marketing-cli 0.1.0 → 0.2.0

package/skills/cmo/rules/progressive-enhancement.md

@@ -0,0 +1,167 @@
+# Progressive Enhancement Ladder
+
+/cmo's capability depends on how populated `brand/` is. Brand memory enhances; it never gates. But be honest about what's possible at each rung — running SEO content at L0 produces generic slop; running it at L4 produces converting, grounded content.
+
+**Always check the ladder first.** Run `mktg status --json --fields brand.populated,brand.missing,brand.stale` to know where you stand. Announce the level to the builder: *"You're at L2 — I can route to X, Y, Z. A and B need another brand file first. Want me to run it now?"*
+
+---
+
+## L0 — Zero context (`mktg init` just ran; all `brand/*.md` templates)
+
+**What's populated:** nothing real. Templates only.
+
+**What /cmo can route to cleanly:**
+
+| Skill | Reason |
+|---|---|
+| `brainstorm` | No brand needed — it's the explorer. |
+| `brand-voice` | Foundation skill. Its job IS to populate voice-profile.md. |
+| `voice-extraction` | Standalone — reverse-engineers voice from external content. |
+| `audience-research` | Foundation. Populates audience.md. |
+| `competitive-intel` | Foundation. Populates competitors.md. |
+| `landscape-scan` | Foundation. Populates landscape.md. |
+| `positioning-angles` | Needs voice + audience; queue it once those land. |
+| `mktg-x` | Utility — reads external X content. |
+| `firecrawl` | Utility — scrapes external content. |
+| `summarize` | Utility — compresses pasted text. |
+| `create-skill` | Meta — adds new skills to the playbook. |
+
+**What /cmo cannot do well:**
+- Write converting copy (no voice, no audience, no positioning).
+- Route to any distribution (no content to distribute).
+- Run any playbook except **Full Product Launch** from scratch.
+
+**Response quality:** *"I can help, but first let me build the foundation. Here's the 4-agent parallel research I'll kick off: brand-voice, audience-research, competitive-intel, landscape-scan. This gives us voice + audience + competitive context + market grounding. It's a 10-minute investment that makes everything else 10× better."*
+
+**Playbooks unlocked:** **Full Product Launch** (starts here by design).
+
+---
+
+## L1 — Voice only (`brand/voice-profile.md` real)
+
+**What's populated:** voice-profile.md with real patterns.
+
+**What /cmo adds from L0:**
+
+| Skill | Reason |
+|---|---|
+| `direct-response-copy` | Can write copy in-voice now. Still generic targeting. |
+| `seo-content` | Same — voiced but audience/keyword-agnostic. |
+| `content-atomizer` | Can rewrite content in-voice across platforms. |
+| `creative` | Can generate copy variants in-voice. |
+| `newsletter` | Can draft in-voice. Topic selection is still guesswork. |
+| `lead-magnet` | Draft only — audience targeting is missing. |
+
+**What's still gated:**
+- `positioning-angles` (needs audience too)
+- `page-cro` / `conversion-flow-cro` (needs positioning for "why us" framing)
+- `launch-strategy` / `startup-launcher` (needs positioning)
+- `competitor-alternatives` (needs competitors.md)
+
+**Response quality:** *"Voice is locked in. Copy will sound like you. But I'm writing blind on who we're talking to — let me run /audience-research (5 min) so the next draft converts."*
+
+**Playbooks unlocked:** partial — Founder Voice Rebrand can finalize step 2; Content Engine can draft if user specifies topic manually.
+
+---
+
+## L2 — Voice + audience (`audience.md` real)
+
+**What /cmo adds:**
+
+| Skill | Reason |
+|---|---|
+| `positioning-angles` | Has both required inputs. Can run. |
+| `pricing-strategy` | Has audience context for willingness-to-pay. |
+| `email-sequences` | Audience-targeted flows now possible. |
+| `lead-magnet` (full) | Targeted resource. |
+| `social-campaign` (without landscape grounding) | Can plan calendar; still no market-claim enforcement. |
+| `keyword-research` | Better with audience context. |
+
+**What's still gated:**
+- Any skill that needs competitive context (`competitor-alternatives`, full `launch-strategy`).
+- Claims-grounded content (no `landscape.md` + Claims Blacklist yet).
