{"id":47718140,"url":"https://github.com/andre-inter-collab-llc/research-workflow-assistant","last_synced_at":"2026-04-06T17:03:15.068Z","repository":{"id":343578207,"uuid":"1176031426","full_name":"andre-inter-collab-llc/research-workflow-assistant","owner":"andre-inter-collab-llc","description":"Open-source AI research assistant for VS Code + GitHub Copilot. Connects to PubMed, OpenAlex, Semantic Scholar, Europe PMC, CrossRef, and Zotero via MCP servers. Custom agents guide systematic reviews, academic writing, data analysis, and project management — all ICMJE-compliant with full audit trails.","archived":false,"fork":false,"pushed_at":"2026-04-01T18:42:16.000Z","size":6105,"stargazers_count":8,"open_issues_count":0,"forks_count":3,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-04-03T05:09:38.755Z","etag":null,"topics":["academic-writing","crossref","europe-pmc","github-copilot","icmje","literature-review","mcp-server","meta-analysis","model-context-protocol","openalex","prisma","pubmed","quarto","reference-management","reproducible-research","research-assistant","semantic-scholar","systematic-review","vscode","zotero"],"latest_commit_sha":null,"homepage":"","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/andre-inter-collab-llc.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-08T14:23:20.000Z","updated_at":"2026-04-02T23:38:02.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/andre-inter-collab-llc/research-workflow-assistant","commit_stats":null,"previous_names":["andre-inter-collab-llc/research-workflow-assistant"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/andre-inter-collab-llc/research-workflow-assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andre-inter-collab-llc%2Fresearch-workflow-assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andre-inter-collab-llc%2Fresearch-workflow-assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andre-inter-collab-llc%2Fresearch-workflow-assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andre-inter-collab-llc%2Fresearch-workflow-assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/andre-inter-collab-llc","download_url":"https://codeload.github.com/andre-inter-collab-llc/research-workflow-assistant/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andre-inter-collab-llc%2Fresearch-workflow-assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31481238,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-06T14:34:32.243Z","status":"ssl_error","status_checked_at":"2026-04-06T14:34:31.723Z","response_time":112,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["academic-writing","crossref","europe-pmc","github-copilot","icmje","literature-review","mcp-server","meta-analysis","model-context-protocol","openalex","prisma","pubmed","quarto","reference-management","reproducible-research","research-assistant","semantic-scholar","systematic-review","vscode","zotero"],"created_at":"2026-04-02T19:08:40.316Z","updated_at":"2026-04-06T17:03:15.063Z","avatar_url":"https://github.com/andre-inter-collab-llc.png","language":"HTML","readme":"# Research Workflow Assistant\n\nAn open-source, modular AI research assistant that runs inside **[VS Code](https://code.visualstudio.com/) + [GitHub Copilot](https://github.com/features/copilot)**. It connects to academic databases via MCP (Model Context Protocol) servers and encodes research best practices through custom Copilot agents. Built for reproducibility, ICMJE compliance, and human-centered research.\n\nAll RWA outputs — manuscripts, protocols, reports, analysis scripts, dashboards, and progress briefs — use **[Quarto](https://quarto.org/)** (by [Posit](https://posit.co/)) as the default document format. Quarto supports R and Python code execution, multi-format rendering (HTML, PDF, Word, PowerPoint, dashboards, websites, books, slides), native Mermaid diagrams, and built-in bibliography management. See [docs/posit-quarto-guide.md](docs/posit-quarto-guide.md) for the full ecosystem guide.