marketing-cli 0.1.0 → 0.2.0

package/README.md

@@ -1,17 +1,18 @@
 <p align="center">
-  <img src="banner.svg" alt="mktg — agent-native marketing playbook CLI" width="100%">
+  <img src="banner.svg" alt="marketing-cli: agent-native marketing playbook" width="100%">
 </p>
 
 <p align="center">
-  <a href="https://github.com/MoizIbnYousaf/mktg/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-10b981" alt="MIT License"></a>
-  <img src="https://img.shields.io/badge/skills-49-10b981" alt="49 Skills">
+  <a href="https://github.com/MoizIbnYousaf/marketing-cli/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-10b981" alt="MIT License"></a>
+  <img src="https://img.shields.io/badge/skills-50-10b981" alt="50 Skills">
   <img src="https://img.shields.io/badge/agents-5-10b981" alt="5 Agents">
-  <img src="https://img.shields.io/badge/tests-extensive-10b981" alt="Extensive test suite">
+  <a href="https://www.npmjs.com/package/marketing-cli"><img src="https://img.shields.io/npm/v/marketing-cli?color=10b981" alt="npm"></a>
+  <img src="https://img.shields.io/badge/tests-2,371-10b981" alt="2,371 tests">
   <img src="https://img.shields.io/badge/TypeScript-strict-3178c6" alt="TypeScript Strict">
 </p>
 
 <p align="center">
-  <b>One install gives AI agents a complete CMO brain — brand memory, parallel research, and 49 composable marketing skills.</b>
+  <b>One install. A full marketing department for your agent: 50 skills, 5 agents, 10 brand memory files.</b>
 </p>
 
 ---
@@ -22,48 +23,48 @@ You have a product. You need marketing. You ask your AI agent to help.
 
 It writes generic copy. It doesn't know your voice. It forgets your audience by next session. It can't research competitors, plan keywords, or coordinate a launch. Every conversation starts from zero.
 
-**mktg fixes this.** One install turns your agent into a marketing department that remembers everything, researches in parallel, and gets sharper with every session.
+One install turns your agent into a marketing department that remembers everything, researches in parallel, and gets sharper with every session.
 
 ---
 
 ## How It Works
 
 <p align="center">
-  <img src="explainer.gif" alt="How mktg works — animated explainer" width="720">
+  <img src="explainer.gif" alt="How marketing-cli works" width="720">
 </p>
 ---
 
-## The Ecosystem — what you actually install
+## The Ecosystem: What You Actually Install
 
-`mktg init` isn't just a CLI install. It bootstraps a layered agent-native marketing workstation.
+`mktg init` bootstraps the full workstation.
 
-### Core — always installed
+### Core (always installed)
 
 | | |
 |---|---|
-| **`mktg` CLI** | 15 commands, 21/21 Agent DX score, JSON-by-default |
-| **49 marketing skills** | The playbook, copied to `~/.claude/skills/` |
+| **`mktg` CLI** | 16 commands, 21/21 Agent DX score, JSON-by-default |
+| **50 marketing skills** | The playbook, copied to `~/.claude/skills/` |
 | **5 research + review agents** | Parallel sub-agents in `~/.claude/agents/` |
 | **10 brand files** | Persistent marketing memory in your project's `brand/` |
 | **`/cmo` orchestrator** | The brain that routes every request to the right skill |
 
-### Chained-in CLIs — external tools mktg orchestrates
+### Chained-in CLIs (external tools mktg orchestrates)
 
-These are **not bundled**. They're external binaries mktg's skills know how to use. `mktg doctor` detects them and surfaces the gap with an install hint. Install the ones you need — skills that require them use them when present and degrade gracefully when missing.
+Not bundled. These are external binaries that mktg's skills know how to call. `mktg doctor` detects what's missing and tells you how to install it. Skills fall back when a tool isn't present.
 