+
+**Response quality:** *"Voice + audience are in. I can target now. But I don't know who you're competing against — let me run /competitive-intel (parallel to your next ask, 5 min) so I don't accidentally position us against ourselves."*
+
+**Playbooks unlocked:** Newsletter Launch, Conversion Audit (if the page exists), Visual Identity.
+
+---
+
+## L3 — Voice + audience + competitors + landscape + positioning
+
+**What's populated:** 5 of 10 brand files — the full research foundation.
+
+**What /cmo adds:**
+
+| Skill | Reason |
+|---|---|
+| `launch-strategy` | All required inputs. |
+| `startup-launcher` | Full brief auto-fills from brand/. |
+| `competitor-alternatives` | Has competitors + positioning. |
+| `free-tool-strategy` | Has audience + positioning for distribution plan. |
+| `seo-audit` | Has content context. |
+| `landscape-scan` refresh becomes meaningful | baseline exists to diff against. |
+
+**What's still gated (minor):**
+- Visual skills work but without `creative-kit.md` produce generic styling.
+- `keyword-plan.md` may or may not be run yet — SEO Authority Build needs it.
+
+**Response quality:** *"Foundation is complete. Claims Blacklist is active (from landscape.md) — I'll enforce it on every piece of copy. Ready to run any playbook."*
+
+**Playbooks unlocked:** all except those requiring visual identity (Visual Identity, Video Content) or SEO-specific (SEO Authority Build requires keyword-plan first).
+
+---
+
+## L4 — All 10 brand files current within freshness windows
+
+**What's populated:** `voice-profile.md`, `positioning.md`, `audience.md`, `competitors.md`, `landscape.md`, `keyword-plan.md`, `creative-kit.md`, `stack.md`, `assets.md` (append-only), `learnings.md` (append-only) — all real, none stale.
+
+**What /cmo adds from L3:**
+
+| Skill | Reason |
+|---|---|
+| `image-gen` | Has `creative-kit.md` style anchors. |
+| `visual-style` → `brand-kit-playground` | Full loop. |
+| `paper-marketing` | Has the design system to spawn designer agents. |
+| `slideshow-script` + `video-content` + `tiktok-slideshow` | Full video pipeline. |
+| `ai-seo` | Has keyword-plan + positioning for entity optimization. |
+| `frontend-slides` | Brand-consistent pitch decks. |
+| `app-store-screenshots` | Brand visuals in place. |
+| `email-sequences` with full stack awareness | Knows which ESP (`stack.md`) + audience segments. |
+| `typefully` + `postiz` routing | Full per-platform calibration. |
+| `mktg compete scan` | Landscape baseline to diff competitor changes against. |
+| `mktg plan next` | Has enough state to pick the single highest-priority task. |
+
+**Response quality:** *"You're at L4 — full CMO mode. I'll route with confidence. If it's a named playbook, I'll run it. If it's an ad-hoc ask, I'll pick the 1-2 best skills and execute."*
+
+**Playbooks unlocked:** all 10. Can compound work across multiple playbooks in one session.
+
+---
+
+## Level detection at activation
+
+Run at On Activation (see main SKILL.md):
+
+```bash
+mktg status --json --fields brand.populated,brand.missing,brand.stale
+```
+
+Map the result:
+
+| State | Level |
+|---|---|
+| `brand.populated.length === 0` OR all files are templates | L0 |
+| only `voice-profile.md` real | L1 |
+| `voice-profile.md` + `audience.md` real | L2 |
+| + `competitors.md` + `landscape.md` (fresh ≤ 14 days) + `positioning.md` | L3 |
+| All 10 files populated AND within freshness (30d profiles, 90d config, append-only never stale) | L4 |
+
+**When landscape.md is stale (>14 days):** downgrade to "L3 but not L4 for content routing" — warn the user before running any copy skill.
+
+**When any profile file (voice/positioning/audience/competitors/landscape) is stale (>30 days):** downgrade one level. Offer to refresh before routing.
+
+---
+
+## What "route with confidence" means
+
+At L3/L4, /cmo doesn't ask "what do you want to do" — it suggests. At L0-L2, /cmo explicitly names the missing input before running anything that needs it. The ladder is a contract: the builder knows what they'll get back at each level, and /cmo is honest about the quality ceiling.