\n\n\u003e **Model note:** This project was developed and tested using **Claude Opus 4.6** and **GPT-5.3-Codex** in GitHub Copilot agent mode. You can switch between models depending on task type and preference. Other models available in Copilot ([model comparison](https://docs.github.com/en/copilot/reference/ai-models/model-comparison)) may also work, but behavior can vary by agent workflow, so validate critical outputs after switching.\n\n\u003e **First time here?** Start with [docs/quick-start.md](docs/quick-start.md),\n\u003e or open Copilot Chat and type `@setup` for an interactive guided setup.\n\u003e If setup is complete and something is not working, use `@troubleshooter` for diagnostics and issue resolution.\n\u003e For the full walkthrough, see [docs/getting-started.md](docs/getting-started.md).\n\n\u003e **Important:** Before using non-setup agents, you must accept the user disclaimer once via `@setup`.\n\n## Philosophy\n\nThe question isn't which AI research tool to adopt. It's whether researchers have the right tech stack to build their own.\n\nRWA is a proof of concept for what becomes possible when researchers have a capable IDE, open-source tools, and access to a capable LLM. If your researchers already have VS Code, R, Python, Quarto, Markdown, and git, they have the building blocks. Give them LLM access, and someone on the team could build a custom, organization-compliant research workflow assistant in a few weeks, with MCP servers tailored to their specific needs.\n\nAny specific implementation is going to be opinionated. This one integrates with Zotero, enforces ICMJE authorship guidelines, and defaults to Quarto for reproducible documents. Your organization might make entirely different choices, and that's fine.\n\nWhat matters is **not locking researchers into a single platform**. Tools that sound impressive but limit you to one documentation system, one output format, one way of working are the kind of constraint that slows people down. The better path: meet researchers where they already are. Make their existing environment AI-capable. Don't replace their tools; connect them.\n\nThe stack already exists:\n\n- **[Positron](https://positron.posit.co/) / [VS Code](https://code.visualstudio.com/)** for the IDE\n- **[R](https://www.r-project.org/) and [Python](https://www.python.org/)** for analysis\n- **[Quarto](https://quarto.org/) and Markdown** for reproducible documents\n- **[Git](https://git-scm.com/)** for version control and collaboration\n- **[MCP](https://modelcontextprotocol.io/)** for connecting LLMs to structured data sources\n\nThe missing piece for most organizations isn't a new product. It's access to a capable LLM within the tools researchers already use, and permission to experiment.\n\nRead the [launch post on LinkedIn](https://www.linkedin.com/posts/andre-van-zyl_evidencesynthesis-systematicreview-publichealth-activity-7437474997612417024-yQ20) for the full backstory.\n\n## Who Is This For?\n\nAny researcher who wants AI-assisted support without surrendering intellectual ownership:\n\n- **NGO and public sector researchers** managing evidence reviews or program evaluations\n- **Government analysts** producing policy briefs backed by systematic evidence\n- **Academic faculty and postdocs** running systematic reviews or multi-study projects\n- **Independent researchers and consultants** needing structured, reproducible workflows\n- **Research organizations** wanting standardized, auditable research processes\n\nNo PhD required. If you do research, this tool is for you.