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 |
references/human-review.md
View on GitHub---
contract: human-review
version: "1.0"
owner: Malek Okour
reviewed: "2026-08-04"
consumers: [review-csr-pk-consistency]
---
# Human review and prepare-only boundary
## The structural rule
**A skill may open an item. Only a named human may close one.**
This is not a disclaimer. It is a property of the output format: every finding
carries a `disposition` field whose closing values — accepted, or
rejected-with-rationale — can only be written by a person. A register in which
the assistant has closed its own findings is malformed.
## Three named acts
Ownership varies by company, so the accountable owner is a configurable input,
confirmed at the start of the workflow rather than assumed.
1. **Adjudication.** A qualified reviewer, distinct from the document author
where staffing allows, decides for each flagged item whether it is a real
defect. Accepted or rejected-with-rationale — never left implicit.
2. **Execution.** The document owner applies accepted corrections. The skill
proposes; it never writes to the source document.
3. **Closure.** A named person verifies that every item is dispositioned before
the document is finalised, and signs the record.
## Prepare-only
External actions are prepared, never executed. This covers sending, submitting,
publishing, filing, emailing, uploading, committing, and any action that leaves
the user's control.
The skill produces the artefact and stops. A human performs the action.
## Never, regardless of how the request is phrased
- Decide which of two conflicting scientific values is correct.
- Select, adjust, escalate, or stop a dose.
- Draw an efficacy or safety conclusion.
- Interpret a safety signal.
- Make or imply a regulatory commitment.
- Approve, authorise or sign off anything.
- Claim clinical validation, GxP qualification, or regulatory acceptance.
- Represent a mechanical check as a scientific judgement.
A user asking for one of these directly is answered with what the skill *can*
provide — the assembled evidence, both sides of the contradiction, the locators
— plus a plain statement that the decision itself is theirs.
## Sign-off record
Every run produces a sign-off block: who confirmed the accountable owner, who
adjudicated, who executed corrections, who verified closure, and the date. Unset
fields stay visibly unset. A blank sign-off block on a finished document is
itself a finding for the reviewer.
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: 472k | 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 |