package/skills/cmo/rules/quality-gate.md

@@ -33,3 +33,58 @@ Do NOT apply to:
 ## The Rule
 
 **If the output reads like AI wrote it, rewrite it until it doesn't.** The quality gate is not a checklist to pass — it's a standard to meet. Every piece of text that leaves /cmo should sound like a human who happens to be very good at marketing wrote it.
+
+---
+
+## Full Pre-Ship Pipeline
+
+The AI slop audit is one of four gates. Before any content ships (landing page goes live, email sequence triggers, posts schedule, article publishes), run them in this order:
+
+| # | Gate | Purpose | How /cmo invokes | Fail behavior |
+|---|---|---|---|---|
+| 1 | `editorial-first-pass` | Structural check — hook, thesis, promise, stakes. Fastest gate; kills obvious misses early. | `/editorial-first-pass <path>` — returns pass/fail + rework recommendations. | On fail: bounce back to the content skill for a second pass. Don't proceed to gate 2. |
+| 2 | `ai-check` + this AI slop audit | Line-by-line pattern detection against the full reference at `references/ai-slop-patterns.md`. | Invoked automatically by content skills in their own post-production; /cmo runs it on batches (e.g., atomizer output). | On fail: rewrite the flagged lines in place. Don't pass slop to a reviewer. |
+| 3 | `mktg-content-reviewer` agent | Voice-profile consistency — does this sound like the brand documented in `brand/voice-profile.md`? | Spawn via Agent tool — see `rules/sub-agents.md` for the pattern. Returns structured score + drift report. | On fail: loop back to the content skill with the specific rewrite recommendations. |
+| 4 | `mktg-seo-analyst` agent (SEO assets only) | Keyword-plan adherence — primary/secondary keywords, search intent match, on-page basics, AI search readiness. | Spawn via Agent tool. Reads `brand/keyword-plan.md` + `brand/audience.md` + `brand/competitors.md`. | On fail: loop back with keyword-gap recommendations. |
+
+**Which gates apply to which outputs:**
+
+| Output | Gate 1 | Gate 2 | Gate 3 | Gate 4 |
+|---|---|---|---|---|
+| Landing page (`direct-response-copy`) | ✓ | ✓ | ✓ | ✓ if SEO is a goal |
+| Sales copy, cold email | ✓ | ✓ | ✓ | — |
+| SEO article (`seo-content`) | ✓ | ✓ | ✓ | ✓ |
+| Email sequence (`email-sequences`) | ✓ (per email) | ✓ | ✓ (batch) | — |
+| Newsletter issue (`newsletter`) | ✓ | ✓ | ✓ | — |
+| Lead magnet (`lead-magnet`) | ✓ | ✓ | ✓ | — |
+| Atomized social posts (`content-atomizer`) | — (platform-native check instead) | ✓ (batch-level) | ✓ (batch) | — |
+| Comparison page (`competitor-alternatives`) | ✓ | ✓ | ✓ | ✓ |
+| AI-search asset (`ai-seo`) | ✓ | ✓ | ✓ | ✓ |
+| Research / strategy output | — | — | — | — (no gates on research) |
+| Visual assets | — (visual review happens in `visual-style` → `brand-kit-playground`) | — | — | — |
+
+**Skipping gates is an anti-pattern.** /cmo doesn't skip gates to save time. If the user demands a skip, surface the risk first:
+
+> *"You want to ship the landing page without the content-reviewer gate. That risks voice drift — my last review on similar content flagged 3 tone issues. OK with you?"*
+
+The user can override. /cmo never silently bypasses.
+
+---
+
+## Named pipeline: `pre-ship-gates`
+
+When /cmo needs to run the full gate chain on one asset:
+
+```
+PIPELINE: pre-ship-gates
+INPUT:    <file path>
+STEPS:
+  1. /editorial-first-pass <path>   → PASS required
+  2. AI slop audit (this file)      → rewrite in place
+  3. Agent: mktg-content-reviewer   → score ≥ threshold required
+  4. Agent: mktg-seo-analyst        → score ≥ threshold required (SEO assets only)
+OUTPUT:   ready-to-ship flag + final asset path
+FAIL:     return to the content skill with aggregated recommendations
+```
+
+Announce the pipeline to the user before running — they see the investment up front, approve once, and let it compound.

