Deep Research
jordan-gibbs/hyperresearch
Deep research with hyperresearch, for Claude Code and OpenAI Codex.
Build a sourced research dossier for one therapeutic indication — patient population, epidemiology, disease biology, standard of care, regulatory path, and landmark trials.
Install Indication Dossier
$ npx skills add xuzhougeng/wisp-science --skill indication-dossier -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xuzhougeng/wisp-science indication-dossier --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/xuzhougeng/wisp-science.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/indication-dossier .claude/skills/indication-dossier && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "indication-dossier" agent skill from https://github.com/xuzhougeng/wisp-science/tree/main/skills/indication-dossier into .claude/skills/indication-dossier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indication-dossier", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/xuzhougeng/wisp-science/tree/main/skills/indication-dossierType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add xuzhougeng/wisp-science --skill indication-dossier -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xuzhougeng/wisp-science indication-dossier --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xuzhougeng/wisp-science.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/indication-dossier .agents/skills/indication-dossier && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "indication-dossier" agent skill from https://github.com/xuzhougeng/wisp-science/tree/main/skills/indication-dossier into .agents/skills/indication-dossier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indication-dossier", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xuzhougeng/wisp-science --skill indication-dossier -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xuzhougeng/wisp-science indication-dossier --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xuzhougeng/wisp-science.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/indication-dossier .cursor/skills/indication-dossier && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "indication-dossier" agent skill from https://github.com/xuzhougeng/wisp-science/tree/main/skills/indication-dossier into .cursor/skills/indication-dossier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indication-dossier", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/xuzhougeng/wisp-science.git --path skills/indication-dossier--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add xuzhougeng/wisp-science --skill indication-dossier -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xuzhougeng/wisp-science indication-dossier --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xuzhougeng/wisp-science.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/indication-dossier .gemini/skills/indication-dossier && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "indication-dossier" agent skill from https://github.com/xuzhougeng/wisp-science/tree/main/skills/indication-dossier into .gemini/skills/indication-dossier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indication-dossier", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install xuzhougeng/wisp-science indication-dossierInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add xuzhougeng/wisp-science --skill indication-dossier -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xuzhougeng/wisp-science.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/indication-dossier .github/skills/indication-dossier && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "indication-dossier" agent skill from https://github.com/xuzhougeng/wisp-science/tree/main/skills/indication-dossier into .github/skills/indication-dossier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indication-dossier", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xuzhougeng/wisp-science --skill indication-dossier -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xuzhougeng/wisp-science indication-dossier --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xuzhougeng/wisp-science.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/indication-dossier .opencode/skills/indication-dossier && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "indication-dossier" agent skill from https://github.com/xuzhougeng/wisp-science/tree/main/skills/indication-dossier into .opencode/skills/indication-dossier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indication-dossier", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
indication-dossier- GitHub stars
- 1k
- Token cost
- ~1k tokens
- SKILL.md length
- 411 words
- Files
- 4 (incl. references)
- Skills in repo
- 25
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Build a sourced research dossier for one therapeutic indication — patient population, epidemiology, disease biology, standard of care, regulatory path, and landmark trials.
- Works in 5 steps: Identity. Resolve definition, ICD codes,… → Epidemiology. Case definition,… → Biology & standard of care. Mechanism,… → …
- The user asks for an indication overview
- SKILL.md covers The framing rule, Inputs, Tooling and Run protocol, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Indication Dossier is an agent skill from xuzhougeng/wisp-science. Build a sourced research dossier for one therapeutic indication — patient population, epidemiology, disease biology, standard of care, regulatory path, and landmark trials. Use when the user asks for an indication overview, disease landscape, or trial-design background.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/phases.md`, `references/standards.md` and `references/waypoints.md`).
It sits in Research & Science. It works with Model Context Protocol. The repository describes itself as: Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models. The licence is Apache-2.0.
When your agent uses it
- The user asks for an indication overview
- Disease landscape
- Trial-design background
Example prompts
- “/indication-dossier”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Identity. Resolve definition, ICD codes, aliases, parent, diagnostic
- Epidemiology. Case definition, prevalence/incidence, demographics,
- Biology & standard of care. Mechanism, biomarkers, approved
- Regulatory & trials. Accepted endpoints, precedents, design
- Synthesis. No new research threads (single targeted gap-fills only).
What it can do on your machine
Read from SKILL.md and the folder at commit 2ba143b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Indication Dossier loads about 1k tokens when it runs, and up to ~4.5k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 411 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from xuzhougeng/wisp-science at commit 2ba143b, republished under its Apache-2.0 licence (© xuzhougeng). 411 words, ~1,011 tokens.