\n\n## What It Does\n\n| Capability | How |\n|---|---|\n| **Systematic literature reviews** | `@systematic-reviewer` agent guides PRISMA-compliant workflows: question refinement (PICO/PEO/SPIDER), search strategy development, database searching, screening, data extraction, risk of bias |\n| **Academic database access** | MCP servers for PubMed, OpenAlex, Semantic Scholar, Europe PMC, and CrossRef |\n| **Reference management** | Zotero MCP server: search library, add items by DOI, tag, organize collections, export BibTeX |\n| **Data analysis** | `@data-analyst` agent generates reproducible R or Python analysis scripts in Quarto documents |\n| **Academic writing** | `@academic-writer` agent scaffolds IMRaD manuscripts, manages citations, enforces ICMJE AI disclosure |\n| **Research planning** | `@research-planner` agent helps with protocols, ethics applications, study design, grant writing |\n| **Project management** | `@project-manager` agent tracks phases, milestones, tasks, decisions; generates progress briefs for colleagues |\n| **End-to-end orchestration** | `@research-orchestrator` routes workflows across specialist agents, tracks stage progression, and provides ready-to-run handoff prompts |\n| **Verification and reproducibility** | `@verification-coordinator` agent co-develops human-friendly, LLM-executable verification workbooks, tracks verifier preferences, and standardizes checkpoint evidence outputs |\n| **Troubleshooting and support** | `@troubleshooter` agent diagnoses environment and MCP issues, validates API keys, and provides practical how-to help for day-to-day RWA usage |\n| **Development and bug fixes** | `@developer` agent gathers requirements for bug fixes, feature requests, and codebase improvements, then directs to plan mode for implementation |\n| **Chat session export** | Export Copilot Chat conversations to QMD for reproducibility via `scripts/export_chat_session.py` or `chat-exporter` MCP server |\n| **ICMJE compliance** | Built into every agent: human-in-the-loop mandate, audit trail, AI disclosure generation, authorship checklist |\n\n## Architecture\n\n```mermaid\ngraph TB\n    YOU[\"👤 You · the Researcher\u003cbr/\u003eAll decisions · All ownership · All accountability\"]\n\n    VSCODE[\"VS Code + GitHub Copilot Chat\"]\n\n    YOU --\u003e VSCODE\n\n    subgraph AGENTS[\"Specialist AI Agents\"]\n        direction LR\n        ORCH[\"@research-orchestrator\u003cbr/\u003eEnd-to-end\u003cbr/\u003eworkflow routing\"] ~~~ SR[\"@systematic-reviewer\u003cbr/\u003ePRISMA-compliant\u003cbr/\u003eevidence reviews\"] ~~~ RP[\"@research-planner\u003cbr/\u003eProtocols \u0026\u003cbr/\u003estudy design\"] ~~~ DA[\"@data-analyst\u003cbr/\u003eReproducible R / Python\u003cbr/\u003eanalysis scripts\"] ~~~ AW[\"@academic-writer\u003cbr/\u003eManuscript drafting\u003cbr/\u003e\u0026 citations\"] ~~~ PM[\"@project-manager\u003cbr/\u003eMilestones, decisions\u003cbr/\u003e\u0026 progress briefs\"] ~~~ VC[\"@verification-coordinator\u003cbr/\u003eHuman + LLM\u003cbr/\u003everification workbooks\"] ~~~ TS[\"@troubleshooter\u003cbr/\u003eDiagnostics \u0026\u003cbr/\u003eenvironment fixes\"] ~~~ DEV[\"@developer\u003cbr/\u003eBug fixes \u0026\u003cbr/\u003efeature planning\"]\n    end\n\n    VSCODE --\u003e AGENTS\n\n    ICMJE[\"🔒 ICMJE Compliance Layer\u003cbr/\u003eHuman-in-the-loop · Audit trail · AI disclosure\"]\n\n    AGENTS --\u003e ICMJE\n\n    subgraph MCP[\"MCP Servers · Model Context Protocol\"]\n        direction LR\n        subgraph LITERATURE[\"Literature Databases\"]\n            direction LR\n            PUB[\"PubMed\u003cbr/\u003eNCBI E-utilities\"] ~~~ OA[\"OpenAlex\u003cbr/\u003eREST API\"] ~~~ SS[\"Semantic Scholar\u003cbr/\u003eAcademic Graph\"] ~~~ EPMC[\"Europe PMC\u003cbr/\u003eREST API\"] ~~~ CR[\"CrossRef\u003cbr/\u003eDOI metadata\"]\n        end\n        subgraph REFERENCE[\"Reference Management\"]\n            direction LR\n            ZOT[\"Zotero Web\u003cbr/\u003eAPI v3\"] ~~~ ZLOC[\"Zotero Local\u003cbr/\u003ePDFs \u0026 annotations\"]\n        end\n        subgraph TRACKING[\"Project Tracking\"]\n            