package/skills/cmo/rules/sub-agents.md

@@ -0,0 +1,135 @@
+# Sub-Agent Orchestration
+
+/cmo spawns specialized sub-agents for parallel research and post-production review. Agents never call agents — /cmo is the only orchestrator. This file documents when and how to invoke each of the 5 agents in `agents-manifest.json`.
+
+**Canonical rule:** research agents spawn on first-run foundation building (3 in parallel). Review agents spawn on-demand after content lands.
+
+---
+
+## The 5 Agents
+
+### Research agents (parallel, spawned on FIRST RUN)
+
+| Agent | Writes | Reads | Skill methodology it follows |
+|---|---|---|---|
+| `mktg-brand-researcher` | `brand/voice-profile.md` | project README, website, existing content | `brand-voice` SKILL.md |
+| `mktg-audience-researcher` | `brand/audience.md` | project context, market space | `audience-research` SKILL.md |
+| `mktg-competitive-scanner` | `brand/competitors.md` | project context, known competitors | `competitive-intel` SKILL.md |
+
+### Review agents (on-demand, post-content)
+
+| Agent | Purpose | Invoke after | Scores (doesn't write) |
+|---|---|---|---|
+| `mktg-content-reviewer` | Voice-profile consistency gate | any content draft (DRC, SEO, email, social, newsletter, lead-magnet) | Reads `brand/voice-profile.md` |
+| `mktg-seo-analyst` | Keyword-plan adherence gate | any SEO asset (seo-content, landing page, competitor-alternatives, ai-seo output) | Reads `brand/keyword-plan.md` |
+
+---
+
+## First-Run Spawn Protocol (the 3 research agents in parallel)
+
+On `/cmo` FIRST RUN — brand files are templates, no real data — spawn **all three research agents in a single message** (one message with 3 Agent tool calls) for maximum parallelism. Foundation research is the biggest time sink; parallelizing saves 10+ minutes.
+
+**Message pattern:**
+
+```
+<Agent tool call 1>
+  subagent_type: mktg-brand-researcher
+  description: Extract brand voice
+  prompt: [project name] + [URL if provided] + [what the project does]
+         + "Write brand/voice-profile.md. Follow the brand-voice SKILL
+            methodology. Do not ask questions — research, analyze, write."
+
+<Agent tool call 2>
+  subagent_type: mktg-audience-researcher
+  description: Build audience profile
+  prompt: [project name] + [market space] + [problem it solves]
+         + "Write brand/audience.md. Follow the audience-research SKILL
+            methodology. Spawn sub-searches via Exa as needed."
+
+<Agent tool call 3>
+  subagent_type: mktg-competitive-scanner
+  description: Scan competitors
+  prompt: [project name] + [market space] + [known competitors if any]
+         + "Write brand/competitors.md. Follow the competitive-intel SKILL
+            methodology. Use Exa for live market research."
+```
+
+**Critical**: send all 3 tool calls in ONE message. Sequential spawns waste 2-3× the wall-clock time.
+
+**What /cmo does while they run:**
+- Tell the user: *"Three research agents are running in parallel — brand-voice, audience, competitors. ETA 5-10 minutes. I'll stitch the outputs when they land."*
+- Don't start other skills. Wait for all 3.
+- When they all return, read the 3 brand files, share what you learned, route to `positioning-angles` (which needs all 3 inputs).
