bmad-planning-orchestrator/skills/bmad-research/SKILL.md
Conducts market, competitive, domain, and technical research using live web sources, producing a cited research-report.md to inform BMAD planning decisions. Use when the user says: - "research [topic/market/technology]" - "competitive analysis" or "who are the competitors" - "market size" or "market landscape" - "technical research" or "evaluate [technology/framework]" - "domain research" or "industry analysis" - "what does the market look like" - "find out about [technology/space]" - "I need research before we plan" - "gather information on [topic]" Supports three modes: Create (new research), Update (refresh existing report with new sources), Validate (cross-check claims in an existing report against live sources). Output lands in bmad-output/ as a cited research-report.md ready for downstream planning skills (business-analyst, product-manager, system-architect).
npx skillsauth add aj-geddes/claude-code-bmad-skills bmad-researchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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.
testing
Solutioning-phase UX planning skill (optional; activate when the project has a UI). Produces TWO planning documents: DESIGN.md (the visual system — design tokens, color palette, typography, spacing, component specs, WCAG 2.1 AA contract) and EXPERIENCE.md (user journeys, flow diagrams, screen states, error/empty/loading handling). Use when the user says "design the UX", "create UX planning docs", "define the design system", "map the user flows", "UX for this feature", "wireframe the flows", "what are the user journeys", "accessibility design", "WCAG compliance", "design tokens", "responsive design plan", "mobile-first design", or "create DESIGN.md / EXPERIENCE.md". Runs after architecture is drafted and before stories are created. Supports Create / Update / Validate intents.
testing
Quick Flow lightweight technical specification for small-scope work (1-15 stories). Replaces the full PRD + architecture pair when scope is small and requirements are clear. Produces bmad-output/tech-spec.md as the single planning artifact before story creation. Use when the user says: "write a tech spec", "create a technical specification", "I need a tech spec for this feature", "quick spec", "small project spec", "we don't need a full PRD", "just a tech spec", "spec out this change", "document this feature". QUICK FLOW TRACK ONLY (1-15 stories). If scope grows beyond ~15 stories or involves multiple teams / external integrations at scale, stop and redirect to bmad-prd + bmad-architecture instead — those skills are built for that complexity. Supports three intents: Create (new spec), Update (revise an existing tech-spec.md), Validate (review a draft for completeness against BMAD criteria).
tools
Orchestration handoff bridge: emits and maintains sprint-status.yaml as the project's sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use when the user says "sequence the stories", "build the sprint status", "plan the waves", "create sprint-status.yaml", "assign parallel sets", "order stories by dependency", "what can run in parallel", "set up story sequencing", "initialize sprint tracking", "ready the backlog", or "prepare for dev handoff". Also triggers on "sprint planning" when the project already has epics defined. SCOPE: SEQUENCING AND ORCHESTRATION ONLY. No velocity, no burndown, no committed points, no coverage metrics. Capacity is expressed as wave width (concurrent story count), not points. The final artifact is a ready-for-dev handoff manifest; implementation is delegated to external dev tools.
development
Distills ANY messy input — brain dump, transcript, long PRD, stakeholder notes, feature request, voice memo — into a tight five-field SPEC.md kernel that any downstream planning skill can consume. The five fields are: Problem, Capabilities, Constraints, Non-Goals, Success Metrics. Use when the user says "create a spec", "write a spec for", "distill this into a spec", "I have a brain dump", "turn this into something structured", "clean up these notes", "make a SPEC from", "I want to define the problem", "help me scope this", "summarize what we're building", "I have a PRD but need a kernel", "what are we actually solving?", or drops raw text/transcript and asks for structure. Also use when starting any new initiative and a clean shared definition is missing.