research-log

Record research verdicts and metadata into docs/research_log.md.

Updated Feb 27, 2026
One-click install
npx skills add https://github.com/danny0926/NLP-data-for-trading --skill research-log-danny0926
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-log
Source: https://github.com/danny0926/NLP-data-for-trading/tree/main/.claude/skills/research-log
Command: npx skills add https://github.com/danny0926/NLP-data-for-trading --skill research-log-danny0926

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This workflow automates the evaluation and recording of research outcomes, consolidating conclusions and actions into a persistent log and state tracker.

Core Features & Use Cases

  • Automatically classify outcomes into ADOPT, ITERATE, REJECT, or INCONCLUSIVE based on predefined criteria.
  • Append structured entries to docs/research_log.md including date, topic, hypothesis, setup, data period, sample size, and next steps.
  • Update docs/research_state.json to reflect the latest result and support follow-up actions such as merging topics, memory updates, and roadmap alignment.

Quick Start

Run the skill after completing an experiment to log the conclusion and append it to docs/research_log.md.

Frequently Asked Questions about research-log

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

FAQPage Schema
How do I automate logging research conclusions and experiment outcomes?

Automating research conclusions involves evaluating experiment verdicts and appending structured entries with metadata like setup, sample size, and next steps to a persistent markdown log. This workflow standardizes the evaluation and recording of research outcomes into triage categories.

What is the best way to record experiment verdicts like ADOPT or REJECT in a research log?

Recording experiment verdicts requires triaging outcomes into ADOPT, ITERATE, REJECT, or INCONCLUSIVE categories. The process appends structured entries including date, topic, hypothesis, and data period to docs/research_log.md, while updating docs/research_state.json to reflect the latest result.

How to update research state and roadmap after completing an experiment?

Updating research state after an experiment involves syncing the latest verdict to docs/research_state.json. This supports follow-up actions such as merging topics, triggering memory updates, and aligning project roadmaps based on the standardized conclusion logged in docs/research_log.md.

Does this research logging workflow require external dependencies or components?

No external dependencies or components are required to run this research logging workflow. It operates natively to evaluate experiment outcomes, generate standardized markdown log entries, and update the JSON state tracker without needing additional frameworks.

Can I use this workflow for phase reviews instead of formal experiments?

Yes, this workflow applies to both experiments and phase reviews. It evaluates outcomes across setup, data period, and sample size, appending the resulting verdict and next steps to docs/research_log.md to maintain a persistent record of research progress.