_count = serious["meta"]["results"]["total"] if "meta" in serious else 0
comparison[drug] = {
"total_events": total,
"serious_events": serious_count,
"serious_rate": (serious_count/total*100) if total > 0 else 0
}
return comparisonLink data across multiple endpoints:
def comprehensive_device_lookup(fda, device_name):
"""Look up device across all relevant databases."""
return {
"adverse_events": fda.query_device_events(device_name, limit=10),
"510k_clearances": fda.query_device_510k(device_name=device_name),
"recalls": fda.query("device", "enforcement",
search=f"product_description:*{device_name}*"),
"udi_info": fda.query("device", "udi",
search=f"brand_name:*{device_name}*")
}All API responses follow this structure:
{
"meta": {
"disclaimer": "...",
"results": {
"skip": 0,
"limit": 100,
"total": 15234
}
},
"results": [
# Array of result objects
]
}Always handle potential errors:
result = fda.query_drug_events("aspirin", limit=10)
if "error" in result:
print(f"Error: {result['error']}")
elif "results" not in result or len(result["results"]) == 0:
print("No results found")
else:
# Process results
for event in result["results"]:
# Handle event data
passFor large result sets, use pagination:
# Automatic pagination
all_results = fda.query_all(
"drug", "event",
search="patient.drug.medicinalproduct:aspirin",
max_results=5000
)
# Manual pagination
for skip in range(0, 1000, 100):
batch = fda.query("drug", "event",
search="...",
limit=100,
skip=skip)
# Process batchDO:
# Specific field search
search="patient.drug.medicinalproduct:aspirin"DON'T:
# Overly broad wildcard
search="*aspirin*"The FDAQuery class handles rate limiting automatically, but be aware of limits:
The FDAQuery class includes built-in caching (enabled by default):
# Caching is automatic
fda = FDAQuery(api_key=api_key, use_cache=True, cache_ttl=3600)When counting/aggregating, use .exact suffix:
# Count exact phrases
fda.count_by_field("drug", "event",
search="...",
field="patient.reaction.reactionmeddrapt",
exact=True) # Adds .exact automaticallyClean and validate search terms:
def clean_drug_name(name):
"""Clean drug name for query."""
return name.strip().replace('"', '\\"')
drug_name = clean_drug_name(user_input)For detailed information about:
references/api_basics.mdreferences/drugs.mdreferences/devices.mdreferences/foods.mdreferences/animal_veterinary.mdreferences/other.mdscripts/fda_query.pyMain query module with FDAQuery class providing:
scripts/fda_examples.pyComprehensive examples demonstrating:
Run examples:
python scripts/fda_examples.pyIssue: Rate limit exceeded
Issue: No results found
Issue: Invalid query syntax
references/api_basics.mdIssue: Missing fields in results
© davila7, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 8 other files (scripts, references) in cli-tool/components/skills/scientific/fda-database of davila7/claude-code-templates.
Open the folder on GitHubat commit 4c82aba
We found 22 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 12 other GitHub owners. This page covers the copy in davila7/claude-code-templates, which our catalogue first saw on October 7, 2026.
openFDA Regulatory Data Queries next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| openFDA Regulatory Data Queries this skilldavila7/claude-code-templates | 32k | 12 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Statistical Data Analysislingzhi227/agent-research-skills | 383 | — | ~886 | Automated safety check: Pass | None | |
| Q-EDA Exploratory AnalysisTyrealQ/q-skills | 108 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Analyzebrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~2.2k | Automated safety check: Notes | Custom licence | |
| Excel and CSV Data Analysisbytedance/deer-flow | 83k | 4 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Python Executorcortega26/chile-hub | 113 | 2 repos | ~1.5k | Automated safety check: Pass | MIT |
lingzhi227/agent-research-skills
Writes statistical analysis code for experimental data, runs it through a four-round review, and reports effect sizes, p-values and confidence intervals.
TyrealQ/q-skills
Runs exploratory data analysis on tabular data after you confirm each column's measurement level, then writes CSV tables and a narrative summary.
brycewang-stanford/Auto-Empirical-Research-Skills
End-to-end data analysis dispatching Coder and Data-engineer for implementation, coder-critic for review.
bytedance/deer-flow
Analyzes uploaded Excel and CSV files with SQL through DuckDB, producing schema inspections, statistical summaries and exports to CSV, JSON or Markdown.
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
zLanqing/codex-claude-academic-skills
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing.
davila7/claude-code-templates
Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.
davila7/claude-code-templates
Analyzes Neuropixels recordings from SpikeGLX or Open Ephys through preprocessing, drift correction, Kilosort4 spike sorting, quality metrics and curation.
davila7/claude-code-templates
Supplies LaTeX templates and formatting rules for journals, conferences, posters, and grant proposals, then can check a draft against them.
davila7/claude-code-templates
Analyzes a brand's existing writing to lock in a consistent voice, then builds SEO blog posts and platform-specific social content around it.
davila7/claude-code-templates
Guides corrective and preventive action (CAPA) work in a quality management system, from initiation and root cause analysis through effectiveness verification.
davila7/claude-code-templates
Senior FDA consultant and specialist for medical device companies including HIPAA compliance and requirement management.
Works with
Categories
Queries the openFDA API from Python for drug, device, food and veterinary data: adverse events, recalls, labels, approvals, NDC and UNII lookups. The skill gives the agent a Python workflow for the public openFDA API, which covers drugs, medical devices, foods, animal and veterinary products, and substances.py` shows worked examples, and separate reference files describe API basics and each product area.
openFDA Regulatory Data Queries fits situations like: checking the adverse event history of a drug before a safety review; looking up a device's 510k clearance or recall record; mapping a substance name to its UNII identifier or CAS number; tracking food recalls and allergen-related enforcement actions.
Run `npx skills add davila7/claude-code-templates --skill fda-database -a claude-code`. Or copy the skill folder (cli-tool/components/skills/scientific/fda-database in davila7/claude-code-templates) into .claude/skills/fda-database in your project. Claude Code loads it when a task matches its description.
Run `npx skills add davila7/claude-code-templates --skill fda-database -a codex`. Or copy the skill folder (cli-tool/components/skills/scientific/fda-database in davila7/claude-code-templates) into .agents/skills/fda-database in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davila7/claude-code-templates --skill fda-database -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fda-database, .gemini/skills/fda-database, .github/skills/fda-database and .opencode/skills/fda-database in your project.
Going by SKILL.md and its folder, openFDA Regulatory Data Queries needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named FDA_API_KEY. Our summary lists: Python; Network access to the openFDA API; An openFDA API key (optional, raises the daily request limit).
SKILL.md names 2 domains. As links in the text: open.fda.gov and github.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
openFDA Regulatory Data Queries is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 21k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with openFDA Regulatory Data Queries: Statistical Data Analysis (lingzhi227/agent-research-skills, 383 stars), Q-EDA Exploratory Analysis (TyrealQ/q-skills, 108 stars), Analyze (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars) and Excel and CSV Data Analysis (bytedance/deer-flow, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
davila7 (a GitHub user) maintains it in davila7/claude-code-templates, which has 32,432 GitHub stars. The repository holds 477 skills in this directory. The repository was last updated on October 7, 2026.
Source: davila7/claude-code-templates on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.