 | CLI | Role | Install |
 |---|---|---|
-| [`firecrawl`](https://github.com/firecrawl/cli) | Web scrape, search, crawl — clean markdown for LLMs | `npm i -g firecrawl` + `FIRECRAWL_API_KEY` |
+| [`firecrawl`](https://github.com/firecrawl/cli) | Web scrape, search, and crawl; outputs clean markdown for LLMs | `npm i -g firecrawl` + `FIRECRAWL_API_KEY` |
 | `ffmpeg` | Video assembly, encoding, frame extraction | `brew install ffmpeg` |
 | [`remotion`](https://remotion.dev) | Programmatic React video rendering | `npm i -g @remotion/cli` |
 | [`playwright-cli`](https://playwright.dev) | Browser automation for demo capture, scraping, CRO audits | `npm i -g @playwright/cli` |
 | [`gh`](https://cli.github.com) | GitHub CLI for launches, PR workflows, issue intelligence | `brew install gh` |
 | `whisper-cli` | Speech-to-text via whisper.cpp | `brew install whisper-cpp` |
 | `yt-dlp` | Media download from YouTube/TikTok/podcasts | `brew install yt-dlp` |
-| [`summarize`](https://github.com/steipete/summarize) | Text compression — TL;DR, digest, key points | `npm i -g @steipete/summarize` |
+| [`summarize`](https://github.com/steipete/summarize) | Text compression: TL;DR, digest, key points | `npm i -g @steipete/summarize` |
 | Exa MCP | Parallel deep research (default for agent web queries) | MCP config in `.mcp.json` |
 
-### Best-practices skills — how-to-use-a-tool knowledge
+### Best-practices skills (how-to-use-a-tool knowledge)
 
 When a chained-in CLI needs usage discipline (security, rate limiting, efficiency patterns), mktg ships a **best-practices skill** alongside it. These are reference SKILL.md files with a `rules/` subdirectory for depth.
 
@@ -71,17 +72,17 @@ Currently shipping: **`firecrawl`** (wraps the firecrawl CLI with `rules/install
 
 ### The orchestration philosophy
 
-**mktg orchestrates, it doesn't reimplement.** When a good tool exists, we chain it in and ship a best-practices skill alongside it. mktg stays focused on marketing playbooks — not reimplementing video encoders, browsers, or scraping engines. Every chained-in tool is a distinct, load-bearing piece of the marketing workstation.
+mktg orchestrates; it does not reimplement. When a good tool exists, we chain it in and ship a best-practices skill alongside it. mktg ships marketing playbooks, not video encoders.
 
 ---
 
 ## Quick Start
 
 ```bash
-npm i -g mktg && mktg init
+npm i -g marketing-cli && mktg init
 ```
 
-That's it. `init` detects your project, scaffolds `brand/`, installs 49 skills to `~/.claude/skills/`, installs 5 marketing agents to `~/.claude/agents/`, and runs `doctor` to verify everything works.
+That's it. `init` detects your project, scaffolds `brand/`, prefers `ai-agent-skills` for installing the 50 marketing skills when it is available on PATH, falls back to direct install into `~/.claude/skills/` when it is not, installs 5 marketing agents to `~/.claude/agents/`, and runs `doctor` to verify everything works.
 
 Then use `/cmo` in Claude Code:
 
