spike

Probe Discovery Harness candidates with toy-scale feasibility and null-model checks.

1|Updated Dec 13, 2025
One-click install
npx skills add https://github.com/stephendor/TDL --skill spike-stephendor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spike
Source: https://github.com/stephendor/TDL/tree/main/.agents/skills/spike
Command: npx skills add https://github.com/stephendor/TDL --skill spike-stephendor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

The spike Skill addresses the need for a toy-scale feasibility probe, pre-registration, and null-model check before advancing a Discovery Harness candidate to APM execution.

Core Features & Use Cases

  • Feasibility Probe: Conducts toy-scale feasibility tests on Discovery Harness candidates.
  • Pre-Registration: Facilitates pre-registration processes for candidate analysis.
  • Null-Model Check: Validates null models before proceeding with in-depth analysis.
  • Use Case: After a candidate is promoted from the assay phase, the spike Skill can be used to confirm the feasibility of a candidate's analysis, ensuring that all pre-requisites are met before moving to APM execution.

Quick Start

To initiate a spike probe, use the command 'run-spike --candidate "candidate_slug" --pre-reg "pre_registration_path"'

Frequently Asked Questions about spike

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a feasibility probe for data analysis before full processing?

A null-model check validates defined null models before proceeding with in-depth analysis. This ensures your baseline assumptions are tested against the data during the pre-registration phase.

When do I need pre-registration for a discovery harness candidate?

You need pre-registration after a candidate is promoted from the assay phase but before APM execution. This confirms the candidate's analysis feasibility and ensures all prerequisites are met.

What inputs are required to initiate a toy-scale feasibility probe?

Initiating a toy-scale feasibility probe requires input data and pre-registration information. You must provide a candidate slug and a pre-registration path to execute the probe successfully.

Does feasibility testing work without defining a null model first?

No, defining a null model is required before proceeding. The spike Skill validates that null models are properly defined to ensure metric spaces are viable for the discovery harness candidate.

What are the limitations of running toy-scale feasibility probes?

Toy-scale feasibility probes are limited to confirming viability and pre-registration readiness before APM execution. They do not replace the advanced processing required for full-scale data analysis.