More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Experiment Replication Pack

    1

    Package an experiment so a stranger can rerun it cold, and find the missing items before you share it.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Experiment Replication Pack

    Experiment Replication Pack

    Example session with this skill installed

    Apply the skill to: Simulation study packaged for a collaborator.

    • Read your context and instructions
    • Compiled the experiment replication

    Worked example: A simulation study produced a result a collaborator could not reproduce, despite receiving the code and a methods section. The pack process ran to find the missing detail. Findings: The as-run procedure differed from the plan in run order: calibration ran after the first batch, not before. One library version had updated mid-study, changing a default parameter the code did not set explicitly. Two failed runs had been excluded without a recorded reason, and their inclusion changed a secondary result. The cold rerun asked seven questions, each marking a missing detail in data cleaning and seed handling. Outcome: The pack recorded both library versions with runs under each, pinned the parameter explicitly, documented the failed-run decisions, and added tolerances for key outputs. The collaborator reran from the pack alone and matched key outputs within tolerance, and the secondary result was reported with its sensitivity to the failed runs noted. This is a worked example produced by applying the skill protocol, not a guarantee of results on new data.

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

    About this skill

    Experiments are described in prose that omits versions, order, random seeds, and failure handling, so a second team cannot reproduce the setup even when they want to, and discrepancies get blamed on skill rather than missing detail. The bottleneck is tacit detail. Authors remember the main procedure and forget environment versions, data cleaning choices, seed values, and the exact order of steps that mattered. A pack must force those details out before memory fades. This skill gives you a full protocol: trigger and scope, an inputs and outputs contract, ordered steps with checks, a decision table, a fill-in template, a checklist, a scoring rubric, a worked example, edge cases, and a pre-delivery quality gate. It also includes a runnable script under scripts/ so the core scoring or checking step can be repeated on new data without redoing the judgement by hand. The focus throughout is bottleneck fixes and workflows that a short free checklist would not cover: what to check first and second, which thresholds change the action, and when to stop and narrow the scope.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.

    A pack documents what was done and enables reruns; it does not prove the original result is correct. Replication still requires independent execution and its own analysis. Results depend on input quality: missing inputs, small samples, or unverified sources limit how strongly conclusions can be stated. The skill helps you state those limits honestly rather than hiding them.

    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 buying a skill.

    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 23 days ago

    Permissions

    Terminal / Shell
    Listed23 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    A free checklist lists tasks. This skill adds diagnosis order, decision thresholds, evidence requirements, a rubric, and a quality gate, so you can tell whether the work is actually done and whether the conclusion follows from the evidence.

    A first run typically takes a focused working session to a few days depending on input size. The protocol is designed so a small, honest run beats a large, rushed run that skips diagnosis.

    The inputs listed in SKILL.md. If an input is missing, the skill tells you how to narrow the scope and record the gap instead of guessing.

    New in Research & Analysis