+
+**Fallback (no agents installed):** if `mktg doctor` shows agents missing, load the 3 foundation skills sequentially instead — `brand-voice`, then `audience-research`, then `competitive-intel`. Slower but identical artifact shape.
+
+---
+
+## On-Demand Review Invocation
+
+### `mktg-content-reviewer` — voice consistency gate
+
+**When /cmo invokes it:**
+- After `direct-response-copy` produces landing page, sales copy, cold email.
+- After `seo-content` produces an article.
+- After `email-sequences` drafts a sequence (review the full flow together).
+- After `content-atomizer` produces multi-platform posts (one review pass over the batch).
+- After `newsletter` drafts an issue.
+- After `social-campaign` Phase 3 (this agent IS the voice gate of that phase).
+
+**Spawn pattern:**
+
+```
+<Agent tool call>
+  subagent_type: mktg-content-reviewer
+  description: Voice consistency review
+  prompt: [file paths to review] + "Read brand/voice-profile.md. Score this
+         content against the voice profile. Return structured feedback —
+         what matches the voice, what drifts, specific rewrite recommendations.
+         Do not rewrite; report only."
+```
+
+**What /cmo does with the result:**
+- If score ≥ threshold (PASS) → present to user for approval, move on.
+- If score < threshold (FAIL) → go back to the content skill with the specific rewrite recommendations. Don't ship drifted content.
+
+### `mktg-seo-analyst` — keyword adherence gate
+
+**When /cmo invokes it:**
+- After `seo-content` produces an article.
+- After `competitor-alternatives` produces a comparison page.
+- After `ai-seo` produces an AI-search-optimized asset.
+- After `direct-response-copy` produces a landing page (if SEO is a goal).
+
+**Spawn pattern:**
+
+```
+<Agent tool call>
+  subagent_type: mktg-seo-analyst
+  description: Keyword adherence audit
+  prompt: [file path] + "Read brand/keyword-plan.md + brand/audience.md +
+         brand/competitors.md. Audit this asset for: primary keyword density,
+         secondary keyword coverage, search intent match, on-page SEO basics
+         (title, meta, heading hierarchy), AI search readiness. Return
+         structured scores and specific recommendations."
+```
+
+**What /cmo does with the result:**
+- Surface the score to the user.
+- If specific improvements are worth making → loop back to the content skill with the recommendations.
+
+---
+
+## Never-Call-Other-Agents Invariant
+
+Each of the 5 agents is **isolated** — they never spawn other agents. If a research agent needs content-reviewer's output, that's a signal the workflow is wrong. CMO is the coordinator; the agents are specialists.
+
+**Anti-pattern to watch:** agents trying to chain work. If `mktg-brand-researcher` asks for audience data mid-run, reject — audience research is a separate agent, run in parallel, merged by CMO afterwards.
+
+---
+
+## Reference
+
+- `AGENTS.md` at repo root — the drop-in agent contract.
+- `agents-manifest.json` — agent registry with `category`, `file`, `reads`, `writes`, `references_skill`, `tier`.
+- Each agent's `.md` file under `agents/research/` or `agents/review/` in the mktg repo; installed to `~/.claude/agents/` by `mktg init`.