direction LR\n            PRISMA[\"PRISMA Tracker\u003cbr/\u003eflow diagrams\"] ~~~ PROJ[\"Project Tracker\u003cbr/\u003etasks \u0026 milestones\"] ~~~ CHATEX[\"Chat Exporter\u003cbr/\u003esession audit trails\"]\n        end\n    end\n\n    ICMJE --\u003e MCP\n\n    subgraph OUTPUTS[\"Research Outputs\"]\n        direction LR\n        QMD[\"📄 Quarto Documents\u003cbr/\u003eManuscripts · Protocols · Reports\"] ~~~ SCRIPTS[\"📊 Analysis Scripts\u003cbr/\u003eR · Python · Reproducible\"] ~~~ PFLOW[\"📋 PRISMA Flow\u003cbr/\u003eDiagrams \u0026 Checklists\"] ~~~ BRIEFS[\"📝 Progress Briefs\u003cbr/\u003eDecision logs · Meeting notes\"]\n    end\n\n    MCP --\u003e OUTPUTS\n\n    %% ── Styles ──\n    classDef researcher fill:#2563eb,stroke:#1e40af,color:#fff,font-weight:bold\n    classDef vscode fill:#007acc,stroke:#005a9e,color:#fff,font-weight:bold\n    classDef agent fill:#7c3aed,stroke:#5b21b6,color:#fff\n    classDef compliance fill:#dc2626,stroke:#991b1b,color:#fff,font-weight:bold\n    classDef litdb fill:#10b981,stroke:#047857,color:#fff\n    classDef refmgmt fill:#14b8a6,stroke:#0d9488,color:#fff\n    classDef tracking fill:#06b6d4,stroke:#0891b2,color:#fff\n    classDef output fill:#d97706,stroke:#b45309,color:#fff\n\n    class YOU researcher\n    class VSCODE vscode\n    class ORCH,SR,RP,DA,AW,PM,VC,TS,DEV agent\n    class ICMJE compliance\n    class PUB,OA,SS,EPMC,CR litdb\n    class ZOT,ZLOC refmgmt\n    class PRISMA,PROJ tracking\n    class QMD,SCRIPTS,PFLOW,BRIEFS output\n```\n\n\u003e Also available as [SVG](docs/rwa-architecture.svg), [rendered HTML](docs/architecture-diagram.qmd) (`quarto render docs/architecture-diagram.qmd`), or [Mermaid source](docs/rwa-architecture.mmd).\n\n## ICMJE Compliance: You Are the Author\n\nThis tool is designed around the [ICMJE authorship criteria](https://www.icmje.org/recommendations/browse/roles-and-responsibilities/defining-the-role-of-authors-and-contributors.html). AI cannot be an author. You must meet all four criteria:\n\n1. **Substantial contributions** to conception, design, data acquisition, analysis, or interpretation\n2. **Drafting or critically revising** the work for important intellectual content\n3. **Final approval** of the version to be published\n4. **Accountability** for all aspects of the work\n\nThe tool enforces this by:\n- Requiring human decisions at every substantive step\n- Tracking AI contributions in an audit trail (`ai-contributions-log.md`)\n- Generating ICMJE-compliant AI disclosure statements for your manuscripts\n- Refusing to finalize outputs without explicit human review\n\nPer ICMJE Section II.A.4: AI use must be disclosed in acknowledgments (writing assistance) and methods (data analysis). This tool generates those disclosures for you.\n\nSetup also captures a default author profile in [.rwa-user-config.yaml](.rwa-user-config.yaml), and new projects can store per-project `authors` metadata in [templates/project-config.yaml](templates/project-config.yaml) so future reports and manuscripts start with the correct author front matter.\n\nWhen RWA itself is cited in a Methods or Acknowledgments section, use the `vanzyl2026rwa` BibTeX entry from [templates/rwa-citation.bib](templates/rwa-citation.bib).\n\n## Disclaimer and Readiness Gate\n\nRWA enforces a disclaimer/readiness gate before non-setup agent workflows.\n\n- Source disclaimer text: [compliance/user-disclaimer.md](compliance/user-disclaimer.md)\n- Acceptance state file: [.rwa-user-config.yaml](.rwa-user-config.yaml)\n- Required value: `disclaimer_accepted: true` (boolean)\n\nWhen accepted through `@setup`, `.rwa-user-config.yaml` should include values like:\n\n```yaml\ndisclaimer_accepted: true\ndisclaimer_accepted_date: \"YYYY-MM-DD\"\nsetup_completed: true\nsetup_completed_date: \"YYYY-MM-DD\"\ndefault_author:\n  name: \"Author Name\"\n  affiliation:\n    name: \"Organization\"\n```\n\nIf acceptance is missing or invalid, agents will return:\n\n`Before using RWA, you need to review and accept the disclaimer. Run @setup to get started.