Skip to content

/neuroflow:tool-validate

Create a comprehensive testing pipeline to verify a tool or paradigm works correctly.

/tool-validate helps you build test scripts and procedures to verify timing accuracy, marker integrity, data output format, hardware integration, and edge cases — before real data collection begins.

When to use it

  • After building a paradigm with /experiment — validate timing and markers
  • After building a tool with /tool-build — verify it meets its spec
  • Before starting data collection — confirm the whole acquisition pipeline works

What it does

Claude asks:

  1. What needs to be validated? (paradigm timing, marker accuracy, LSL streaming, data output format, hardware integration, edge cases)
  2. What is the tool / paradigm under test? (point to the file or folder)
  3. Pass/fail criteria — what does "correct" look like?

Validation areas

Area What is checked
Paradigm timing Trial duration, ISI, SOA, jitter range
Marker accuracy Correct codes sent, timing relative to stimulus onset
LSL streaming Stream info, sampling rate stability, chunk integrity
Data output File format, BIDS naming, sidecar JSON completeness
Hardware integration Amplifier connection, trigger box wiring, device sync
Edge cases Missing responses, early exits, hardware disconnects

Steps

1. Write a validation-plan.md

Defines what is being tested, how, and the pass/fail criteria.

2. Build test scripts or procedures

Claude writes automated tests where possible and step-by-step manual procedures where automation is not feasible.

3. Run validation and record results

Claude runs the tests and records outcomes in a validation-results.md document.

4. PsychoPy script audit (if applicable)

Claude reads the PsychoPy script directly and checks: - Trial timing matches the design spec - Marker codes are correct for each event type - Response handling covers all cases - Edge cases (no response, early exit, block transitions) are handled

Example session

/neuroflow:tool-validate

Claude: What needs to be validated?

You: The oddball paradigm in paradigm/oddball.py — timing and markers.

Claude: I'll check the PsychoPy script for:
        ✓ ISI jitter: expected 800–1200ms
        ✓ Stimulus duration: expected 50ms
        ✓ Marker codes: S=standard (1), T=target (2)
        ✓ LSL outlet initialization
        ✓ Block transitions

        Reading paradigm/oddball.py...

        Issues found:
        ⚠ ISI jitter implementation uses clock.getTime() — rounding to frame
          boundaries could produce actual ISI of 800 ± 16.7ms at 60Hz.
          Suggest using core.wait() with precise timing.
        ✓ Stimulus duration: correct
        ✓ Marker codes: correct
        ✓ LSL outlet: initialized before trial loop — correct

Output

All validation output is saved in .neuroflow/tool-validate/: - validation-plan.md - validation-results.md

Files read and written

Direction Files
Reads .neuroflow/project_config.md, .neuroflow/flow.md, .neuroflow/tool-build/flow.md, .neuroflow/experiment/flow.md, .neuroflow/tool-validate/flow.md
Writes .neuroflow/tool-validate/, .neuroflow/tool-validate/flow.md, .neuroflow/sessions/YYYY-MM-DD.md
  • /tool-build — build the tool before validating it
  • /experiment — design the paradigm being validated
  • /data — the next step after validation passes