aj-geddes/bmad-help
bmad-planning-orchestrator/skills/bmad-help/SKILL.md
Orchestration spine and "what do I do next?" router for the BMAD Planning & Orchestrator plugin. Detects current planning state by scanning the output folder for which artifacts exist (project-context.md, decision-log.md, product-brief, prd/tech-spec, architecture, ux, epics, stories), infers the current phase and track, then recommends the next BMAD skill to run — skipping optional phases (Analysis is always optional; UX only when there is a UI). Use when the user asks "what's next", "what do I do next", "where am I", "what's my status", "continue", "resume planning", "which skill should I run", "what BMAD step is next", or types "/bmad-help" / "/status". Auto-invoke at the start of any BMAD planning session to orient. This skill ROUTES only — it never writes planning documents itself.
$ install --global
skillsauthnpx skillsauth add aj-geddes/claude-code-bmad-skills bmad-helpInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 20, 2026, 4:07 AM112.4s4 files scanned
SKILL.md
- name:
- bmad-help
- description:
- |
- allowed-tools:
- Read, Bash, Glob, Grep, TodoWrite
BMAD Help — Orchestration Spine
A lean router. It answers one question: what do I run next? It detects planning state, infers the phase and track, and points to the next skill. It is auto-invoked to orient a session and replaces a heavyweight master/orchestrator agent.
This skill produces NO planning documents. It reads state and recommends. All artifacts are produced by the specialized planning skills it routes to.
When to use
- User asks "what's next", "where am I", "what's my status", "continue", "resume".
- Start of any BMAD session, to orient before doing planning work.
- User is unsure which skill to invoke.
Phase Map
Analysis ──► Planning ──► Solutioning ──► Implementation-handoff
(optional) (required) (conditional) (required: ready-for-dev stories)
| Phase | Artifact(s) | Skill |
|-------|-------------|-------|
| Analysis (optional) | product-brief, research, brainstorm | bmad-product-brief / bmad-research / bmad-brainstorm |
| Planning (required) | prd.md OR tech-spec.md, epics.md | bmad-prd / bmad-tech-spec / bmad-epics-and-stories |
| Planning — UX (only if UI) | ux-design.md | bmad-ux |
| Solutioning (track-dependent) | architecture.md | bmad-architecture |
| Implementation-handoff (required) | {epic}.{story}.{slug}.story.md (ready-for-dev) | bmad-epics-and-stories → bmad-sprint-planning |
Threaded across every phase: project-context.md (the project "constitution") and decision-log.md (decisions carried between workflows). If these are missing, the first recommendation is always to establish them.
Implementation itself (writing code, running tests) is OUT OF SCOPE. The last artifact this plugin produces is a ready-for-dev story file or handoff manifest, passed to an external dev tool.
Tracks (scale-adaptive — never numbered levels)
A heuristic may suggest a track from story count; the user confirms.
| Track | Scope | Required planning | Optional | |-------|-------|-------------------|----------| | Quick Flow | 1–15 stories | tech-spec + stories | analysis, ux | | BMad Method | 10–50+ stories | prd + architecture + epics + stories | analysis; ux (if UI) | | Enterprise | 30+ stories | prd + architecture + security + devops + epics + stories | analysis |
Per-track required vs optional steps in detail: see REFERENCE.md.
How it works
-
Detect state. Run the detector to list which artifacts exist and the inferred phase:
bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-help/scripts/detect-state.sh [output-folder]Default output folder is
bmad-output/. It prints a checklist of artifacts (present or missing), the detected track (from decision-log if recorded), and the inferred phase. -
Recommend next. Map the detected state to the next skill:
bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-help/scripts/recommend-next.sh [output-folder]It prints the single next skill to run, plus why, plus any skipped optional phases.
-
Present the recommendation to the user in plain prose. Offer to invoke the recommended skill. Do not auto-run planning skills without confirmation when the track is still ambiguous.
If project-context.md does not exist yet, treat the project as un-initialized: the
recommendation is to start with bmad-init (or bmad-product-brief if the user wants the
optional Analysis phase first) to establish project context and choose a track.
Routing logic (summary)
Evaluate in order; recommend the first unmet step for the active track.
- No
project-context.md→ establish project context (runbmad-init, orbmad-product-briefif the user opts into Analysis). Confirm the track. - No
prd.mdand notech-spec.md→- Quick Flow →
bmad-tech-spec(tech-spec). - BMad Method / Enterprise →
bmad-prd(PRD).
- Quick Flow →
- Project has a UI and no
ux-design.md(BMad/Enterprise) →bmad-ux. - Track needs architecture and no
architecture.md(BMad/Enterprise) →bmad-architecture. (Quick Flow skips architecture.) - Enterprise and no security/devops planning →
bmad-architecture(security + devops sections / handoff). - No
epics.md(BMad/Enterprise) →bmad-epics-and-stories(epic breakdown). - No story files under
stories/→bmad-epics-and-stories(create ready-for-dev stories). - Stories exist but some are still
backlog/notready-for-dev→bmad-epics-and-stories(finish compiling story context objects); thenbmad-sprint-planningto sequence waves. - All required artifacts present and stories are
ready-for-dev→ handoff complete. Recommend handing the stories to the external dev tool. Nothing left to plan.
Skipping rules: Analysis is always optional — never block on it. UX is recommended only when the project has a UI. Architecture is skipped for Quick Flow.
Full decision table with edge cases: REFERENCE.md.
Notes for Claude
- This is the entry point. Always detect state before recommending.
- Recommend exactly ONE next skill. Keep it actionable.
- Never produce planning documents here — route to the owning skill.
- Never recommend running tests, builds, linters, or writing code — that is out of scope for this plugin entirely.
- Respect locked sections: Acceptance Criteria, Dev Notes, and Testing in story files are owned by planning skills and must not be edited downstream.
- Use
decision-log.mdto read the confirmed track; if absent, ask the user to confirm the track before recommending track-specific steps.
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-help. All methodology credit belongs to the BMAD Code Organization.
Related Skills
aj-geddes/bmad-ux
testing
VerifiedTrustedCommunity
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.
451SKILL.mdUpdated Jun 20, 2026
aj-geddes/bmad-tech-spec
testing
VerifiedTrustedCommunity
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).
451SKILL.mdUpdated Jun 20, 2026
aj-geddes/bmad-sprint-planning
tools
VerifiedTrustedCommunity
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.
451SKILL.mdUpdated Jun 20, 2026
aj-geddes/bmad-spec
development
VerifiedTrustedCommunity
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.
451SKILL.mdUpdated Jun 20, 2026