tda-research-ideation-lab

Generates labelled speculative research hypotheses and routes them to verification skills.

1|Updated Dec 13, 2025
One-click install
npx skills add https://github.com/ZK-Theory/TDL --skill tda-research-ideation-lab-zk-theory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tda-research-ideation-lab
Source: https://github.com/ZK-Theory/TDL/tree/main/.agents/skills/tda-research-ideation-lab
Command: npx skills add https://github.com/ZK-Theory/TDL --skill tda-research-ideation-lab-zk-theory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Research teams need a safe space to brainstorm hypotheses, alternative nulls, robustness checks, and future-paper directions without accidentally treating unverified ideas as findings or paper claims. ## Core Features & Use Cases - Speculative Idea Generation: Produces candidate hypotheses, methods, negative controls, external datasets, reviewer objections, and future paper directions. - Mandatory Labelling: Every idea is tagged with labels such as speculative, literature-needed, data-needed, contract-needed, implementation-needed, or paper-scope-risk. - Structured Output Records: Emits a JSON record per idea capturing status, evidence needed, method risks, assurance lanes, and the next routing skill. - Use Case: Before drafting a paper section, run an ideation pass to enumerate alternative explanations and robustness checks, then route surviving ideas to literature verification or task briefs. ## Quick Start Ask the agent to run an ideation pass on your research question and return labelled speculative hypotheses with their evidence needs.

Frequently Asked Questions about tda-research-ideation-lab

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

FAQPage Schema
How do I generate research hypotheses before verification?

Run an ideation pass that produces candidate hypotheses, methods, and negative controls, each labelled as speculative with its evidence and literature needs. Ideas stay outside the claim pipeline until routed through verification skills.

What labels does the ideation lab apply to generated ideas?

Every idea carries applicable labels: speculative, literature-needed, data-needed, contract-needed, implementation-needed, and paper-scope-risk. These labels prevent unverified ideas from being treated as findings.

Can the ideation lab run experiments or write paper sections?

No. It cannot create paper claims, run compute, or draft scoped paper prose. Ideas that survive are routed to literature verification, task briefs, or the Discovery Harness (scout-review, assay, spike).

What is the output format of a generated research idea?

Each idea is emitted as a JSON record with fields for idea text, status, paper target, evidence needed, literature needed, data needed, method risks, assurance lanes, and the next routing skill.

When should I not use speculative ideation?

Do not use it when you need verified claims, canonical computations, or contract-bearing implementations. Those require tier 1 or tier 2 assurance skills; the lab only widens the idea funnel.