mcpField
A
analysis-assumptions-log

analysis-assumptions-log

github.com/nimrodfisherData & databases504231 installsUpdated 5w ago
Repository

About analysis-assumptions-log

A skill for recording assumptions, rationales, confidence, and validation plans in data analysis. It is intended for analysts preparing work for review, handoff, or audit, and includes a structured JSON log, critical-assumption report, and review template.

Key features

  1. 01Initialize a structured assumptions log
  2. 02Record data and business-rule assumptions
  3. 03Document statistical assumptions
  4. 04Flag low-confidence, high-impact items
  5. 05Generate a critical-items report
  6. 06Export a review template

Use cases

  1. 01Record methodological choices in complex analysis
  2. 02Prepare for peer or stakeholder review
  3. 03Explain prior decisions when handing off analysis
  4. 04Maintain an audit trail for regulated work

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/nimrodfisher/data-analytics-skills --skill analysis-assumptions-log

After installing, type/analysis-assumptions-login Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

assets/
assumptions_log_template.md
references/
assumption_categories.md
scripts/
assumptions_tracker.py

Details

From the project README

Analysis Assumptions Log

When to use

  • Starting an analysis with significant scope, method, or data quality choices
  • Preparing work for peer review or stakeholder sign-off
  • Returning to an old analysis and needing to understand prior decisions
  • Working in a regulated environment where auditability is required
  • Handing off an analysis to another analyst

Process

  1. Initialize the log — create a log entry for the analysis with its name, date, analyst, and the decision it informs. Use scripts/assumptions_tracker.py to initialise a structured JSON log.
  2. Enumerate data assumptions — document representativeness, completeness, how missing values are handled, and any known quality issues. For each assumption, record the rationale and confidence level (high/medium/low). See references/assumption_categories.md for the full taxonomy.
  3. Enumerate business logic assumptions — record metric definitions, time windows, inclusion/exclusion rules, and any definitions provided by stakeholders. Note alternatives considered.
  4. Enumerate statistical assumptions — record distribution assumptions, independence claims, stationarity, or model assumptions relevant to the methods used.
  5. Assess impact and flag critical assumptions — for each low-confidence assumption with high impact if wrong, create a validation plan. Run scripts/assumptions_tracker.py --report to surface the critical list.
  6. Validate and close — as validation occurs, update the log with results. Export assets/assumptions_log_template.md for peer review sign-off before delivery.

Inputs the skill needs

  • Analysis name and the decision it informs
  • Data sources, time period, and population being analysed
  • Key methodological choices made (and alternatives considered)
  • Stakeholder-provided business rule definitions
  • Any known data quality issues

Output

  • scripts/assumptions_tracker.py — CLI tool to log assumptions, flag critical ones, and export a summary
  • assets/assumptions_log_template.md — completed log for peer review and audit trail

Comments

Markdown supported