@@ -98,7 +99,7 @@ a content engine.
 Want to start there?
 ```
 
-`/cmo` reads your project's marketing state, understands what's been done and what's missing, and routes to the right skill. It's not a menu — it's a strategic partner.
+`/cmo` reads your project's marketing state, knows what's done and what's missing, and routes to the right skill.
 
 ### Requirements
 
@@ -109,45 +110,41 @@ Want to start there?
 
 ## How It's Different
 
-Other marketing skill repos give you a folder of markdown files and wish you luck. **mktg is infrastructure.**
+Other marketing skill repos give you a folder of markdown files. mktg is infrastructure.
 
 | | mktg | Other skill repos |
 |---|---|---|
-| **Install** | `npm i -g mktg && mktg init` | `git clone` + manually copy files |
+| **Install** | `npm i -g marketing-cli && mktg init` | `git clone` + manually copy files |
 | **CLI** | 15 top-level commands, JSON output, exit codes, `--dry-run` | None |
-| **Memory** | 10 brand files that compound across sessions | Stateless — starts from scratch every time |
+| **Memory** | 10 brand files that compound across sessions | Stateless; starts from scratch every time |
 | **Health checks** | `mktg doctor` with pass/warn/fail diagnostics | None |
 | **Skill lifecycle** | Dependency DAG, freshness tracking, versioning | Flat directory of markdown |
 | **Integration checks** | Proactive env var verification before routing | Fails mid-execution |
 | **Schema introspection** | `mktg schema --json` for agent self-discovery | None |
-| **Tests** | Extensive Bun tests (real file I/O, no mocks) | 0 |
+| **Tests** | 2,371 tests (real file I/O, no mocks) | 0 |
 | **Orchestrator** | `/cmo` with routing table, disambiguation, guardrails | Command menus |
 
 ---
 
 ## Why a CLI?
 
-Marketing skills are just markdown files. So why build a real CLI around them?
+Marketing skills are just markdown files. Without infrastructure, an agent can't tell which skills are installed, whether brand files exist, or if API keys are set. It reads a skill, does one thing, and forgets.
 
-**Because skills alone can't answer "what's the state of my marketing?"**
+The CLI gives agents what skills can't:
 
-Without infrastructure, your agent has no way to know which skills are installed, whether brand files exist, if API keys are configured, or what's been done vs. what's missing. It reads a skill, does one thing, and forgets. There's no continuity, no health checks, no lifecycle.
+- **`mktg init`**: One command bootstraps everything. Detects your project, scaffolds `brand/`, prefers `ai-agent-skills` for skill installation when available, installs agents directly, and runs doctor. Works on any machine, every time.
+- **`mktg status --json`**: A structured snapshot of your marketing state. `/cmo` reads this on every activation to know what exists, what's stale, and what to suggest next.
+- **`mktg doctor --json`**: Health checks with pass/warn/fail. Are skills installed? Are brand files populated? Are API keys set? The agent knows before it tries, rather than failing mid-execution.
+- **`mktg update`**: Skill versioning. When skills improve, one command updates them all without touching your brand memory.
+- **`mktg schema --json`**: Self-discovery. The agent can introspect every command, flag, and output shape at runtime.
 
-The CLI gives agents something skills can't:
-
-- **`mktg init`** — One command bootstraps everything. Detects your project, scaffolds `brand/`, installs skills and agents, runs doctor. Works on any machine, every time.
-- **`mktg status --json`** — A structured snapshot of your marketing state. `/cmo` reads this on every activation to know what exists, what's stale, and what to suggest next.
-- **`mktg doctor --json`** — Health checks with pass/warn/fail. Are skills installed? Are brand files populated? Are API keys set? The agent knows before it tries — instead of failing mid-execution.
-- **`mktg update`** — Skill versioning. When skills improve, one command updates them all without touching your brand memory.
-- **`mktg schema --json`** — Self-discovery. The agent can introspect every command, flag, and output shape at runtime.
-
-The pattern: **skills are knowledge, the CLI is infrastructure.** Skills teach your agent *how* to do marketing. The CLI tells it *where things are*, *what's ready*, and *what's broken*. Together they create a feedback loop that gets smarter every session.
+Skills are knowledge; the CLI is infrastructure. Together they create a feedback loop that gets sharper every session.
 
 ---
 
 ## Brand Memory
 
-This is mktg's secret weapon. The `brand/` directory holds ten files that compound across sessions:
+The `brand/` directory holds ten files that compound across sessions:
 
