From research
Add a new topic (directory + chapter stubs) to an existing research project. Use when the project already exists and you want to introduce a new top-level topic area. Arguments: topic name (required), optional summary to seed scoping.
How this skill is triggered — by the user, by Claude, or both
Slash command
/research:research-add-topic <topic-name> [summary of the topic]<topic-name> [summary of the topic]opusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are adding a new topic to an existing research project. A topic is a directory under `research/content/` containing chapter files (`.md` stubs). This skill bridges the gap between project inception and chapter-level inquiry.
You are adding a new topic to an existing research project. A topic is a directory under research/content/ containing chapter files (.md stubs). This skill bridges the gap between project inception and chapter-level inquiry.
$ARGUMENTS contains the topic name as the first word, and an optional free-text summary after it.
research/content/)If a summary is provided, use it as the starting point for scoping: propose chapters, boundaries, and relationships that align with the summary rather than asking open-ended questions. The Socratic exchange then refines and validates your proposal instead of starting from scratch.
research/CLAUDE.md for project conventions, tone, scope, and goals.research/INDEX.md to understand existing topics and their relationships.research/content/.
/research-inquiry (to outline a chapter) or /research-restructure (to reorganize).This is a brief Socratic exchange — typically 2-3 rounds, not a full inception. The project's motivation and conventions are already established; you're scoping one new topic within that frame.
Use the summary as a seed: read it alongside the existing INDEX.md, then lead with a concrete proposal covering all four scoping dimensions below. Frame it as "Here's what I'd suggest based on your summary — let's refine." This collapses the exchange from exploratory to confirmatory, often converging in 1-2 rounds.
Explore openly with the user across the same dimensions.
Guide the user, don't interrogate. Offer hypotheses when helpful — "Based on the existing topics, it seems like this would naturally cover X and Y — does that match your thinking?"
Before generating files, present a summary:
Ask for confirmation before proceeding.
Create research/content/<topic-name>/ with one stub file per chapter:
---
title: "<Chapter Title>"
created: <today>
updated: <today>
---
# <Chapter Title>
Filenames use lowercase with hyphens, no numeric prefixes (consistent with project conventions).
Add the new topic to research/INDEX.md in a logically appropriate position (not necessarily at the end). Follow the existing format:
## <topic-name>/
<abstract for this topic>
### <topic-name>/<chapter-file>.md
**Status**: stub
<1-2 sentence abstract>
Preserve the existing content and structure — only add the new entries.
Present:
/research-inquiry <topic-name>/<chapter>.md for each chapterDo NOT commit. The user will review and use /commit when ready.
The expected commit message format: research(add-topic): <topic-name>
research/CLAUDE.md, DECISIONS.md, or glossary.md.Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub mtrense/skills --plugin research