Single plugin, namespaced
All Vakari work routes through /vakari:<skill>. No fragmented plugin maze, no name collisions, no "which version of /research is this." One pull, one install, one source of truth.
A consolidated Claude Code plugin that encodes the full Vakari workflow — research, strategy, creative, production guidance, diagnostics, reporting, case studies, sell — as skills that hand off clean packets to each other.
Each one is load-bearing. Together they explain why this is one plugin instead of fifteen separate skills — and why outputs feel coherent across skills you've never explicitly trained together.
All Vakari work routes through /vakari:<skill>. No fragmented plugin maze, no name collisions, no "which version of /research is this." One pull, one install, one source of truth.
Skills produce Markdown packets with named sections — not rigid JSON. Enough structure to make the next skill's job reliable; loose enough that judgment isn't squeezed out.
Nine shared reference files hold the operating doctrine — confidence levels, packet shapes, artifact system, diagnostic rules. Skills consult them. Updating one reference makes every consuming skill smarter without per-skill rewrites.
Every generating skill produces both — a text-heavy Markdown packet (the carrier) and a fit-for-purpose HTML artifact (the action surface, designed for what someone actually wants to do with it).
The canonical chain runs through research → strategy → planning → production. Three loops sit around it: feedback (winners), data (campaigns DB), artifact + sell (proof and growth). Click any skill node to jump to its detail.
vakari:researchvakari:meta-strategyvakari:campaignvakari:creative-strategyvakari:scriptsvakari:static-adsvakari:designvakari:transcribevakari:winnersvakari:ingestvakari:diagnosevakari:reportvakari:case-studyvakari:growth-diagnosticvakari:sell
Each handoff is a packet — a Markdown doc with named sections defined in references/packet-contracts.md. Skills can skip levels (case-study consumes research + campaign + winners + transcripts directly), but the chain is the default reliable route. The data loop accepts two input shapes: a Meta CSV (loaded into the campaigns DB) or a performance-packet bundling Meta-side metrics with downstream CRM funnel data (Meta rows written to the DB; full-funnel context preserved as queryable Markdown).
Each skill stays lean by deferring shared concepts to references. Click + details on any skill to see inputs, outputs, agents, and references. Click any slash command to copy it.
Client research orchestrator — foundation or campaign-add mode. Spawns 5 specialist agents in parallel; produces research-packet, brand.json updates, and an HTML client-intelligence dashboard.
Meta account architecture + operational strategy. Translates research into how the account is structured and operated. ABO equal-spend default per methodology.
Campaign launch planner — the launch container. Defines slots to be tested (format + hypothesis + production route), budget allocation, success/kill criteria. Hands off slots; doesn't fill them.
Concept generator. Fills each campaign variant slot with a concept (angle + hook + visual + format + production route + what it tests). Consults winners library and creative intelligence by default.
Video ad script writer. Each script follows the Vakari 5-beat path (hook → pain → outcome → offer → CTA) in the client's voice. Reads winners + brand.json + audience language.
Static (and carousel) ad planning + copy. On-image text, primary text, description, CTA, format, dimensions, carousel order. Plans the copy; doesn't execute the design.
Static ad design + production-route recommendation. Per-job tooling (Figma / AI generation / HTML render / hybrid) — owns the design spec and recommends the route, optionally executes HTML render for typographic ads.
Local video transcription via yt-dlp + mlx_whisper. Accepts Instagram URLs, Meta Ad Library URLs, business names, batch instructions. Produces transcript-packet + JSON word-timings for HyperFrames caption sync.
<spot>/_docs/script-as-delivered.md + <spot>/transcript.json~/wikis/vakari/raw/notes/7-category winner capture. Stores proven creative — video scripts, static ads, prompts, offers, visual hooks, campaign structures, downstream-quality observations — with templatized versions for cross-client reuse.
_winners/<vertical>/<category>/<slug>.md[COMPANY], [CITY], [SPEC], etc.) so future skills can fill the template for new clients in the same vertical.creative-intelligence.md via wiki ingest.Two modes — Meta CSV → campaigns DB, or performance-packet (Meta + CRM full-funnel together, produced by the external data layer) → campaigns DB (Meta rows) + preserved as queryable Markdown (downstream context). Auto-detects mode. Idempotent. Doesn't make recommendations — emits an ingest log + recommended-next-skill pointer.
Live-campaign triage. Reads the performance-packet (Meta + CRM together) where available, plus the campaigns DB. Applies kill rules / troubleshooting patterns / fatigue thresholds / scaling triggers. Separates cheap leads from leads that actually progress, weighted by attribution confidence. Produces priority-tagged actions (Immediate / This Week / Monitor). Internal tier — direct, no client softening.
exact matches reliable, strong-inferred usable with caveats, weak-inferred shouldn't drive kill/scale decisions alone.diagnostic-rules.mdRecurring client-facing performance report. Reads the performance-packet (Meta + CRM together) where available for full-funnel framing — lead quality and pipeline movement alongside the headline metrics, not just CPL. Client-facing tier — polished, narrative, no internal jargon.
