product-domain-engine
Conductor skill that formalizes any domain-tied product through a 5-phase protocol (identify-map-encode-express-deploy) expressed through four rhetorical modes (logos-ethos-pathos-kairos). Orchestrates seven existing skills.
What this skill does
# Product Domain Engine
The meta-system. Every product tied to a domain is an instance of the same operation: formalize informal knowledge into computable structure, then express that structure through four independent rhetorical channels.
This skill does not invent new patterns. It names a system that was already running across four products (`public-record-data-scrapper`, `styx`, `sovereign-systems--elevate-align`, `hokage-chess`) and was being re-derived every time. Naming it converts re-derivation into composition.
## What This Is
A **conductor**, not a monolith. The PDE sequences seven existing skills through a five-phase protocol, adds the rhetorical-mode framework that none of them carries, and provides the composition matrix that selects which output blends which mode.
You invoke this skill when the work to be done is *building a new product tied to a domain* — chess improvement, public records, behavioral economics, wellness, anything where lived knowledge needs to become computable structure.
## The Five-Phase Formalization Protocol
Every domain receives the same treatment. Phases are sequential within a single pass and recursive across product lifecycle.
### Phase 1 — IDENTIFY: the domain's agents
Who acts in this space? Their roles, incentives, constraints. The agent census is the first ontological move; it forces the domain to reveal itself as a graph of actors rather than a topic.
Drives the *systemic-product-analyst* skill (Lane A). Agents map onto users, opponents, intermediaries, gatekeepers, ledgers.
### Phase 2 — MAP: the domain's structures
Real relationships, hierarchies, flows, constraints. What binds the agents into a system? What can break or limit the system in reality (the constraint-domain pillars)?
Drives *market-gap-analysis* (competitive structure) and *research-synthesis-workflow* (causal structure).
### Phase 3 — ENCODE: structures as computable objects
Not concepts. Not documents. **Types, functions, schemas, tests.** The formalization becomes executable.
Drives *product-requirements-designer*. Output: typed interfaces, algorithm implementations, data schemas, deployable test suites.
This is the gate. A domain that cannot produce computable objects has not been formalized — it has only been described.
### Phase 4 — EXPRESS: through four rhetorical modes
The encoded structure speaks through four independent registers. They are not communication styles; they are independent output classes from the same underlying truth. See `references/rhetorical-modes.md`.
Drives *brand-guidelines* (pathos), *pitch-deck-patterns* (pathos+ethos), *content-distribution* (kairos+pathos).
### Phase 5 — DEPLOY: let density create gravity
The `public-record-data-scrapper` principle: a sufficiently dense, sufficiently real formalization attracts its own audience. The 4,455-word README, the 60+ collection agents, the 2,055 tests — that mass *was* the marketing.
Density is gravitational. Promotion only matters at low mass.
### The autopoietic loop
The protocol is not linear. Phase 5's output (deployment metrics, audience behavior, community questions) feeds back into Phase 1 (which agents matter most? which constraints are real?). The system makes itself.
```
IDENTIFY → MAP → ENCODE → EXPRESS → DEPLOY → OBSERVE
↑ │
└──────────────────────────────────────────────┘
observation refines the formalization
```
The OBSERVE step is implemented through analytics modules (e.g. hokage-chess `analytics.ts`, `growth.ts`). They are the observation instruments, not afterthoughts.
## The Four Rhetorical Modes
Classical rhetoric has four modes. Earlier internal drafts of this engine carried only three — the omitted fourth, **kairos**, is the most strategic, and we restore it here. See `references/rhetorical-modes.md` for the full treatment.
| Mode | Greek | Internal/External | Question it answers | Generation method |
|------|-------|------------------|---------------------|-------------------|
| Logos | λόγος | Internal | What is structurally true? | Engineering — types, proofs, algorithms |
| Ethos | ἦθος | External | Why should this be trusted? | Academic density — research, tests, citations |
| Pathos | πάθος | External | Why does this matter to a human? | Social/media content — community, voice, narrative |
| Kairos | καιρός | Strategic | When is the right moment? | Market-timing analysis, zeitgeist alignment |
**Logos is never customer-facing on its own.** It always expresses through ethos (the audience sees that proofs *exist* and trusts the source) or pathos (the audience feels the formalization through narrative). The customer never consumes types directly; they consume credibility or feeling.
**Ethos is built through scholarly density.** Research papers, source lists, test counts, deployment URLs, PROVENANCE files. The depth of the research is the raw material that ethos is forged from.
**Pathos is built through social/media volume.** YouTube, Discord, email sequences, landing pages, brand voice, naming systems, physical objects. The authenticity and volume of the media is the raw material.
**Kairos is built through market-timing observation.** When is the wave arriving, peaking, fading? Each domain rides a zeitgeist; kairos is the choice of when to enter and when to hold.
## The Composition Matrix
Every product output is a specific blend of the four modes. The blend ratio determines what the output *is*. See `references/composition-matrix.md` for the full table; the abridged version:
| Output | Logos | Ethos | Pathos | Kairos |
|--------|:-----:|:-----:|:------:|:------:|
| Technical spec | ■■■ | — | — | — |
| Test suite | ■■■ | ■■ ext | — | — |
| Academic study | ■■■ | ■■■ ext | — | ■ |
| README (flagship) | ■■ | ■■■ ext | — | — |
| Source list | ■■■ | ■■■ ext | — | — |
| Financial model | ■■■ | ■■ ext | — | ■ |
| Pitch deck | ■ | ■■ ext | ■■ ext | ■ |
| Landing page | ■ | ■ | ■■■ ext | ■■ |
| YouTube content | ■ | — | ■■■ ext | ■■ |
| Community (Discord) | — | — | ■■■ ext | ■ |
| Physical product | — | — | ■■■ ext | ■ |
| Email sequence | — | — | ■■ ext | ■■ |
| Launch announcement | — | — | ■■ ext | ■■■ |
| Roadmap | ■ | ■ | — | ■■■ |
`ext` = the mode's *external function* (what the audience consumes), distinct from its internal mass.
