clinical-research-orchestra
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/drtranquanghung91-vn--clinical-research-orchestra)HTML
<a href="/listings/drtranquanghung91-vn--clinical-research-orchestra"><img src="/api/listings/drtranquanghung91-vn--clinical-research-orchestra/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Claude Code
/plugin marketplace add drtranquanghung91-vn/clinical-research-orchestra /plugin install phi-guard@clinical-research-orchestra /plugin install orchestra@clinical-research-orchestra
Then start a project:
/orchestra:start
Tools the scripts use
Python 3.10 or later. The harness scripts use the standard library only. Literature lookups call the public PubMed, Europe PMC and Crossref APIs; no API key is needed. Analysis scripts written by `statistical-analysis` need `pandas`, `scipy` and `statsmodels` (`lifelines` for Cox models): `python -m pip install pandas scipy statsmodels openpyxl lifelines`.
Optional, for presenting (P3): `matplotlib` for figures, `python-pptx` for the defence deck and the poster PPTX (`python -m pip install matplotlib python-pptx`), and Google Chrome or Microsoft Edge (headless) for the poster PDF, PNG and print preflight. A script that needs a missing one prints the install hint and exits 2; the skills report that check as not run.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 20 lines
- {
- "name": "clinical-research-orchestra",
- "owner": { "name": "Trần Quang Hưng" },
- "metadata": {
- "description": "Evidence-first Claude Code plugins for clinical research: question, evidence, protocol, analysis, manuscript, thesis, poster and defence.",
- "version": "0.4.0"
- },
- "plugins": [
- {
- "name": "phi-guard",
- "source": "./plugins/phi-guard",
- "description": "Blocks patient identifiers from leaving the machine through MCP, WebFetch or WebSearch; de-identifies CSV/XLSX files. Install first."
- },
- {
- "name": "orchestra",
- "source": "./plugins/orchestra",
- "description": "Research lifecycle skills: question, literature, appraisal, protocol, sample size, analysis, manuscript, thesis, poster and defence, with verified references and checked numbers."
- }
- ]
- }
README.md · README · 232 lines
- <h1 align="center">Clinical Research Orchestra: A Multi-Agent Harness for<br>Evidence-First Clinical Research</h1>
- <p align="center">
- <b>From bedside question to podium, with every citation and number checked.</b><br>
- Claude Code plugins that take medical students, residents, doctors and other healthcare
- professionals through a research project: question, evidence, protocol, analysis,
- manuscript or thesis, poster and defence.
- </p>
- <p align="center">
- <a href="LICENSE"><img alt="MIT licence" src="https://img.shields.io/badge/licence-MIT-0F5E7A"></a>
- <img alt="Claude Code" src="https://img.shields.io/badge/Claude%20Code-plugin-C8372D">
- <img alt="Languages" src="https://img.shields.io/badge/languages-English%20%7C%20Vietnamese-56677F">
- <img alt="Status" src="https://img.shields.io/badge/status-0.4.0%20present-B7791F">
- <a href="https://github.com/drtranquanghung91-vn/clinical-research-orchestra/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/drtranquanghung91-vn/clinical-research-orchestra/actions/workflows/ci.yml/badge.svg"></a>
- </p>
- > **Status: early.** Version 0.4.0 adds the P3 "present" skills (figures, conference abstract,
- > print poster in three layouts with preflight, thesis-defence deck with rehearsal questions, prose
- > humanizer, consistency audit) to the P2 "analyse and report results" skills (data
- > preparation, statistical analysis per the SAP, results writing with a Chapter 3 .docx), the
- > P1 "plan the study" skills (research question, literature search, critical appraisal, guideline
- > check, literature review, protocol design, sample size and SAP) and the 0.1.0 foundation (project
- > folder, ledgers, gates, reference verification and patient-data protection). Manuscript and thesis
- > writing skills arrive phase by phase; see [Roadmap](#roadmap). A simulated project run through
- > every P1, P2 and P3 skill is in [`examples/fictional-cohort/`](examples/fictional-cohort/). Do not
- > rely on it for real studies yet.