Download SKILL.mdSave it as
.claude/skills/indication-dossier/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- indication-dossier
- description
- Build a sourced research dossier for one therapeutic indication — patient population, epidemiology, disease biology, standard of care, regulatory path, and landmark trials. Use when the user asks for an indication overview, disease landscape, or trial-design background.
- license
- Apache-2.0
Indication dossier
Five research phases, each writing one waypoint JSON under
<workdir>/waypoints/, ending in a cited Markdown report. Waypoints make the
run resumable: a later invocation reads which files exist and continues from
the first missing one. The only pause for user input is after Phase 1.
The framing rule
Treat the indication as a patient population, not a disease entry. Every section answers a population question — who are these patients, how are they identified and managed, which trials would help them — rather than a textbook question about the condition. Nesting is population nesting: everyone in the child indication is in the parent.
Some inputs are not billable diagnoses at all: a biological state ("immunosenescence"), a non-accepted indication ("ageing"), an iatrogenic population ("GLP-1 induced sarcopenia"). Detect and label this early — it changes the epidemiology evidence base, the regulatory path, and what a "complete" dossier even looks like.
Inputs
| Input | Required | Meaning |
|---|---|---|
indication | yes | e.g. "sarcopenia", "idiopathic pulmonary fibrosis" |
additional_context | no | focus areas, parent indication, framing |
workdir | no | waypoint/report location; default ./do_not_commit/indication-dossier-<slug>/ |
Tooling
Preferred: clinical-trials MCP for CT.gov, pubmed MCP for literature,
WebSearch/WebFetch for FDA guidance, specialty-society guidelines
(NCCN, AASLD, …), and CDC/WHO data; WebFetch for remote PDFs, Read for
local ones; Agent subagents for parallel evidence gathering. When a listed
MCP is not connected, say so and fall back to WebSearch against the public
site itself.
Show full SKILL.md (186 more words)Show less
Run protocol
Read references/standards.md first — it defines what counts as a citable
finding, the anti-fabrication rules, and the report style. Phase-by-phase
instructions live in references/phases.md; waypoint formats in
references/waypoints.md.
- Identity. Resolve definition, ICD codes, aliases, parent, diagnostic
status; quick CT.gov landscape count. Write
meta.json. Then show the resolved identity and end the turn asking Proceed / Revise identity / Stop — the expensive phases wait for the answer (Wisp has no separate interactive-question tool, so this is a normal turn end). - Epidemiology. Case definition, prevalence/incidence, demographics,
natural history →
epidemiology.json. - Biology & standard of care. Mechanism, biomarkers, approved
therapies, guidelines, unmet need →
biology_soc.json. - Regulatory & trials. Accepted endpoints, precedents, design
parameters, landmark trials, failures →
regulatory_trials.json. - Synthesis. No new research threads (single targeted gap-fills only).
Write
indication_dossier_report.mdandresearch_output.json, then markprogress.jsoncomplete.
After each of phases 2–5, write the waypoint, emit a ≤200-word summary of findings and open uncertainties, and continue directly.
Resuming
When workdir already contains waypoints: list which phases are complete
(file exists and is non-empty), show the meta summary, and ask which phase to
run. Never overwrite an existing waypoint without confirmation.
Output layout
<workdir>/waypoints/
├── progress.json # loop control, flipped last
├── meta.json # phase 1
├── epidemiology.json # phase 2
├── biology_soc.json # phase 3
├── regulatory_trials.json # phase 4
├── sources_evaluated.json # appended by every phase
├── research_output.json # phase 5, structured
└── indication_dossier_report.md # phase 5, the deliverable© xuzhougeng, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in skills/indication-dossier of xuzhougeng/wisp-science.
- SKILL.md
- references/phases.md
- references/standards.md
- references/waypoints.md
Open the folder on GitHubat commit 2ba143b
Compare with similar skills
Indication Dossier next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Indication Dossier this skillxuzhougeng/wisp-science | 1k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Deep Researchjordan-gibbs/hyperresearch | 3.8k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Annotate Paper54yyyu/zotero-mcp | 5.3k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Paper Searchopenags/paper-search-mcp | 2.8k | — | ~1.2k | Automated safety check: Notes | MIT | |
| NSFC Literature Review WriterHuiyuLi-2000/Chinese-Grant-Writer-Skills | 439 | 1 repos | ~1.4k | Automated safety check: Notes | MIT | |
| Arxiv MCP Serverblazickjp/arxiv-mcp-server | 3.2k | — | ~353 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Annotate Paper
54yyyu/zotero-mcp
Read the open paper and write study annotations into its PDF with zotero-cli - a context box on the title, a four-part summary on the abstract, role-coded abstract highlights, one box per figure…
Paper Search
openags/paper-search-mcp
Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc).