 ```
 brand/
@@ -163,22 +160,22 @@ brand/
 └── learnings.md          # What worked, what didn't (append-only)
 ```
 
-**Session 1:** Research from scratch. **Session 10:** Your agent knows your voice, audience, competitors, keyword gaps, and what's worked before. No other marketing skill system does this.
+**Session 1:** Research from scratch. **Session 10:** Your agent knows your voice, audience, competitors, keyword gaps, and what's worked before.
 
-Foundation research launches 3 agents **in parallel** — brand voice extraction, audience persona building, and competitor teardown — all writing back to `brand/` simultaneously.
+Foundation research launches 3 agents **in parallel**: brand voice extraction, audience persona building, and competitor teardown, all writing back to `brand/` simultaneously.
 
 ---
 
-## Skills (49)
+## Skills (50)
 
-Organized by marketing layer — foundation builds up to distribution.
+Organized by marketing layer; foundation builds up to distribution.
 
 <details>
-<summary><b>Foundation (9 skills)</b> — Brand identity, audience research, competitive intelligence</summary>
+<summary><b>Foundation (9 skills)</b>: Brand identity, audience research, competitive intelligence</summary>
 
 | Skill | What it does |
 |-------|-------------|
-| **cmo** | Orchestrates all 49 skills. Routing table, disambiguation, guardrails. |
+| **cmo** | Orchestrates all 50 skills. Routing table, disambiguation, guardrails. |
 | **brand-voice** | Define or extract brand voice from existing content |
 | **audience-research** | Build buyer personas with parallel web research |
 | **competitive-intel** | Analyze competitors with real-time web intelligence |
@@ -191,7 +188,7 @@ Organized by marketing layer — foundation builds up to distribution.
 </details>
 
 <details>
-<summary><b>Strategy (4 skills)</b> — Keywords, pricing, launch timing, plan strengthening</summary>
+<summary><b>Strategy (4 skills)</b>: Keywords, pricing, launch timing, plan strengthening</summary>
 
 | Skill | What it does |
 |-------|-------------|
@@ -203,7 +200,7 @@ Organized by marketing layer — foundation builds up to distribution.
 </details>
 
 <details>
-<summary><b>Execution (19 skills)</b> — Copy, content, SEO, creative, conversion optimization</summary>
+<summary><b>Execution (19 skills)</b>: Copy, content, SEO, creative, conversion optimization</summary>
 
 | Skill | What it does |
 |-------|-------------|
@@ -230,7 +227,7 @@ Organized by marketing layer — foundation builds up to distribution.
 </details>
 
 <details>
-<summary><b>Distribution (9 skills)</b> — Email, social, newsletters, third-party integrations</summary>
+<summary><b>Distribution (9 skills)</b>: Email, social, newsletters, third-party integrations</summary>
 
 | Skill | What it does |
 |-------|-------------|
@@ -260,7 +257,7 @@ Parallel sub-agents for research and review. Spawned by `/cmo` during foundation
 | **content-reviewer** | Quality review for any marketing output |
 | **seo-analyst** | SEO audit for content and pages |
 
-Foundation research launches all 3 research agents **in parallel** — brand, audience, and competitors simultaneously. Results write back to `brand/` so every future session benefits.
+Foundation research runs all 3 research agents **in parallel**. Results write back to `brand/` so every future session starts ahead.
 
 ---
 
@@ -271,7 +268,7 @@ Foundation research launches all 3 research agents **in parallel** — brand, au
 | `mktg init` | Scaffold `brand/` + install skills + install agents |
 | `mktg status` | Project marketing state snapshot |
 | `mktg doctor` | Health checks: brand files, skills, agents, CLI tools, integrations |
-| `mktg list` | Show all 49 skills with install status and metadata |
+| `mktg list` | Show all 50 skills with install status and metadata |
 | `mktg update` | Re-install skills from latest package version |
 | `mktg schema` | Introspect all commands, flags, and output shapes |
 | `mktg skill` | Inspect, validate, register, analyze, and chain external skills |
@@ -285,13 +282,13 @@ Foundation research launches all 3 research agents **in parallel** — brand, au
 | `mktg dashboard` | Local command center: snapshot, actions, launch |
 | `mktg transcribe` | Audio/video → transcript via whisper.cpp (YouTube, TikTok, podcasts, local files) |
 
-Every command supports `--json` for agent consumption, `--dry-run` for safe previews, and `--fields` for selective output.
+Every command ships `--json`, `--dry-run`, and `--fields`.
 
 ---
 
 ## Integration Checks
 
-Third-party skills (Typefully, Resend) need API keys. mktg checks **proactively** — before routing, not mid-execution:
+Third-party skills (Typefully, Resend) need API keys. mktg checks **proactively**, before routing rather than mid-execution:
 
 ```bash
 $ mktg doctor --json | jq '.checks[] | select(.name | startswith("integration"))'
@@ -303,7 +300,7 @@ $ mktg doctor --json | jq '.checks[] | select(.name | startswith("integration"))
 }
 ```
 
-`/cmo` reads this and guides setup before routing to a skill that needs the key. Missing integrations produce warnings, never blockers — progressive enhancement means every skill works at zero config.
+`/cmo` reads this and guides setup before routing to a skill that needs the key. Missing integrations produce warnings, not errors. Every skill works at zero config.
 
 ---
 
@@ -316,7 +313,7 @@ src/
 ├── commands/           # 15 top-level commands (init, doctor, status, list, update, schema, skill, brand, run, context, plan, publish, compete, dashboard, transcribe)
 └── core/               # Shared modules (output, errors, brand, skills, agents, integrations)
 
-skills/                 # 49 SKILL.md files → installed to ~/.claude/skills/
+skills/                 # 50 SKILL.md files → manifest-backed subset installed via ai-agent-skills or directly
 ├── cmo/                # Orchestrator with rules/, references/
 ├── brand-voice/
 ├── direct-response-copy/
@@ -332,37 +329,36 @@ agents-manifest.json    # Source of truth for agent metadata
 
 ### Design Principles
 
-1. **Progressive Enhancement** — Every skill works at zero context. Brand memory enhances, never gates.
-2. **Agent-Native** — JSON output, structured errors, exit codes 0–6, `--dry-run`, schema introspection.
-3. **Self-Bootstrapping** — `mktg init` installs everything on any machine. No manual setup.
-4. **Drop-In Skills** — Add a skill by dropping `SKILL.md` + updating `skills-manifest.json`.
-5. **Skills Never Call Skills** — Skills read/write files. `/cmo` orchestrates. No implicit chains.
-6. **Parallel by Default** — Foundation building spawns 3 research agents simultaneously.
-7. **Warn, Never Gate** — Missing dependencies produce warnings, not blockers.
+1. **Progressive Enhancement**: Every skill works at zero context. Brand memory enhances, never gates.
+2. **Agent-Native**: JSON output, structured errors, exit codes 0–6, `--dry-run`, schema introspection.
+3. **Self-Bootstrapping**: `mktg init` installs everything on any machine. It prefers `ai-agent-skills` as the installer/catalog layer when available and falls back to direct install when it is not.
+4. **Drop-In Skills**: Add a skill by dropping `SKILL.md` + updating `skills-manifest.json`.
+5. **Skills Never Call Skills**: Skills read/write files. `/cmo` orchestrates. No implicit chains.
+6. **Parallel by Default**: Foundation building spawns 3 research agents simultaneously.
+7. **Warn, Never Gate**: Missing dependencies produce warnings, not blockers.
 
 ---
 
 ## Development
 
