OpenScience Research Workflow - 28 Skills

    1

    28 evidence-first skills for literature, research workflows, analysis and epidemiology.

    $19.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    OpenScience Research Workflow - 28 Skills

    Example session with this skill installed

    Illustrative scenario only: help organize an epidemiology literature review with explicit source status and human review stages.

    • Read your context and instructions
    • Compiled the openscience research workflow

    ILLUSTRATIVE FORMAT ONLY — no live search or analysis was executed.

    Intake
    Confirm the research question, population, outcome, date range, available sources and permitted workspace. Record missing information before selecting a workflow.

    Evidence plan
    Choose the relevant literature and evidence skills. Record search queries, source identifiers and retrieval dates only after actual retrieval. Keep inaccessible sources marked unavailable, and distinguish abstracts from full texts.

    Review record
    For each proposed claim, record its supporting source, the relevant passage, limitations and whether a human has reviewed it. Do not infer a verified result from a plausible citation or empty search.

    Deliverable format
    A research workspace index, evidence table, unresolved-question checklist and proposed next stage. No scientific result, citation or file is claimed to exist in this example.

    Approval boundary
    Request authorization before remote jobs or sharing private research data. Findings and publication decisions need qualified human review.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A complete collection of 28 original skills across six research plugin domains, plus one root routing entry (29 SKILL.md files). Includes original source and runtime helpers, license notices, installation guidance and a source-integrity manifest.

    Use it to structure literature searches, evidence records, analysis workflows, research workspaces and epidemiology tasks. Human stage approvals and source verification remain required. This is workflow assistance, not proof of scientific truth.

    Free upstream source: https://github.com/Hylouis233/openscience/tree/fee2bde6ac7296ae98dadeff2e900c992ec37a85 . MIT licensed; this packaged distribution does not remove upstream open-source rights.

    Requires Python 3.11+, uv and a compatible agent host; R workflows require R and their documented packages. Optional bibverify MCP, data connectors and buyer-supplied credentials must be configured separately. Remote compute requires an authorized host and separate setup.

    Agensi runtime integration has not been tested. Packaging received static integrity and secret-pattern review only, not live application testing. No API keys, credits, model subscription, hosted service or third-party data access are included. The demo is an illustrative format, not a verified execution.

    Price: US$19.99 one-time purchase for the complete package, not a subscription.

    Research workflow assistance, not proof of scientific truth. Unavailable evidence must remain unavailable. Human stage approvals remain required. No hosted service, API key, API credits or third-party source rights included. Python, R, connectors and remote compute require separate setup as applicable. Agensi runtime integration has not been tested; static packaging checks only.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    bibverify
    uv (Python tool runner)
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Access only user-authorized research workspace files. Selected workflows use academic/data APIs and buyer-supplied credentials. Optional MCP integrations and SSH/remote compute require separate setup and explicit authorization. Scope network calls and data sharing to the chosen workflow.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    All 85 original files and 28 original skills are retained, with four added security review and regression-test files (89 files total). Authorized local process execution remains available with hardened controls. The package includes patch notes and test evidence; it does not establish absolute safety or tested Agensi runtime compatibility.

    New in Research & Analysis