From BMAD Planning & Orchestrator
Conducts market, competitive, technical, and domain research using live web sources, producing a cited report for downstream planning skills.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bmad-planning-orchestrator:bmad-researchThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Conducts structured, cited research across three modes to feed BMAD planning workflows.
Conducts structured, cited research across three modes to feed BMAD planning workflows. Output is a research-report.md in bmad-output/, ready for handoff to planning skills.
Before searching, confirm:
bmad-output/research-report.mdIf project-context.md exists, read it first (bmad-output/project-context.md) for
scope constraints.
Use the source-type strategy guide to pick sources by research type:
${CLAUDE_PLUGIN_ROOT}/skills/bmad-research/scripts/research-sources.sh
Run it (Bash) to print the guide, then sketch a query plan:
Track progress with TodoWrite.
Citation discipline: for every factual claim, record source URL + access date.
When a claim cannot be verified across 2+ sources, mark it [UNVERIFIED].
If mode is Update, read the existing report first. Then:
[UNVERIFIED])If mode is Validate:
[VERIFIED], [CONTRADICTED source: …], or [UNVERIFIED]Use the template:
${CLAUDE_PLUGIN_ROOT}/skills/bmad-research/templates/research-report.template.md
Fill all sections. Sections irrelevant to the research type may be omitted (mark as N/A). Write the completed report to:
bmad-output/research-report.md # or a user-specified path
Required sections regardless of mode:
After writing the report, tell the user:
Record the research decision in bmad-output/decision-log.md:
## Research: [Topic] — [Date]
- Mode: [Create/Update/Validate]
- Types: [Market/Competitive/Technical/Domain]
- Key finding: [one sentence]
- Report: bmad-output/research-report.md
- Next skill: [skill name]
For broad research covering multiple types simultaneously, fan out parallel agents:
Agent 1 — Market Agent
Read project-context.md, then conduct market research on [topic]:
TAM/SAM/SOM, growth rates, key trends. Write findings to
bmad-output/research-scratch/market.md with full citations.
Agent 2 — Competitive Agent
Read project-context.md, then research top 3-5 competitors for [topic]:
features, pricing, strengths/weaknesses, user sentiment. Write findings to
bmad-output/research-scratch/competitive.md with full citations.
Agent 3 — Technical/Domain Agent
Read project-context.md, then research technical landscape for [topic]:
technology options, ecosystem health, standards. Write findings to
bmad-output/research-scratch/technical.md with full citations.
After all agents complete, synthesize scratch files into the final report using the template. Delete scratch files after synthesis.
Part of the BMAD Planning & Orchestrator plugin — a Claude Code harness for the BMAD Method by the BMAD Code Organization (https://github.com/bmad-code-org/BMAD-METHOD). Implements the spirit of
bmad-market/domain/technical-research. All methodology credit belongs to the BMAD Code Organization.
npx claudepluginhub aj-geddes/claude-code-bmad-skills --plugin bmad-planning-orchestratorConducts market, domain, or technical research using verified web sources. Routes to specialized tracks based on user input and outputs cited analysis documents.
Conducts deep research via parallel web searches, multi-source validation, and confidence tracking across 11 types like market, competitive, technical; outputs cited Markdown reports.
Conducts market research, competitive analysis, investor diligence, and tech scans with sourced findings, contrarian views, and decision recommendations.