`\n\nIf you see this message unexpectedly:\n\n1. Confirm [.rwa-user-config.yaml](.rwa-user-config.yaml) exists at workspace root.\n2. Confirm `disclaimer_accepted` is boolean `true` (not a quoted string).\n3. Run `@setup` again to refresh config if needed.\n4. Open a new Copilot Chat session after setup changes.\n\n## Quick Start\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eWhat setup includes (typical 20-30 minutes)\u003c/strong\u003e\u003c/summary\u003e\n\n- Stage 1: Verify Python and VS Code prerequisites\n- Stage 2: Create `.venv` and install all MCP servers\n- Stage 3: Configure `.env` API keys and `PROJECTS_ROOT`\n- Stage 4: Run setup validation + MCP smoke check\n- Stage 5: Confirm servers in VS Code\n- Stage 6: Save a default author profile for future outputs\n- Stage 7: Optionally start a first project with project-specific authorship metadata\n\n\u003c/details\u003e\n\n\u003e **Prefer a guided setup?** Open Copilot Chat and type `@setup`. It will\n\u003e walk you through every step interactively.\n\n### Prerequisites\n\n| Requirement | Notes |\n|---|---|\n| [VS Code](https://code.visualstudio.com/) 1.99+ with [GitHub Copilot](https://github.com/features/copilot) | Agent mode must be enabled |\n| [Python 3.11+](https://www.python.org/) | Required — runs the MCP servers |\n| [R 4.0+](https://www.r-project.org/) | Optional — for R-based analysis templates |\n| [Quarto](https://quarto.org/) | Optional — for rendering document templates |\n| [Zotero](https://www.zotero.org/) | Optional — for reference management |\n\n### Step 1 — Clone and open the repo\n\n```bash\ngit clone https://github.com/yourusername/research-workflow-assistant.git\ncd research-workflow-assistant\ncode .\n```\n\n### Step 2 — Create a Python environment and install MCP servers\n\n```bash\n# Create and activate a virtual environment\npython -m venv .venv\n# Windows:\n\u0026 .venv\\Scripts\\Activate.ps1\n# macOS / Linux:\n# source .venv/bin/activate\n\n# Install all 11 MCP servers in development mode\npip install -e mcp-servers/_shared \\\n            -e mcp-servers/pubmed-server \\\n            -e mcp-servers/openalex-server \\\n            -e mcp-servers/semantic-scholar-server \\\n            -e mcp-servers/europe-pmc-server \\\n            -e mcp-servers/crossref-server \\\n            -e mcp-servers/zotero-server \\\n            -e mcp-servers/zotero-local-server \\\n            -e mcp-servers/prisma-tracker \\\n            -e mcp-servers/project-tracker \\\n            -e mcp-servers/chat-exporter \\\n            -e mcp-servers/bibliography-manager\n\n# Install dev tools (linting, testing)\npip install -e \".[dev]\"\n```\n\n### Step 3 — Configure API keys\n\n```bash\n# Copy the example env file\ncp .env.example .env          # macOS / Linux\ncopy .env.example .env        # Windows\n```\n\nOpen `.env` and add your credentials. At minimum:\n\n| Key | Where to get it | Required? |\n|---|---|---|\n| `NCBI_API_KEY` | [NCBI account settings](https://www.ncbi.nlm.nih.gov/account/settings/) | Recommended |\n| `OPENALEX_API_KEY` | [OpenAlex API key settings](https://openalex.org/settings/api-key) | Recommended |\n| `ZOTERO_API_KEY` | [Zotero key settings](https://www.zotero.org/settings/keys) | If using Zotero |\n| `ZOTERO_USER_ID` | Numeric ID shown at the top of the [Zotero keys page](https://www.zotero.org/settings/keys) (not your username) | If using Zotero |\n\nFull details: [docs/api-setup-guide.md](docs/api-setup-guide.md)\n\n`PROJECTS_ROOT` should normally remain `./my_projects` unless you explicitly want projects in another folder.\n\n### Step 4 — Verify everything works\n\n```bash\npython scripts/validate_setup.py\n```\n\nNeed JSON for automation?