## The Prompt Sequence
Universal build commands, ordered per domain stage. See `references/prompt-sequence.md` for the full sequence with example invocations. Five tiers:
1. **Foundation** — what is this domain? (`$MODE`, `$DEPTH`, Natural Center, constraint-domain pillars)
2. **Research** — scholarly study (`$RESEARCH_ATLAS_V3`, peer-reviewed sources, methodological pillars)
3. **Architecture** — how does it become a system? (`$REPO_ARCHITECTURE_CME_FULL`, brand embedding structure, algorithms)
4. **Product Expression** — logos→ethos→pathos outputs (one-pager, landing page, pitch deck, experiment design pack)
5. **Deployment & Scaling** — service scaffolds, multi-tenant SaaS, orchestration
**Order varies by stage:**
| Stage | Sequence |
|-------|----------|
| New domain (e.g. hokage-chess at session start) | 1 → 2 (light) → 3 → 4 → 5 |
| Theory-heavy (e.g. styx) | 1 → 2 (deep) → 3 → 4 → 5 |
| Already-deployed (e.g. public-record-data-scrapper) | 3 → 4 → 5 (1 and 2 already done) |
| Client-driven (e.g. elevate-align) | 1 → 4 → 3 → 5 (pathos first, architecture follows brand) |
## Organ Chain Traversal
Every domain selects which ORGANVM organs it must cross. Not every domain crosses all seven.
| Organ | Function | Logos role | Output kind |
|-------|----------|-----------|-------------|
| I — Theoria | Formalize the domain's truth | types, proofs, research | research papers, theory documents |
| II — Poiesis | Express it aesthetically | brand, visual identity | brand voice, visual system, narrative |
| III — Ergon | Derive revenue | products, pricing, funnel | landing page, course, SaaS |
| IV — Taxis | OrchestrRelated in Cloud & DevOps
appbuilder-action-scaffolder
IncludedCreate, implement, deploy, and debug Adobe Runtime actions with consistent layout, validation, and error handling. Use this skill whenever the user needs to add actions to an App Builder project, understand action structure (params, response format, web/raw actions), configure actions in the manifest, use App Builder SDKs (State, Files, Events, database), deploy and invoke actions via CLI, debug action issues, or implement patterns such as webhook receivers, custom event providers, journaling consumers, large payload redirects, action sequence pipelines, and Asset Compute workers. Also trigger when users mention serverless functions in Adobe context, action logging, IMS authentication for actions, or cron-style scheduled actions.
orchestrating-datacloud
IncludedSalesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. Use this skill when the user needs a multi-step Data Cloud pipeline, cross-phase troubleshooting, or data space and data kit management. TRIGGER when: user needs a multi-step Data Cloud pipeline, asks to set up or troubleshoot Data Cloud across phases, manages data spaces or data kits, or wants a cross-phase sf data360 workflow. DO NOT TRIGGER when: work is isolated to a single phase (use the matching phase-specific skill), the task is STDM/session tracing/parquet telemetry (use observing-agentforce), standard CRM SOQL (use querying-soql), or Apex implementation (use generating-apex).
github-project-automation
IncludedAutomate GitHub repository setup with CI/CD workflows, issue templates, Dependabot, and CodeQL security scanning. Includes 12 production-tested workflows and prevents 18 errors: YAML syntax, action pinning, and configuration. Use when: setting up GitHub Actions CI/CD, creating issue/PR templates, enabling Dependabot or CodeQL scanning, deploying to Cloudflare Workers, implementing matrix testing, or troubleshooting YAML indentation, action version pinning, secrets syntax, runner versions, or CodeQL configuration. Keywords: github actions, github workflow, ci/cd, issue templates, pull request templates, dependabot, codeql, security scanning, yaml syntax, github automation, repository setup, workflow templates, github actions matrix, secrets management, branch protection, codeowners, github projects, continuous integration, continuous deployment, workflow syntax error, action version pinning, runner version, github context, yaml indentation error
sf-datacloud
IncludedSalesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. TRIGGER when: user needs a multi-step Data Cloud pipeline, asks to set up or troubleshoot Data Cloud across phases, manages data spaces or data kits, or wants a cross-phase `sf data360` workflow. DO NOT TRIGGER when: work is isolated to a single phase (use the matching sf-datacloud-* skill), the task is STDM/session tracing/parquet telemetry (use sf-ai-agentforce-observability), standard CRM SOQL (use sf-soql), or Apex implementation (use sf-apex).
fabric-cli
IncludedUse this skill for Fabric.so CLI workflows with the `fabric` terminal command: diagnose/install/login, search or browse a Fabric library, save notes/links/files, create folders, ask the Fabric AI assistant, manage tasks/workspaces, generate shell completion, check subscription usage, produce JSON output, and use Fabric as persistent agent memory. Do not use for Microsoft Fabric/Azure/Power BI `fab`, Daniel Miessler's Fabric framework, Python Fabric SSH, Fabric.js, or textile/fashion fabric.
lark
IncludedLark/Feishu CLI skills: lark-cli operations for docs, markdown, sheets, base, calendar, im, mail, task, okr, drive, wiki, slides, whiteboard, apps, approval, attendance, contact, vc, minutes, event. Use when the user needs to operate Lark/Feishu resources via lark-cli, send messages, manage documents, spreadsheets, calendars, tasks, OKRs, deploy web pages, or any Feishu/Lark workspace operations.