 ```bash
-git clone https://github.com/MoizIbnYousaf/mktg.git
-cd mktg
+git clone https://github.com/MoizIbnYousaf/marketing-cli.git
+cd marketing-cli
 
-bun install           # Install dependencies
+bun install
 bun run dev doctor    # Run locally
-bun test              # Extensive Bun test suite, real file I/O, no mocks
+bun test              # 2,371 tests, real file I/O, no mocks
 bun x tsc --noEmit    # Type check
 bun run build         # Build
 ```
 
 ### Project Structure
 
-- `src/` — CLI source (TypeScript, ~8,500 lines)
-- `skills/` — 49 SKILL.md files (~65,000 lines of marketing expertise)
-- `agents/` — 5 agent definitions
-- `tests/` — Bun test suite for CLI and runtime behavior
-- `website/` — Next.js marketing site
-- `docs/` — Reference docs (`EXIT_CODES.md`, `skill-contract.md`)
+- `src/`: CLI source (TypeScript, ~10,700 lines)
+- `skills/`: 50 SKILL.md files (manifest-backed)
+- `agents/`: 5 agent definitions
+- `tests/`: 2,371 tests (real file I/O, no mocks)
+- `docs/`: Reference docs (`EXIT_CODES.md`, `skill-contract.md`)
 
 ---
 
@@ -370,19 +366,19 @@ bun run build         # Build
 
 Contributions welcome. The easiest ways to help:
 
-1. **Add a skill** — Drop a `SKILL.md` in `skills/<name>/` and add an entry to `skills-manifest.json`
-2. **Improve existing skills** — Better prompts, more examples, edge case handling
-3. **Add tests** — Real file I/O in isolated temp dirs, no mocks
-4. **Report issues** — [github.com/MoizIbnYousaf/mktg/issues](https://github.com/MoizIbnYousaf/mktg/issues)
+1. **Add a skill**: Drop a `SKILL.md` in `skills/<name>/` and add an entry to `skills-manifest.json`
+2. **Improve existing skills**: Better prompts, more examples, edge case handling
+3. **Add tests**: Real file I/O in isolated temp dirs, no mocks
+4. **Report issues**: [github.com/MoizIbnYousaf/marketing-cli/issues](https://github.com/MoizIbnYousaf/marketing-cli/issues)
 
 ---
 
 ## License
 
-[MIT](LICENSE) — Use freely. Build on it.
+[MIT](LICENSE). Use freely. Build on it.
 
 ---
 
 ## Acknowledgments
 
-- [Corey Haines' Marketing Skills](https://github.com/coreyhaines31/marketingskills) — the breadth skill collection that inspired many of mktg's 49 skills
+- [Corey Haines' Marketing Skills](https://github.com/coreyhaines31/marketingskills): the breadth skill collection that inspired many of mktg's 50 skills

package/catalogs-manifest.json

@@ -0,0 +1,24 @@
+{
+  "version": 1,
+  "catalogs": {
+    "postiz": {
+      "name": "postiz",
+      "repo_url": "https://github.com/gitroomhq/postiz-app",
+      "docs_url": "https://docs.postiz.com",
+      "license": "AGPL-3.0",
+      "version_pinned": "v2.21.6",
+      "capabilities": {
+        "publish_adapters": ["postiz"]
+      },
+      "transport": "http",
+      "sdk_reference": null,
+      "auth": {
+        "style": "bearer",
+        "base_env": "POSTIZ_API_BASE",
+        "credential_envs": ["POSTIZ_API_KEY"],
+        "header_format": "bare"
+      },
+      "skills": ["postiz"]
+    }
+  }
+}