NSFC Literature Review Writer
HuiyuLi-2000/Chinese-Grant-Writer-Skills
Writes the research-status literature review and critique section of an NSFC grant proposal, backed by a bundled multi-source literature search.
Arxiv MCP Server
blazickjp/arxiv-mcp-server
A skill your agent uses when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or…
Nature Academic Search
wp-a/nature-academic-search
A skill your agent uses when users ask to 找文献、做文献检索、查论文、查临床试验、核验引用、去重文献、设计 PubMed/MeSH 检索式、追踪上下游引文、解析 DOI/PMID/PMCID/arXiv/OpenAlex/Semantic Scholar/NCT ID， 或导出 RIS、BibTeX、NBIB、ENW；also use for…
More from xuzhougeng/wisp-science
All 25 skills in this repoSinglecell Qc
xuzhougeng/wisp-science
A skill your agent uses when designing, reviewing, or implementing single-cell RNA-seq QC in Python or R with a human-in-the-loop, data-driven approach.
Research Integrity Audit
xuzhougeng/wisp-science
学术审查 / research-integrity screening of a manuscript's figures and reported numbers.
Distill Concept Books
xuzhougeng/wisp-science
将概念、理论或分析方法类图书蒸馏为证据可追溯、经人工门禁审核且不暴露书名、作者、出版社等来源身份的任务型 Skill 候选。用于新建或恢复图书蒸馏、以本地 Tesseract 扫描 DOCX 全部内嵌图像或 Poppler 渲染的扫描 PDF 全页、建立 source map 与 evidence/claim/relation/capability…
Skill Creator
xuzhougeng/wisp-science
Create, update, validate, and evaluate Wisp skills. An agent skill from xuzhougeng/wisp-science.
Word Zotero Citations
xuzhougeng/wisp-science
Build, audit, authorize, recover, or finalize dynamic Zotero citations and bibliographies in Microsoft Word DOCX files with a protected-source, digest-bound workflow.
Compute Env Setup
xuzhougeng/wisp-science
Set up and validate a reproducible Python or R environment on a Wisp execution context.
Related
Works with
Categories
Questions about Indication Dossier
What does Indication Dossier do?
Build a sourced research dossier for one therapeutic indication — patient population, epidemiology, disease biology, standard of care, regulatory path, and landmark trials. Indication Dossier is an agent skill from xuzhougeng/wisp-science. Build a sourced research dossier for one therapeutic indication — patient population, epidemiology, disease biology, standard of care, regulatory path, and landmark trials.
When should I use Indication Dossier?
Indication Dossier fits situations like: the user asks for an indication overview; disease landscape; trial-design background.
How do I install Indication Dossier in Claude Code?
Run `npx skills add xuzhougeng/wisp-science --skill indication-dossier -a claude-code`. Or copy the skill folder (skills/indication-dossier in xuzhougeng/wisp-science) into .claude/skills/indication-dossier in your project. Claude Code loads it when a task matches its description.
How do I install Indication Dossier in Codex?
Run `npx skills add xuzhougeng/wisp-science --skill indication-dossier -a codex`. Or copy the skill folder (skills/indication-dossier in xuzhougeng/wisp-science) into .agents/skills/indication-dossier in your project. Codex loads it when a task matches its description.
Can I use Indication Dossier in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xuzhougeng/wisp-science --skill indication-dossier -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/indication-dossier, .gemini/skills/indication-dossier, .github/skills/indication-dossier and .opencode/skills/indication-dossier in your project.
What does Indication Dossier need to run?
SKILL.md names no scripts, command-line tools or credentials: Indication Dossier is instructions for the agent only.
Does Indication Dossier access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Indication Dossier safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Indication Dossier use?
Indication Dossier is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Indication Dossier use?
About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.5k tokens, read only when the agent opens those files.
What are the alternatives to Indication Dossier?
Skills that share tags, products or a category with Indication Dossier: Deep Research (jordan-gibbs/hyperresearch, 3.8k stars), Annotate Paper (54yyyu/zotero-mcp, 5.3k stars), Paper Search (openags/paper-search-mcp, 2.8k stars) and NSFC Literature Review Writer (HuiyuLi-2000/Chinese-Grant-Writer-Skills, 439 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Indication Dossier?
xuzhougeng (a GitHub user) maintains it in xuzhougeng/wisp-science, which has 1,026 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 10, 2026.
Source: xuzhougeng/wisp-science on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.