- ---
- ## Why this exists
- Ask a general-purpose agent to "write the literature review for my thesis" or "calculate the
- sample size" and you get fluent text in minutes. It is often wrong in the ways that a
- supervisor, an ethics committee or a journal reviewer will catch:
- - **References are recalled, not retrieved.** A PMID or DOI "from memory" ends up in the
- reference list, or a real paper is cited for a claim it does not make.
- - **Numbers drift.** 85% in the abstract, 86.3% in the results; a sample size of "≈26"
- that was never rounded up; a confidence-interval bound used in place of the point estimate.
- - **The review is a list of papers.** Chapter 1 reads "Smith found… Nguyen found…" instead
- of a synthesis organised by question.
- - **Patient data leaks.** A name, a national ID number or a record number goes into a web
- search or an external tool.
- - **The prose sounds machine-written**, and nothing says how AI was used.
- Clinical Research Orchestra turns these steps into a method with files, checks and gates,
- in the spirit of [Superpowers](https://github.com/obra/superpowers) and
- [PaperOrchestra](https://github.com/google-research/paper-orchestra). The agent reasons;
- scripts measure. Anything a script can verify (an identifier, a number, a sample-size
- calculation, a poster's print resolution) is not left to the model's word.
- ## How it works
- Every project lives in one folder with stage directories (`01_question/` to `07_present/`),
- ledgers for references, results and claims, and four human gates:
- | Gate | Stops before | You decide |
- |---|---|---|
- | G1 Question | searching and protocol work | the research question, PICO/PECO and objectives |
- | G2 Protocol | data collection | design, eligibility, variables, sample size, analysis plan |
- | G3 Results lock | writing | the analysis outputs, locked with a SHA-256 hash |
- | G4 Release | sending anything out | the manuscript, thesis, poster or deck after all checks pass |
- Skills hand work forward through these files, not through the conversation, so you can
- enter at any stage (a thesis already half written, a poster due next week) and resume later
- with `/orchestra:status`. A gate can be waived only with a written reason in `decisions.md`.
- Two plugins ship from this marketplace:
- - **`orchestra`**: the research skills, commands, scripts and reference library.
- - **`phi-guard`**: a hook that scans outbound tool calls (web search, fetch, MCP tools,
- network commands) for patient identifiers and blocks or asks, plus a
- `deidentify-data` skill for CSV and Excel files. Install it on its own if you only want
- the protection.
- ## The skills
- | Stage | Skill | What it produces | Phase |
- |---|---|---|---|
- | 0 | `research-project-setup`, `/orchestra:start`, `/orchestra:status` | project folder, ledgers, gates, next step | 0.1.0 |
- | 0 | `deidentify-data` (phi-guard) | de-identified data file and a separate key file | 0.1.0 |
- | 1 | `research-question` | PICO/PECO, FINER check, objectives, hypotheses, title options | 0.2.0 |
- | 2 | `literature-search` | nomenclature check, search strategy, verified references, evidence table and map, gaps | 0.2.0 |
- | 2 | `critical-appraisal`, `/orchestra:appraise` | appraisal by the study's real design, with the matching tool | 0.2.0 |
- | 2 | `guideline-check` | current clinical and reporting guidelines, each with version and date | 0.2.0 |
- | 2 | `literature-review`, `/orchestra:review` | thesis Chapter 1 or manuscript background, synthesised by question (`review_lint.py`, `cite_render.py`) | 0.2.0 |
- | 3 | `protocol-design` | design with trade-offs, eligibility, variables table, bias and confounding | 0.2.0 |
- | 3 | `sample-size-sap` | sample size with a sensitivity table (`samplesize.py`) and a statistical analysis plan with an analysis register | 0.2.0 |
- | 4 | `data-preparation` | codebook, data audit, cleaning log, de-identified data in `04_data/` | 0.3.0 |
- | 4 | `statistical-analysis`, `/orchestra:analyze` | analysis per the SAP register with a vendored `crostats.py`, or SPSS/Stata/R output imported; declared post-hoc analyses; results ledger (`analysis_plan.py`, `results_ledger.py`) | 0.3.0 |
