xuzhougeng/wisp-science/skills/indication-dossier/SKILL.md
indication-dossier
Generate a therapeutic indication dossier. Covers the patient population, epidemiology, disease biology, standard of care, regulatory precedent, and landmark clinical trials.
- Source repository stars
- 560
- Declared platforms
- 0
- Static risk flags
- 1
- Last source update
- 2026-07-28
- Source checked
- 2026-07-28
Decision brief
What it does—and where it fits
Produces a structured research dossier on a single indication, framed as a patient population: who they are, what's wrong, how they're treated today, and how clinical trials can be designed to help them. Runs as five phases that write resumable waypoint files; after a brief iden…
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/xuzhougeng/wisp-science --skill "skills/indication-dossier"Inspect the Agent Skill "indication-dossier" from https://github.com/xuzhougeng/wisp-science/blob/95d2c13d1665d46a388b5bdc998dcce0d5ec2eee/skills/indication-dossier/SKILL.md at commit 95d2c13d1665d46a388b5bdc998dcce0d5ec2eee. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
Workflow
The dossier is built in five phases. After each phase, write the waypoint file and emit a ≤200-word summary of what you found and what's uncertain, then proceed directly to the next phase. The one exception is Phase 1: after writing meta.json, show the resolved indication identi…
The dossier is built in five phases. After each phase, write the waypoint file and emit a ≤200-word summary of what you found and what's uncertain, then proceed directly to the next phase. The one exception is Phase 1:…Read references/01-meta-initialization.md. Resolve the indication identity: clinical definition, ICD codes, aliases, parent indication, and whether it's a recognized diagnostic entity. Run a quick CT.gov landscape scan.…Read references/02-epidemiology-research.md. Characterize the population: diagnostic criteria, prevalence and incidence, demographics and risk factors, natural history. Use parallel subagents to search PubMed and the we… - 02
Phase 1 — Meta initialization
Read references/01-meta-initialization.md. Resolve the indication identity: clinical definition, ICD codes, aliases, parent indication, and whether it's a recognized diagnostic entity. Run a quick CT.gov landscape scan. Stand up waypoints/meta.json.
Read references/01-meta-initialization.md. Resolve the indication identity: clinical definition, ICD codes, aliases, parent indication, and whether it's a recognized diagnostic entity. Run a quick CT.gov landscape scan.… - 03
Phase 2 — Epidemiology research
Read references/02-epidemiology-research.md. Characterize the population: diagnostic criteria, prevalence and incidence, demographics and risk factors, natural history. Use parallel subagents to search PubMed and the web simultaneously. Write waypoints/epidemiology.json.
Read references/02-epidemiology-research.md. Characterize the population: diagnostic criteria, prevalence and incidence, demographics and risk factors, natural history. Use parallel subagents to search PubMed and the we… - 04
Phase 3 — Biology & standard-of-care research
Read references/03-biology-soc-research.md. Establish pathophysiology, biomarkers, approved therapies, treatment guidelines, and unmet need. Use parallel subagents: PubMed for biology, web for guidelines, FDA for approvals. Write waypoints/biologysoc.json.
Read references/03-biology-soc-research.md. Establish pathophysiology, biomarkers, approved therapies, treatment guidelines, and unmet need. Use parallel subagents: PubMed for biology, web for guidelines, FDA for approv… - 05
Phase 4 — Regulatory & trials research
Read references/04-regulatory-trials-research.md. Establish FDA/EMA accepted endpoints, regulatory precedents, typical trial design parameters, landmark trials, and notable failures. Use parallel subagents: FDA for guidance/approvals, CT.gov for trial patterns, PubMed for trial-…
Read references/04-regulatory-trials-research.md. Establish FDA/EMA accepted endpoints, regulatory precedents, typical trial design parameters, landmark trials, and notable failures. Use parallel subagents: FDA for guid…
Permission review
Static risk signals and limitations
Network access
The documentation includes network, browsing, or remote request actions.
natural history. Use parallel subagents to search PubMed and the webEvidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 77/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 560 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- xuzhougeng/wisp-science
- Skill path
- skills/indication-dossier/SKILL.md
- Commit
- 95d2c13d1665d46a388b5bdc998dcce0d5ec2eee
- License
- AGPL-3.0
- Collected
- 2026-07-28
- Default branch
- main
View the original SKILL.md
Indication Dossier
Produces a structured research dossier on a single indication, framed as a patient population: who they are, what's wrong, how they're treated today, and how clinical trials can be designed to help them. Runs as five phases that write resumable waypoint files; after a brief identity check at the end of Phase 1, the remaining phases run straight through.
Framing
Think of an indication as a patient population. Frame everything from the patient perspective: "Who are these patients?" not "What is this disease?"; "How are these patients identified and managed?" not "What causes this condition?"; population nesting: "all patients in {child} are patients in {parent}".
