malekokour/clinpharm-pmx-skills / skills/assess-development-plan-gaps
assess-development-plan-gaps
VerifiedAssesses a clinical pharmacology development plan against guidance-anchored evidence expectations, classifying every expected element as present, triggered, waivable-with-rationale, or a residual gap, each traced to the criterion that creates the obligation. Use this skill when someone asks what clinical pharmacology evidence a programme is still missing, whether a plan covers what a reviewer will expect, or which studies the drug's own properties have made obligatory — for example "what CP work are we still missing before the pre-NDA meeting" or "does this plan cover the renal and hepatic expectations". Do not use for reviewing one interaction package, for assembling agency-facing briefing content, or for any request to decide whether a gap is acceptable, to commit to a study, or to approve a plan.
| File | Kind | Size |
|---|---|---|
| PASTE.md | markdown | 22.4 KB |
| README.md | markdown | 7.8 KB |
| SKILL.md | skill md | 22.7 KB |
| assets/guidance-index.md | markdown | 5.2 KB |
| references/development-extension-modes.md | markdown | 5.4 KB |
| references/evidence-hierarchy.md | markdown | 2.7 KB |
| references/human-review.md | markdown | 2.4 KB |
| references/output-states.md | markdown | 2.5 KB |
| references/source-preflight.md | markdown | 2.8 KB |
| scripts/assess_coverage.pyexecutable | script | 3.0 KB |
| scripts/findings.py | script | 4.7 KB |
| scripts/public_development_intelligence.pyexecutable | script | 15.9 KB |
| scripts/renal_staging.pyexecutable | script | 1.7 KB |
scripts/assess_coverage.py
View on GitHub#!/usr/bin/env python3
"""Check a clinical pharmacology development plan for the study types a programme is normally expected to address.
Emits mechanical findings only. Both sides of every conflict are preserved with
their locators; this script never decides which is correct.
Author: Malek Okour
Dependencies: Python standard library only
"""
from __future__ import annotations
import argparse
import re
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent))
from findings import Finding, Report
REQUIRED = [
("single ascending dose", r"single[- ]ascending|\bsad\b"),
("multiple ascending dose", r"multiple[- ]ascending|\bmad\b"),
("food effect", r"food[- ]effect|fed[/ ]fasted"),
# Accept the three deliberate prose separators only. The synthetic plan uses
# an en dash; allowing arbitrary punctuation would weaken this into a fuzzy
# match and could hide a genuinely absent interaction section.
("drug-drug interaction", r"drug(?:-|–| )drug interaction|\bddi\b"),
("renal impairment", r"renal impairment"),
("hepatic impairment", r"hepatic impairment"),
("QT assessment", r"\bqt\b|thorough qt|cardiac repolarisation"),
("mass balance / ADME", r"mass balance|\badme\b|human radiolabel"),
("population PK", r"population pk|\bpoppk\b|nonlinear mixed"),
("exposure-response", r"exposure[- ]response|\be-r\b"),
]
def run(ns) -> Report:
text = read(ns.plan).lower()
report = Report(tool="assess_coverage")
report.count("required study types", len(REQUIRED))
present = 0
for name, pattern in REQUIRED:
if re.search(pattern, text):
present += 1
else:
report.add(Finding(
rule="required-element-absent",
severity="Major",
item=name,
observed="not found",
expected="an explicit statement addressing this item",
locator="whole document",
detail="Absence is reported as absence. A missing element is not assumed "
"to be covered elsewhere or intentionally omitted.",
))
report.count("study types present", present)
if present == 0:
report.cannot_assess(
"coverage assessment",
"none of the expected elements were found, which usually means the wrong "
"document was supplied",
"the document this checker targets",
)
return report
def read(path: str) -> str:
return Path(path).read_text(encoding="utf-8", errors="replace")
def main() -> int:
parser = argparse.ArgumentParser(description=__doc__.split("\n")[0])
parser.add_argument("--plan", required=True, help="document text")
parser.add_argument("--json", action="store_true", help="machine-readable output")
ns = parser.parse_args()
report = run(ns)
print(report.render(as_json=ns.json))
return 1 if any(f.severity == "Critical" for f in report.findings) else 0
if __name__ == "__main__":
raise SystemExit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |