malekokour/clinpharm-pmx-skills / skills/review-adc-analyte-strategy
review-adc-analyte-strategy
VerifiedReviews the analyte strategy for an antibody-drug conjugate — which analytes are measured, how each is defined, whether the set supports the exposure questions the programme asks, and whether reported parameters are internally consistent across analytes. Use this skill when someone asks to review, QC, or check the PK characterisation plan or results for an ADC or other multi-analyte modality — for example "does this analyte set support a DAR-shift question" or "check that total antibody and conjugated payload are consistently defined across these documents". Do not use to select an analyte strategy, to decide whether an analyte is scientifically necessary, to review bioanalytical method validation, or to review a single-analyte small-molecule programme.
| File | Kind | Size |
|---|---|---|
| PASTE.md | markdown | 12.4 KB |
| README.md | markdown | 2.8 KB |
| SKILL.md | skill md | 12.7 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/analyte_consistency.pyexecutable | script | 7.5 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: 323k | 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: 323k | 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: 323k | Updated | Claude CodeCodex | Verified | Install |