Some indications don't map to ICD codes or standard disease definitions: "immunosenescence" is a biological state, not a billable diagnosis; "ageing" is not an FDA-accepted indication; "GLP-1 induced sarcopenia" is an iatrogenic population. Note these distinctions explicitly. They matter for regulatory path and trial design.
Inputs
indication(required) — indication name (e.g., "sarcopenia", "idiopathic pulmonary fibrosis").additional_context(optional) — areas to focus on, parent indication, or other framing.workdir(optional) — where to write waypoints and the final report. Defaults to./do_not_commit/indication-dossier-<slug>/.
Tools this skill expects
| Purpose | Tool |
|---|---|
| ClinicalTrials.gov | clinical-trials MCP |
| Literature | pubmed MCP |
| Web | WebSearch, WebFetch — FDA guidance, treatment guidelines (NCCN, AASLD, specialty societies), CDC/WHO epidemiology data |
| Documents | WebFetch for remote PDFs; Read for local PDFs |
| Subagents | Agent for parallel evidence gathering |
If a listed MCP isn't connected, say so and fall back to WebSearch against
the underlying public source (clinicaltrials.gov, pubmed.ncbi.nlm.nih.gov).
Output layout
<workdir>/
└── waypoints/
├── progress.json # loop control
├── meta.json # phase 1
├── epidemiology.json # phase 2
├── biology_soc.json # phase 3
├── regulatory_trials.json # phase 4
├── sources_evaluated.json
├── research_output.json # phase 5 — structured output
└── indication_dossier_report.md # phase 5 — the deliverable
Schemas for every waypoint file are in references/waypoint-schemas.md.
Waypoints are the resumable state. If the workdir already has waypoints, read
them, summarize what's done, and ask which phase to resume from.
Before starting
Read references/00-research-standards.md. It governs sourcing and the
anti-fabrication rules for every phase. Then create <workdir>/waypoints/.
Workflow
The dossier is built in five phases. After each phase, write the waypoint
file and emit a ≤200-word summary of what you found and what's uncertain,
then proceed directly to the next phase. The one exception is Phase 1: after
writing meta.json, show the resolved indication identity and end the turn
with a concise request for Proceed, Revise identity, or Stop. Do
not start the expensive phases until the user answers; Wisp has no separate
interactive-question tool that can be called from the workflow.
Phase 1 — Meta initialization
Read references/01-meta-initialization.md. Resolve the indication identity:
clinical definition, ICD codes, aliases, parent indication, and whether it's
a recognized diagnostic entity. Run a quick CT.gov landscape scan. Stand up
waypoints/meta.json.
Phase 2 — Epidemiology research
Read references/02-epidemiology-research.md. Characterize the population:
diagnostic criteria, prevalence and incidence, demographics and risk factors,
natural history. Use parallel subagents to search PubMed and the web
simultaneously. Write waypoints/epidemiology.json.
Phase 3 — Biology & standard-of-care research
Read references/03-biology-soc-research.md. Establish pathophysiology,
biomarkers, approved therapies, treatment guidelines, and unmet need. Use
parallel subagents: PubMed for biology, web for guidelines, FDA for
approvals. Write waypoints/biology_soc.json.
Phase 4 — Regulatory & trials research
Read references/04-regulatory-trials-research.md. Establish FDA/EMA
accepted endpoints, regulatory precedents, typical trial design parameters,
landmark trials, and notable failures. Use parallel subagents: FDA for
guidance/approvals, CT.gov for trial patterns, PubMed for trial-history
reviews. Write waypoints/regulatory_trials.json.
Phase 5 — Synthesis
Read references/05-synthesis.md and references/06-writing-style.md. Read
all four consolidated waypoint files. Write
waypoints/indication_dossier_report.md — narrative sections in the order
the synthesis reference specifies, with inline citations per the style guide
— and waypoints/research_output.json. No new research threads in this
phase. Targeted gap-fills are allowed: a single fetch to resolve a specific
missing value in an existing waypoint field (an approval year, an NCT ID, a
figure from a sponsor pipeline page). Anything broader than that, name as a
gap rather than filling it.
Resuming
If invoked with a workdir that already contains waypoints: list which phases
are complete (waypoint file exists and is non-empty), show the meta summary,
and ask the user which phase to run next. Never overwrite an existing waypoint
without confirmation.
Alternatives
Compare before choosing
event4u-app/agent-config
design-review
Use when the user says "review the design", "check the UI", or wants a comprehensive UI/UX review. Uses a 7-phase methodology covering interaction, responsiveness, accessibility, and more.
K-Dense-AI/scientific-agent-skills
dask
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
K-Dense-AI/scientific-agent-skills
neurokit2
Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Trigger when code imports neurokit2 or needs its current APIs, schemas, and method-aware validation—not for diagnosis or device validation.
K-Dense-AI/scientific-agent-skills
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.