package/skills/deepen-plan/SKILL.md

@@ -184,4 +184,4 @@ After all research agents complete, merge findings into the plan. Follow these r
 - **launch-strategy**: When the plan to deepen is a launch plan, or when no plan exists
 - **keyword-research**: For filling keyword/search strategy gaps identified in gap analysis
 - **audience-research**: For deep-dive audience work beyond what the researcher agent provides
-- **competitive-intel**: For comprehensive competitive analysis beyond the scanner agent
+- **competitive-intel**: For deep competitive analysis beyond the scanner agent

package/skills/direct-response-copy/SKILL.md

@@ -277,7 +277,7 @@ After each sweep, loop back to check previous sweeps aren't compromised.
 **Cut**: very, really, extremely, just, actually, basically, in order to
 **Replace**: utilize→use, implement→set up, leverage→use, facilitate→help, robust→strong, seamless→smooth, cutting-edge→new
 
-See [references/plain-english-alternatives.md](references/plain-english-alternatives.md) for comprehensive list.
+See [references/plain-english-alternatives.md](references/plain-english-alternatives.md) for the full list.
 
 ---
 

package/skills/email-sequences/SKILL.md

@@ -239,7 +239,7 @@ Email 4 (Day 9): MYTH-BUST
 
 Email 5 (Day 12): DEEP DIVE
 - Subject: "Everything I know about [narrow topic]"
-- Body: Your best content on a topic they care about. Comprehensive but scannable.
+- Body: Your best content on a topic they care about. Thorough but scannable.
 - CTA: Bookmark this / share with a colleague
 
 Email 6+ (Every 3 days): ROTATE

package/skills/firecrawl/.skill-meta.json

@@ -1,8 +1,8 @@
 {
   "sourceType": "github",
   "source": "github",
-  "url": "https://github.com/MoizIbnYousaf/mktg",
-  "repo": "MoizIbnYousaf/mktg",
+  "url": "https://github.com/MoizIbnYousaf/marketing-cli",
+  "repo": "MoizIbnYousaf/marketing-cli",
   "ref": null,
   "subpath": "firecrawl",
   "installSource": "mktg/skills/firecrawl",

package/skills/keyword-research/SKILL.md

@@ -132,7 +132,7 @@ SEED --> EXPAND --> SEARCH --> CLUSTER --> VALIDATE --> PRIORITIZE --> MAP --> B
 ```
 
 1. **Seed** -- Generate initial keywords from business context and brand memory
-2. **Expand** -- Use the 6 Circles Method to build comprehensive list
+2. **Expand** -- Use the 6 Circles Method to build the full list
 3. **Search** -- Pull live SERP data: autocomplete, People Also Ask, competitor rankings
 4. **Cluster** -- Group related keywords into content pillars
 5. **Validate** -- Run 4-check pillar validation with live competitive data

package/skills/launch-strategy/SKILL.md

@@ -70,7 +70,7 @@ Based on context, classify:
 
 Using the ORB Framework, Five-Phase Approach, and reference files, produce a plan tailored to the classification. Reference:
 - [references/launch-timeline.md](references/launch-timeline.md) for week-by-week timeline
-- [references/launch-checklist.md](references/launch-checklist.md) for comprehensive pre-flight checklist
+- [references/launch-checklist.md](references/launch-checklist.md) for the full pre-flight checklist
 
 ### Phase 4: Write Deliverables
 
@@ -212,7 +212,7 @@ Borrowed channels give instant credibility, but only work if you convert borrowe
 |---|---|---|
 | < 1,000 | Owned channels only (blog, email list) | Build foundation before spending on reach |
 | 1K - 10K | Owned + Rented (social, SEO, ads) | Enough audience to test paid channels |
-| 10K+ | All three: Owned + Rented + Borrowed (partnerships, press) | Leverage existing reach for maximum amplification |
+| 10K+ | All three: Owned + Rented + Borrowed (partnerships, press) | Use existing reach for maximum amplification |
 
 ---
 

package/skills/marketing-psychology/SKILL.md

@@ -10,7 +10,7 @@ description: |
 
 This is a KNOWLEDGE skill. It does not produce standalone deliverables. Instead, it enhances any marketing asset — landing pages, emails, ads, CTAs, pricing pages, onboarding flows — by applying behavioral psychology principles that increase persuasion and conversion.
 
-When another skill produces copy or UX, this skill provides the psychological layer: why certain framings work, which biases to leverage, and specific before/after rewrites grounded in research.
+When another skill produces copy or UX, this skill provides the psychological layer: why certain framings work, which biases to apply, and specific before/after rewrites grounded in research.
 
 ## No Reads/Writes
 

package/skills/mktg-x/.skill-meta.json

@@ -1,8 +1,8 @@
 {
   "sourceType": "first-party",
   "source": "first-party",
-  "url": "https://github.com/MoizIbnYousaf/mktg",
-  "repo": "MoizIbnYousaf/mktg",
+  "url": "https://github.com/MoizIbnYousaf/marketing-cli",
+  "repo": "MoizIbnYousaf/marketing-cli",
   "ref": null,
   "subpath": "skills/mktg-x",
   "installSource": "mktg/skills/mktg-x",

package/skills/positioning-angles/SKILL.md

@@ -56,7 +56,7 @@ On invocation, check for `./brand/` and load available context:
 
 5. **If `./brand/` does not exist:**
    - Skip brand loading entirely. Do not error.
-   - Note in opening message: "No brand profile found — this skill works standalone. I'll ask what I need. You can run /start-here or /brand-voice later to unlock personalization."
+   - Note in opening message: "No brand profile found — this skill works standalone. I'll ask what I need. You can run /cmo or /brand-voice later to unlock personalization."
 
 ---