\n\n```bash\npython scripts/validate_setup.py --json\n```\n\nOr in VS Code: **Ctrl+Shift+P** → \"MCP: List Servers\" — all 11 servers should appear.\n\n### Step 5 — Start using it\n\nIf you want one entry point that coordinates all phases, start with:\n\n```\n@research-orchestrator I am starting a systematic review. Orchestrate the full workflow and tell me exactly which agent prompt to run at each stage.\n```\n\nOr choose a specialist agent directly if you already know the stage.\n\nOpen Copilot Chat and try an agent:\n\n```\n@project-manager Initialize a new project called \"my-first-review\" in my_projects/my-first-review.\n```\n\nSee [docs/getting-started.md](docs/getting-started.md) for the full guide, including project setup, multi-project workflows, and cross-workspace usage.\n\n### Usage examples\n\n```\n@systematic-reviewer I want to conduct a systematic review on the effectiveness\nof community health worker interventions for maternal mental health in low- and\nmiddle-income countries.\n```\n\n```\n@project-manager Initialize a new project for my systematic review. Target\ncompletion is September 2026.\n```\n\n```\n@data-analyst I have extracted data from 23 studies. Help me set up a\nrandom-effects meta-analysis using the metafor package in R.\n```\n\n### Sample project\n\nThe repository includes a fully worked sample project at [`sample_projects/chw-maternal-mental-health/`](sample_projects/chw-maternal-mental-health/) — a systematic review of community health worker interventions for maternal mental health in low- and middle-income countries. It demonstrates the end-to-end outputs that RWA generates:\n\n| Output | Path | What it shows |\n|---|---|---|\n| Review protocol | [`protocol.qmd`](sample_projects/chw-maternal-mental-health/protocol.qmd) | PRISMA-compliant protocol with PICO framework |\n| Manuscript (source) | [`manuscript.qmd`](sample_projects/chw-maternal-mental-health/manuscript.qmd) | IMRaD manuscript with citations and AI disclosure |\n| Manuscript (HTML) | [`manuscript.html`](sample_projects/chw-maternal-mental-health/manuscript.html) | Rendered HTML version for browser viewing |\n| Manuscript (PDF) | [`manuscript.pdf`](sample_projects/chw-maternal-mental-health/manuscript.pdf) | Rendered PDF for print/submission |\n| Manuscript (Word) | [`manuscript.docx`](sample_projects/chw-maternal-mental-health/manuscript.docx) | Rendered DOCX for journal submission or collaboration |\n| Search results (SQLite) | [`data/search_results.db`](sample_projects/chw-maternal-mental-health/data/) | Structured database of results from PubMed, OpenAlex, CrossRef, Semantic Scholar |\n| Search results (Excel) | [`data/search_results.xlsx`](sample_projects/chw-maternal-mental-health/data/) | Filterable Excel workbook with clickable DOI/PMID hyperlinks |\n| Reproducible search scripts | [`scripts/`](sample_projects/chw-maternal-mental-health/scripts/) | Thin stub scripts that reproduce each database search |\n| Data extraction | [`data-extraction.qmd`](sample_projects/chw-maternal-mental-health/data-extraction.qmd) | Structured data extraction template |\n| Risk of bias | [`rob2-assessments.qmd`](sample_projects/chw-maternal-mental-health/rob2-assessments.qmd) | Cochrane RoB 2 assessments |\n| Evidence synthesis | [`synthesis.qmd`](sample_projects/chw-maternal-mental-health/synthesis.qmd) | Narrative and quantitative synthesis |\n| PRISMA flow | [`review-tracking/`](sample_projects/chw-maternal-mental-health/review-tracking/) | PRISMA flow diagram tracking data |\n| Project tracking | [`project-tracking/`](sample_projects/chw-maternal-mental-health/project-tracking/) | Milestones, tasks, and decision log |\n| AI contributions log | [`ai-contributions-log.md`](sample_projects/chw-maternal-mental-health/ai-contributions-log.md) | Full audit trail of AI-assisted work |\n| References | [`references.bib`](sample_projects/chw-maternal-mental-health/references.bib) | BibTeX bibliography managed via Zotero |\n\nBrowse the sample project to see what a completed RWA-assisted review looks like before starting your own.