Pharma Skills

---
name: group-sequential-design
description: >
  Design group sequential clinical trials for survival endpoints (OS, PFS, DFS) with interim analyses,
  spending functions, boundaries, multiplicity, and event/enrollment prediction. Triggers on: Phase 3 trial design, sample size/events for survival endpoints, alpha spending, group sequential design, interim analysis planning, or enrollment/event timeline prediction for clinical trials.
---

## Bundled Resources

| File | What it contains | When to read |
|------|-----------------|--------------|
| `reference.md` | Design guidance, parameter tables, spending functions, key rules, failure modes, analysis framework, protocol references | After collecting user inputs, before writing R code |
| `examples.md` | All R code examples organized by design pattern | When you need code for a specific pattern — read only the relevant section |
| `post_design.md` | IA timing checks (warning messages, user options), verification procedure (pass criteria, lrsim code, log template) | After computing the design (step 6), before delivering |
| `scripts/gsd_report_template.py` | Bundled Python report template — reads gsd_results.json, generates gsd_report.docx with zero hardcoded values | Step 9: copy to output dir and run (or extend for design-specific features) |

Do NOT read these files upfront. Read them only when you reach the corresponding step.

---

## Compact Instructions

When the conversation gets long and context is compressed, preserve information in this priority order:

1. **Architecture decisions** — never re-summarize these; they are settled
2. **Key changes** — what was computed, what parameters were chosen
3. **Current verification status** — pass/fail only, drop verbose logs
4. **Tool outputs** — can be deleted; keep only essential numbers (events, boundaries, power, sample size)

---

## Workflow

**Task Progress Tracking:** At the start of step 6 (after user confirms inputs), create a task checklist using `TaskCreate` for all remaining steps. Mark each task `in_progress` when starting and `completed` when done. Typical tasks:
1. Write and run R design script (gsd_design.R)
2. Check IA timing constraints
3. Run verification simulation (gsd_verification.R)
4. Generate Word report (gsd_report.py)

This gives the user a visual progress indicator (spinner → checkmark) throughout the computation.

**Pacing — one artifact per turn.** Do not bundle multiple major artifacts into a single response. Each of these is its own turn:
- Writing `gsd_design.R` (then stop — let the tool result come back)
- Running `gsd_design.R` (then stop)
- Writing `gsd_verification.R`