- | 5 | `results-writing`, `/orchestra:results` | thesis Chapter 3 or manuscript Results from the locked ledger, with .docx (`render_results.py`, `check_numbers.py`, `build_docx.py`) | 0.3.0 |
- | 4 | `research-figures` | forest plot, Kaplan–Meier with numbers at risk, rates chart, STROBE/CONSORT flow from the locked ledger or the de-identified data (`figures.py`) | 0.4.0 |
- | 6 | `conference-abstract` | structured abstract within the word limit, every number a ledger placeholder (`lint_prose.py --count-words`, `check_numbers.py`) | 0.4.0 |
- | 6 | `research-poster`, `/orchestra:poster` | print poster in three layouts (editorial, pathway, figure-led) as PDF, PNG and PPTX, with print preflight (`poster_build.py`, `poster_preflight.py`) | 0.4.0 |
- | 6 | `defense-prep`, `/orchestra:defense` | consistency audit before any slide, thesis-defence deck, committee questions (`consistency_audit.py`, `pptx_from_spec.py`, `check_pptx.py`) | 0.4.0 |
- | 5–6 | `prose-humanizer` | rewrites AI-sounding prose, keeps every number, citation and hedge (`lint_prose.py`, `invariants.py`) | 0.4.0 |
- | 5–6 | agents `consistency-auditor`, `committee-simulator` | numbers, dates and terms checked across deliverables; likely committee or reviewer questions with answers from the project files | 0.4.0 |
- | 5 | `manuscript`, `thesis`, `case-report`, `systematic-review` | manuscript and thesis .docx, CARE case report, PRISMA review | P4 |
- | 3, 7 | `ethics-and-crf`, `journal-selection`, `reviewer-response` | ethics dossier and CRF, journal shortlist, response to reviewers | P5 |
- You can talk to the skills in Vietnamese or English. The language of research documents is
- a project setting (`project.yaml → language.output`), so a thesis can be written in
- Vietnamese while the manuscript from the same study is in English.
- ## What makes it different
- - **Verified references only.** Every reference enters through `search_lit.py add` and is
- checked by `verify_refs.py` against PubMed, Europe PMC or Crossref. Citations in text use
- `[@id]` keys that must exist in the ledger, and `cite_render.py` numbers them in Vancouver
- style from the ledger. A source with no PMID or DOI enters only as an author-supplied record
- (`add-manual`) and is listed as MANUAL, never as verified.
- - **Numbers from files.** Results come from a results ledger, not from the model's memory, and a
- sample size comes from `samplesize.py` with a sensitivity table, every parameter sourced or
- labelled as an assumption.
- Results enter text only as `{{R-…}}` placeholders filled from the locked ledger, and
- `check_numbers.py` blocks any typed number the ledger does not hold, at its printed precision (see
- `judgement-defaults.md`). `consistency_audit.py`
- flags numbers, dates and terms that disagree between the thesis, abstract, poster and slides.
- - **Patient data protected by default.** `phi-guard` knows Vietnamese identifier formats
- (CCCD/CMND, BHYT, record numbers, labelled names, dates of birth, addresses) as well as
- phones and emails. Detection is heuristic and not proof that a text is clean.
- - **Tested like code.** Unit tests for every script, and behaviour scenarios that were run
- first without the skills (RED) and then with them (GREEN).
- - **Honest about AI.** Manuscripts and theses get an AI-use disclosure; the humanizer
- removes tells of machine prose without hiding that AI helped.
- ## Install
- ### Claude Code
- ```
- /plugin marketplace add drtranquanghung91-vn/clinical-research-orchestra
- /plugin install phi-guard@clinical-research-orchestra
- /plugin install orchestra@clinical-research-orchestra
- ```
- Then start a project:
- ```
- /orchestra:start
- ```
- ### Tools the scripts use
- Python 3.10 or later. The harness scripts use the standard library only. Literature lookups call
- the public PubMed, Europe PMC and Crossref APIs; no API key is needed. Analysis scripts written by
- `statistical-analysis` need `pandas`, `scipy` and `statsmodels` (`lifelines` for Cox models):
- `python -m pip install pandas scipy statsmodels openpyxl lifelines`.
