aipoch/open-science / resources/skills/indication-dossier
indication-dossier
VerifiedGenerate a therapeutic indication dossier. Covers the patient population, epidemiology, disease biology, standard of care, regulatory precedent, and landmark clinical trials.
| File | Kind | Size |
|---|---|---|
| .catalog_stamp | other | 13 B |
| SKILL.md | skill md | 6.4 KB |
| references/00-research-standards.md | markdown | 3.0 KB |
| references/01-meta-initialization.md | markdown | 1.7 KB |
| references/02-epidemiology-research.md | markdown | 2.1 KB |
| references/03-biology-soc-research.md | markdown | 2.3 KB |
| references/04-regulatory-trials-research.md | markdown | 3.1 KB |
| references/05-synthesis.md | markdown | 5.2 KB |
| references/06-writing-style.md | markdown | 1.7 KB |
| references/waypoint-schemas.md | markdown | 2.9 KB |
references/01-meta-initialization.md
View on GitHub# Phase 1 — Meta initialization
**When:** first phase, or `waypoints/meta.json` doesn't exist.
## Objective
Resolve indication identity and gather basic context.
This is the foundation for all subsequent phases.
## Actions
**Step 1: Setup**
```bash
mkdir -p "<workdir>/waypoints"
```
**Step 2: Resolve indication identity**
- WebSearch for the indication name to confirm:
- Standard clinical definition (if one exists)
- ICD-10 codes (if applicable)
- Common aliases and alternative names
- Whether this is a recognized diagnostic entity or a biological state/concept
- Note: some indications are not standard diagnoses (e.g., "immunosenescence",
"ageing", "GLP-1 induced sarcopenia") — document this explicitly
**Step 3: Establish hierarchy**
- Identify the parent indication from the input (additional_context may contain this)
- Understand where this fits in the clinical taxonomy (therapy area, condition class)
- Note cross-cutting classifications if applicable
**Step 4: Quick trial landscape scan**
- Use clinical-trials MCP to search for trials: `search_trials(condition="[indication name]")`
- Record total count, phase distribution, and status distribution
- This gives a rough sense of how mature the indication is clinically
**Step 5: Write outputs**
- Write `waypoints/meta.json` with indication identity
- Initialize `waypoints/sources_evaluated.json`
## Guidance
- This phase should complete in a single iteration
- If the indication has no ICD codes or standard definition, note this clearly —
it affects every downstream section (epidemiology data will be scarce,
regulatory path will be novel)
- Output references: see `references/waypoint-schemas.md` for `meta.json` format
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |