Marketing Agentic SDLC Skill

Evidence-First marketing planning protocol for AI coding agents (Claude Code, Gemini CLI, Google Antigravity, Codex). The sibling of @antoneeo/agentic-sdlc-skill, transplanted from software engineering to marketing strategy.

What's new in 0.30.1

Codex hook checks can recognize the work the agent is doing. The shared validator recognizes supported native Codex patches and transcript records, and gives more accurate orientation-hook diagnostics when definitions are disabled or cannot be verified. Existing hook setup and opt-outs are preserved.

What to do

Run npm install -g @antoneeo/mkt-agentic-sdlc-skill@latest, then mkt-sdlc-install-skill, and restart your agent sessions so they load the updated validator. Check that npm ls -g @antoneeo/mkt-agentic-sdlc-skill shows 0.30.1. Any configured Codex hooks still require their normal client trust review.

Full history: CHANGELOG

What it does

Turns an AI agent into a disciplined marketing strategist that produces a professional, professionally-recognized marketing plan (SOSTAC structure) with three engineered guarantees:

1. Evidence ledger — every market number is classified FACT / BENCHMARK / ASSUMPTION and carries an [EV-nn] reference to its source. No invented numbers.
2. Mechanical validator (mkt_check.py + sdlc_core.py + knowledge.py — entry point, shared spine and memory; copy all three) — budget sums (±1%), funnel math recomputed cell by cell (±5%) and the objective→tactic→KPI chain are checked mechanically, not rhetorically: check, validate, ledger, budget, funnel, trace, index, plus the spine's stale/mark/benefit/gate/plan/orient/migrate. benefit reports what the review gates have already caught, beside what the doctrine costs to read; it always exits 0 and carries no verdict.
3. Adversarial CMO review — an independent, fresh-context reviewer attacks the strategy before the user sees it (generic-positioning swap test, untraced claims, orphan tactics).
4. Verbatim request record — every E3 engagement starts audit/requests/REQUEST_[engagement].md before Wave 1: the client's own words and every later decision, append-only and redacted for secrets; owner-given FACT rows and the plan cite its entries, and reviews check client statements against it.

The docs site (scripts/docs_site.py --root <project> [--open] [--zip <file>]) writes a static, offline, read-only website of what the agent reads in the project — reading guide, Vision, rules, documents, open work with each next step, and, with a knowledge base, the topic map, each fact with its exact source passage, and the source documents. It is written to .docs-site/ (added to .gitignore on the first run), outside the docs root (mkt_docs/ or ai_docs/); nothing is ranked or recommended.

The agent asks the user only for facts the user uniquely owns (product, price, budget, capacity); everything else — market sizing, competitor analysis, channel benchmarks — is derived from real web research.

Shared project memory

All four lenses include project memory by default; install the lens you need, not a second skill just for recall. index registers guides, decisions and plans in the docs root's memory/INDEX.md, linking originals without copying them. recall "onboarding" finds related metadata across domains; optional topics: [onboarding] links documents by subject. Read the originals for authority, status and evidence: discovery is not approval or proof of implementation.

Registration happens at index/documentation closure, not through a background watcher. Existing projects acquire the catalog on their next index; recall also sees live metadata. The KB lens remains the specialist for ingestion and taxonomy. Marketing retains its numerical validators. See the skill's memory.md. Vendoring requires all three files: the entry point, sdlc_core.py, knowledge.py.

Install

npm i -g @antoneeo/mkt-agentic-sdlc-skill

That's it — the skill is copied into every detected AI client automatically (the package's postinstall runs the installer). Restart the agent to load it.

If your npm blocks install scripts (--ignore-scripts, some CI/pnpm setups), run the installer manually:

npx mkt-sdlc-install-skill

The mkt-sdlc-install-skill command is only on your PATH after a global (-g) install. After a local npm i, invoke it via npx as above.

Initialize a project:

cd my-business-project
npx mkt-sdlc-init        # creates mkt_docs/ + protocol pointers

It also wires the SessionStart orientation hook into .claude/, so an agent opening the project is handed the triage line, the guide router, the workstream registry and the reading guide (with pointers to the manifest) before it does anything — instead of only when it remembers to look. That wiring used to be a manual step documented in ENFORCEMENT.md; being manual, it was skipped, and a project could run fully governed with an agent that never met the process.

The hook command names a validator, so where that validator lives decides which file gets it: a repo that vendors it gets a repo-relative command in the shared .claude/settings.json (portable — commit it); otherwise the path is machine-specific and goes to the git-ignored .claude/settings.local.json, and each teammate runs init once. Re-running init never duplicates the hook, and a hook whose validator no longer resolves is reported as broken with the correction rather than counted as installed.

Engagement levels (Rule Zero)

Several people, one project

The workstream registry (audit/handoff.md) is generated from one file per open workstream, so two people opening or closing two workstreams on two branches edit two different files and their merge is clean. Row-per-workstream alone was not enough — a file-global Date: header defeats row-level ownership — so the header is derived from the sources and no writer touches it. The generated view can still conflict; that conflict is resolved by re-running index, never by hand, and validate refuses CLEAN until the file matches its sources. The append-only review log gets merge=union (a built-in driver, no per-clone configuration). It all works with no VCS at all: it is files and a generator.

Modes

• Standalone — everything on the filesystem under mkt_docs/.
• Hybrid with devPNT — plans and strategy artifacts governed as versioned devPNT documents (MKT-VISION, ICP/Personas, Threat Map, Strategy, Tactical Plan, Measurement Plan), with proposal/approval workflow; every artifact passes an independent agent review before it is proposed, and devPNT is where you review and approve it.

On a shared ai_docs/ tree, run mkt_check.py index --docs-dir ai_docs to generate the common index. An existing marketing-format ai_docs/INDEX.md receives an explicit migration diagnostic; validate and check leave it untouched. Marketing-specific checks run when the tree declares a marketing engagement, while a course-only tree remains governed by its own course lens.

The Hybrid seam ships as its own file, hybrid.md — the authoritative hierarchy and the ownership matrix naming which artifact is mastered where. A Standalone engagement never reads it, which is why it is not in the operating contract every session loads.

Installing or updating the npm package wires the session-orientation hook machine-wide (user-level Claude Code settings; removal is a standing opt-out that no update overrides -- ENFORCEMENT.md par.4).

The family: four lenses, one spine

The four lenses share the process spine and project memory. Each lens keeps its own fidelity discipline. When two live in the same project, routing.md decides ownership by the deliverable's purpose: persuasion is marketing, instruction for a learner is course, even when both draw on the same source documents.

Which model to run it on

The skill names capability tiers, never providers — a model name in doctrine rots at the next release. The binding is yours to make, and the rule is one line:

A session's floor is the highest floor among the roles it performs itself.

Authoring a governed artifact — the vision, the analysis, the use cases, the threat model — is a deep-tier role: its output is judgement, and nothing downstream scores it. So a session that will DESIGN wants your strongest model. A session that only executes an already-approved plan, or does small maintenance, can sit a tier lower. The cheapest tier is the wrong choice for the main session whatever the task, because the failure there is not a wrong answer — it is silently not applying the process: a triage never run, a router verdict declared without the lookup, a gate nobody noticed. That failure is invisible to every check in here.

The reviewer's tier is not automatically yours. On some clients a subagent inherits the session's model; on others it takes one from its own definition, so a strong session can be reviewed by a weak one — and a weak session can buy a strong review. Set it deliberately; the model column in the review log is where the choice becomes visible.

Avoid one combination: authoring below the floor AND reviewing below the floor on the same unit. One disclosed weakness is a disclosed weakness; two is an artifact nobody competent ever read. Where your client offers nothing better, the review still runs and both facts are recorded — a disclosed worst case beats skipping the review.

License

Apache-2.0 — the full terms are in the LICENSE file, the attribution in NOTICE. Copyright 2026 Antonio Pinto.

If you redistribute this skill, or a version you modified, keep LICENSE and NOTICE with it.

Using the skill in your own project carries no obligation: the documents it creates or templates there are yours, and so is a copy of the validator and its tests placed in that project to check its own documents.

Versions up to 0.11.0 were released under the MIT license and remain available under it.

If you use the skill in commercial work, a mention on your product page or website is appreciated. It is a request, not a condition of the license. A ready-made badge:

[![Made with mkt-agentic-sdlc](https://img.shields.io/badge/made%20with-mkt--agentic--sdlc-blue)](https://www.npmjs.com/package/@antoneeo/mkt-agentic-sdlc-skill)