- Optional, for presenting (P3): `matplotlib` for figures, `python-pptx` for the defence deck and the
- poster PPTX (`python -m pip install matplotlib python-pptx`), and Google Chrome or Microsoft Edge
- (headless) for the poster PDF, PNG and print preflight. A script that needs a missing one prints the
- install hint and exits 2; the skills report that check as not run.
- ## Roadmap
- | Phase | Scope | State |
- |---|---|---|
- | P0 Foundation | project folder, ledgers, gates, `phi-guard`, `verify_refs.py`, `search_lit.py`, CI | done (0.1.0) |
- | P1 Plan the study | research question, literature search, appraisal, guideline check, literature review, protocol, sample size and SAP | done (0.2.0) |
- | P2 Analyse and report results | data preparation, statistical analysis (run and import), results ledger, results writing, Chapter 3 .docx | done (0.3.0) |
- | P3 Present | figures, conference abstract, poster with print preflight, defence deck, prose humanizer, consistency audit | done (0.4.0) |
- | P4 Write | manuscript, thesis, case report, systematic review | next |
- | P5 Extend | ethics and CRF, journal selection, reviewer response, Codex and Antigravity packaging | planned |
- The design spec is in [`docs/superpowers/specs/`](docs/superpowers/specs/) and each phase
- has its implementation plan in [`docs/superpowers/plans/`](docs/superpowers/plans/).
- ## Repository layout
- ```
- .claude-plugin/marketplace.json marketplace manifest (plugins: orchestra, phi-guard)
- plugins/orchestra/ research skills, commands, scripts/, templates/project/
- plugins/phi-guard/ outbound PHI hook, phi_scan.py, deidentify.py, deidentify-data skill
- examples/fictional-cohort/ a simulated project run through every P1 and P2 skill, with its checks
- tests/unit/ tests for every script
- tests/scenarios/ RED/GREEN behaviour scenarios and the baseline record
- tools/lint_skills.py skill frontmatter and length checks
- docs/superpowers/ design spec and phase plans
- AGENTS.md conventions for agents working on this repository
- ```
- ## Testing
- ```bash
- python -m unittest discover -s tests/unit -v
- python tools/lint_skills.py
- ```
- CI runs both on Linux and Windows with Python 3.10 and 3.12 on every push.
- The skills are written test-first, as Superpowers prescribes. Each behaviour is first run on
- an agent without the plugin, and the failures are recorded in
- [`tests/scenarios/BASELINE.md`](tests/scenarios/BASELINE.md). The skills are then written to
- fix those failures and the scenarios re-run with them loaded
- ([`tests/scenarios/README.md`](tests/scenarios/README.md)).
- ## Authors
- - **Trần Quang Hưng**: owner, architecture, harness and scripts.
- - **Amelia Le** ([@ngoclnl189-amelia](https://github.com/ngoclnl189-amelia)): co-author of the research-methods skills (research question, literature and
- evidence, critical appraisal, protocol design, sample size and SAP) and their reference
- material.
- See [CONTRIBUTORS.md](CONTRIBUTORS.md).
- ## Acknowledgements
- - [google-research/paper-orchestra](https://github.com/google-research/paper-orchestra):
- outline-as-plan, two-stage citation verification, reviewer accept/revert loop (ideas only;
- no code or prompt text copied)
- - [obra/superpowers](https://github.com/obra/superpowers): skills as methodology, TDD for
- skills, subagent-driven development
- - [drtranquanghung91-vn/grand-rounds](https://github.com/drtranquanghung91-vn/grand-rounds):
- the literature API client, reference verification and PHI patterns this harness builds on;
- use it for medical talks beyond the thesis-defence path
- - The `humanizer` skill: the pattern catalog behind `prose-humanizer`
- Details and licences are in [NOTICE.md](NOTICE.md).
- ## Disclaimer
- Clinical Research Orchestra helps plan, write and present research. It does not give medical
- advice and does not replace a supervisor, a statistician or an ethics committee. The author
- is responsible for the study, for checking every claim against its source, for ethics
- approval and patient consent, for de-identifying data, and for disclosing AI use as their
- institution and journal require.
- ## Licence
- [MIT](LICENSE) © 2026 Trần Quang Hưng and contributors.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.