Prospect Blueprint diagnostic. 6 weighted pillars (acquisition, conversion, lead handoff, sales process, measurement integrity, unit economics). Scorecard + funnel leak map + top findings + quick wins + 30-day roadmap. Engine for the paid Blueprint deliverable.
Durable proof / narrative artifact from a closed campaign. Three tiers — internal (sources cited), client-facing (polished), prospect-facing (one-paragraph + KPI bar). ONE headline metric discipline; named transferable pattern.
Founder-led sales advisor for agency operations. Modes spanning the sales cycle — outreach, blueprint framing, pre-call prep, discovery, qualification, objection handling, proposal drafting, follow-up. Composes with public sales frameworks for depth on hard prospects.
Skills stay lean by deferring shared concepts here. Updating one reference makes every consuming skill smarter without per-skill rewrites — the engine for ongoing improvement.
| Reference | What it owns | Consumed by |
|---|---|---|
| methodology.md | Operating doctrine: account-structure defaults (ABO equal-spend) · four-level confidence scale · brand-as-reference framing · lead-conversion moat | every skill |
| artifact-system.md | MD-as-carrier / HTML-as-deliverable doctrine · use-first design · 3 tiers (internal/client/prospect) · rejection of default shapes | every generating skill |
| artifact-components.md | 13-component vocabulary: KPI cards · scorecards · funnel leak maps · campaign architecture maps · script cards · hook tables · creative test matrices · persona cards · competitor blocks · prompt blocks · source drawers · action cards · tier markers | every HTML-rendering skill |
| packet-contracts.md | 14 packet shapes: research · meta-strategy · campaign · creative-strategy · script · static-ad · design · performance (Meta + CRM full-funnel with attribution confidence) · winner · diagnosis · prospect-blueprint · case-study · ingest · transcript | every skill |
| winners-schema.md | 7-category winner taxonomy · per-type required content · file location convention · templatization rules · promotion path | winners · scripts · static-ads · creative-strategy · design · case-study · sell · growth-diagnostic |
| creative-intelligence.md | Crystallized patterns from validated winners — hook patterns · offer patterns · visual patterns · campaign-structure patterns · downstream-quality patterns · format patterns · script structure patterns · vertical notes | scripts · static-ads · creative-strategy · design · sell · growth-diagnostic · meta-strategy · diagnose |
| case-study-schema.md | Three tier shapes · ONE-headline-metric discipline · pattern naming · sources discipline · file naming | case-study · sell |
| data-paths.md | Canonical paths to the campaigns DB · ingestion + analysis scripts · CRM fetch wrapper · performance-packet drop location + naming + preservation rules · brief DB schema · idiomatic query examples | ingest · diagnose · report |
| diagnostic-rules.md | Kill rules (hard + soft) · troubleshooting pattern matching · frequency / fatigue thresholds · scaling rules · don't-recommend-changes rules · common-mistakes watchlist | diagnose · report |
These are the canonical compositions. Skip-level invocations are fine (case-study can consume research + winners directly), but these are the reliable default chains.
When: a new client signs up. Goal: get from intake brief to a launched campaign with a documented creative foundation.
When: a campaign is running. Goal: surface what to do this week + capture what's working.
optimization_log for closed-loop tracking.When: a campaign closes with proof worth carrying forward. Goal: durable proof artifact + named transferable pattern.
creative-intelligence.md in the next wiki ingest.When: a prospect signs up for the paid Blueprint diagnostic (or a new client needs a baseline assessment).
When: any sales interaction — outreach, pre-call prep, discovery, qualification, objection handling, proposal, follow-up.
<!-- ADD: --> slot. The skill gets sharper with each completed conversation.The architecture isn't just for organization — it's for compounding. Three mechanics make every campaign improve every future campaign.
Proven creative gets captured via /vakari:winners with structured evidence. When 3+ winners share an underlying mechanism, the pattern crystallizes in creative-intelligence.md through wiki ingest. All consuming skills (scripts, static-ads, creative-strategy, design) immediately reference the new pattern on next invocation.
Every skill consumes and produces packets with named sections. The contract forces skills to surface what they need rather than guess; it forces upstream skills to deliver substantive output rather than narrate. Brittle conversations become reliable handoffs that survive across sessions and across machines.
When the diagnostic rules need a new kill threshold, edit diagnostic-rules.md once. /vakari:diagnose and /vakari:report both pick it up immediately. When a new artifact component earns its place, add to artifact-components.md — every HTML-producing skill has the new vocabulary. No per-skill rewrites.