From marten-superpower
Use as Phase 2 of marten-workflow, immediately after brainstorming and before writing-plans. Dispatches ≥2 parallel research subagents (web + codebase) to triangulate facts, libraries, prior art, and existing code patterns. Produces a written research report. Triggers on phrases like "research X", "investigate options for Y", "what's the best library for Z", or implicit need for fact-finding before planning.
How this skill is triggered — by the user, by Claude, or both
Slash command
/marten-superpower:research-phaseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<SUBAGENT-STOP>
This is Phase 2 of marten-workflow. Its job: replace assumption-based planning
with evidence-based planning. Output is a written research report that feeds
directly into Phase 3 (writing-plans).
Skipping research causes:
Martin's global rules already mandate "research before implementing" and "≥2 subagents per topic". This skill operationalizes both.
WebSearch and WebFetch only. Chrome MCP
(mcp__claude-in-chrome__*) is banned inside research subagents.
Include this ban explicitly in every dispatch prompt.Before starting, confirm Phase 1 (brainstorming) produced:
If brainstorming output is missing or thin, return to Phase 1 first.
Break the brainstorming output into 2–5 narrow research topics. Each topic must be answerable with primary-source evidence. Examples:
Avoid topics like "is this a good idea?" — that's Phase 1 territory.
| Topic flavor | Subagent type | Tools |
|---|---|---|
| Web facts, library research, API docs | general-purpose (research only) | WebSearch, WebFetch |
| Codebase patterns, file locations, existing impls | Explore | Read-only filesystem + grep |
| Independent verification of disputed fact | scientist-researcher | WebSearch, WebFetch |
Every subagent prompt must include:
mcp__claude-in-chrome__* tools. Use only
WebSearch and WebFetch."Use a single message with multiple Agent tool calls. Pair web+web (different
angles) or web+codebase per topic.
When all subagents return:
Save to research-report.md at the worktree root (or repo root if worktree
not yet created). Format:
# Research Report — <topic>
## Topics investigated
1. <topic 1>
2. <topic 2>
...
## Findings
### Topic 1: <question>
**Answer:** <one-sentence answer>
**Confidence:** <high|medium|low>
**Evidence:**
- <bullet> ([source](url), credibility 8/10)
- <bullet> ([source](url), credibility 7/10)
**Conflicts:** <any disagreements + resolution>
### Topic 2: ...
## Recommendations for the plan
- <actionable recommendation 1>
- <actionable recommendation 2>
## Open questions (defer to user)
- <anything subagents could not resolve>
Tell the user:
"Research phase complete. Report at
research-report.md. Key findings: <2-3 bullet summary>. Open questions: . Ready for Phase 3 (writing-plans)."
If open questions exist, ask the user before proceeding — do not auto-resolve.
Paste verbatim into every research subagent prompt:
Tool restrictions: Use only
WebSearchandWebFetchfor web work, andRead/Grep/Globfor codebase work. Do NOT use anymcp__claude-in-chrome__*tools — Chrome MCP is reserved for the main thread with explicit user consent. Violating this is a hard error.
npx claudepluginhub adeanima/marten-superpowerCreates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.