\n\n## Project Structure\n\n```\nresearch-workflow-assistant/\n├── .github/\n│   ├── copilot-instructions.md      # ICMJE + research integrity rules\n│   └── agents/                      # Custom Copilot agents\n├── .vscode/\n│   ├── settings.json\n│   └── mcp.json                     # MCP server configuration\n├── mcp-servers/                     # MCP server implementations (Python)\n│   ├── _shared/                     # Shared SQLite result storage module\n│   ├── pubmed-server/\n│   ├── openalex-server/\n│   ├── semantic-scholar-server/\n│   ├── europe-pmc-server/\n│   ├── crossref-server/\n│   ├── zotero-server/\n│   ├── prisma-tracker/\n│   └── project-tracker/\n├── templates/                       # Quarto templates\n│   ├── systematic-review/\n│   ├── manuscript/\n│   ├── report/\n│   └── project-management/\n├── analysis-templates/              # Reusable R/Python analysis templates\n├── compliance/                      # ICMJE checklists, reporting standards\n├── docs/                            # User documentation\n└── tests/\n```\n\n## Database Access\n\n| Database | API | Access | Auth |\n|---|---|---|---|\n| PubMed/MEDLINE | NCBI E-utilities | Free | API key (recommended) |\n| OpenAlex | REST API | Free ($1/day budget) | API key (free) |\n| Semantic Scholar | Academic Graph API | Free (rate limited) | API key (optional) |\n| Europe PMC | REST API | Free | None |\n| CrossRef | REST API | Free | Email (polite pool) |\n| Zotero | Web API v3 | Free | API key |\n| Scopus | Elsevier API | Planned (institutional) | API key |\n\nDatabases without APIs (CINAHL, PsycINFO, Web of Science, Google Scholar, Cochrane Library): the agents help you build database-specific queries, but you run the searches manually and import results.\n\n## Reporting Standards\n\nThe tool supports multiple systematic review reporting standards (user selects):\n- **PRISMA 2020** (systematic reviews with meta-analysis)\n- **PRISMA-ScR** (scoping reviews)\n- **MOOSE** (meta-analyses of observational studies)\n- **Cochrane Handbook** methods\n\n## Contributing\n\nContributions are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n## License\n\n[MIT License](LICENSE)\n\n## How To Cite\n\nIf you use Research Workflow Assistant in a manuscript, report, protocol, or other cited output, cite it as:\n\nvan Zyl, A. (2026). Research Workflow Assistant [Computer software]. https://github.com/andre-inter-collab-llc/research-workflow-assistant\n\nBibTeX:\n\n```bibtex\n@misc{vanzyl2026rwa,\n  author = {{Van Zyl}, Andre},\n  title = {Research Workflow Assistant},\n  year = {2026},\n  url = {https://github.com/andre-inter-collab-llc/research-workflow-assistant},\n  note = {GitHub repository}\n}\n```\n\nYou can also copy the canonical entry directly from [templates/rwa-citation.bib](templates/rwa-citation.bib) into your project's `references.bib`.\n\n## Acknowledgments\n\n- [ICMJE](https://www.icmje.org/) for authorship and AI disclosure guidelines\n- [PRISMA](http://www.prisma-statement.org/) for systematic review reporting standards\n- [MCP](https://modelcontextprotocol.io/) for the Model Context Protocol specification\n- [Quarto](https://quarto.org/) for scientific publishing\n- [Posit](https://posit.co/) for the R ecosystem\n- Built with [GitHub Copilot](https://github.com/features/copilot) using [Claude Opus 4.6](https://docs.github.com/en/copilot/reference/ai-models/model-comparison) by Anthropic and GPT-5.3-Codex\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandre-inter-collab-llc%2Fresearch-workflow-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fandre-inter-collab-llc%2Fresearch-workflow-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandre-inter-collab-llc%2Fresearch-workflow-assistant/lists"}