taketomarket 2.2.0 → 2.3.1

package/workflows/lifecycle/humanize.md

@@ -0,0 +1,280 @@
+## Step 0: First-run inline education
+
+Read `.taketomarket/CONFIG.md`. Parse `first_run_seen` (object) and `inline_education` (boolean, default true).
+
+If `inline_education` is false: skip this step. Else if `first_run_seen.ttm-humanize` is not `true`, print the explainer below verbatim, then mark this skill as seen:
+
+```bash
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run mark ttm-humanize
+```
+
+Use this exact check (bash) to decide whether to print: `node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run check ttm-humanize --raw` -- the JSON `seen` field is `true` once the explainer has run before.
+
+### Explainer for `/ttm-humanize`
+
+`/ttm-humanize` rewrites AI-flavored prose into something that sounds like a
+person wrote it: varied sentence rhythm, fewer hedges, specific verbs, no
+"furthermore" or "in today's fast-paced." It runs after verify, before review,
+and only on assets flagged for tone tuning.
+
+Why it matters: detection models and human readers both pattern-match on the
+same tells, and AI-fingerprinted copy converts worse and damages trust. Think
+of humanize as a code formatter that targets the LLM-prose anti-patterns the
+way Prettier targets whitespace.
+
+(Canonical source: `references/inline-education-blurbs.md`. Embedded verbatim because workflows do not @-resolve files at runtime.)
+
+---
+
+<purpose>
+Humanization workflow for /ttm-humanize. Detects and rewrites the AI-writing patterns
+cataloged in references/humanizer-patterns.md against an audience-facing asset, calibrated
+to the brand voice declared in .taketomarket/BRAND.md and constrained by the positioning
+invariant in .taketomarket/POSITIONING.md. Every audience-facing asset in takeToMarket
+passes through this workflow before write -- no asset ships with the AI fingerprint intact.
+</purpose>
+
+<required_reading>
+@${CLAUDE_PLUGIN_ROOT}/references/humanizer-patterns.md
+@${CLAUDE_PLUGIN_ROOT}/references/context-loading.md
+</required_reading>
+
+<constraints>
+## POSITIONING.md is READ-ONLY
+
+**Do NOT modify `.taketomarket/POSITIONING.md` during this workflow.**
+
+Humanization rewrites style and rhythm. It must not change positioning anchors, proof
+points, ICP framing, or any must-not-say term enforcement. If a humanization rewrite would
+contradict POSITIONING.md, abort the rewrite for that span and flag it instead.
+
+## BRAND.md voice is authoritative
+
+The asset's voice MUST match `.taketomarket/BRAND.md`. If the source asset already deviates
+from BRAND.md, humanization is not the place to fix it -- flag the deviation and recommend
+`/ttm-positioning-check` or a manual brand review.
+
+## Meaning is preserved
+
+Humanization rewrites the surface. Claims, numbers, proper nouns, citations, and CTAs are
+preserved verbatim unless they are themselves AI-pattern instances (vague attribution,
+knowledge-cutoff disclaimer, sycophantic opener).
+</constraints>
+
+<process>
+
+## Text-Mode Detection
+
+**Text mode (`--text` flag):** Set `TEXT_MODE=true` if `--text` is present in `$ARGUMENTS`
+or if the runtime is not Claude Code. When TEXT_MODE is active, replace every
+`AskUserQuestion` call with a plain-text numbered list.
+
+```bash
+if echo "$ARGUMENTS" | grep -q -- '--text'; then TEXT_MODE=true; fi
+```
+
+If `AskUserQuestion` tool is not available in the current runtime, set `TEXT_MODE=true`.
+
+---
+
+## Step 1: Resolve Target Asset
+
+```
+takeToMarket > LOADING ASSET
+```
+
+Parse `$ARGUMENTS`. Strip the `--text` flag if present. The remaining token is the target:
+
+- A file path (absolute or repo-relative ending in `.md`): treat as `TARGET_PATH`. Read it.
+- A campaign slug followed by an asset id (e.g., `pricing-q2 02`): resolve to
+  `.taketomarket/CAMPAIGNS/${SLUG}/ASSETS/${NN}-*.md`.
+- A bare campaign slug: read `.taketomarket/CAMPAIGNS/${SLUG}/MANIFEST.json` and humanize
+  every asset listed. Process the hero first, then derivatives.
+- No argument and stdin/clipboard text present: treat as inline mode -- humanize the pasted
+  text and print the result; do not write to disk.
+
+Store the source text as `DRAFT`. Store the resolution mode as `MODE` (`file` | `campaign` |
+`inline`).
+
+---
+
+## Step 2: Load Voice Context
+
+```
+takeToMarket > CALIBRATING VOICE
+```
+
+Read full content (Tier 2 per context-loading.md):
+
+- `.taketomarket/BRAND.md` -- voice, tone, vocabulary, must-not-say terms
+- `.taketomarket/POSITIONING.md` -- anchors, proof points, must-not-say terms (positioning)
+
+If the asset belongs to a campaign (MODE is `file` under `CAMPAIGNS/${SLUG}/ASSETS/` or
+MODE is `campaign`), also read:
+
+- `.taketomarket/CAMPAIGNS/${SLUG}/BRIEF.md` -- campaign-specific hook, proof points,
+  channel constraints
+
+From BRAND.md, extract a **voice profile**:
+
+- Sentence length pattern (short/punchy, long/flowing, mixed)
+- Word-choice register (casual, technical, formal, mixed)
+- Paragraph openers (jump straight in vs. set context first)
+- Punctuation habits (dashes, parentheticals, semicolons, fragments)
+- Recurring phrases or verbal tics declared in BRAND.md
+- Transition style (explicit connectors vs. abrupt cuts)
+- First-person stance (uses "I"/"we" vs. third-person only)
+
+If BRAND.md does not declare these explicitly, infer them from any sample passages it
+contains. If no samples exist, set `VOICE_PROFILE=default` (varied rhythm, opinionated,
+first-person allowed, no AI tells -- see "Signs of soulless writing" in
+`references/humanizer-patterns.md`).
+
+---
+
+## Step 3: Scan for AI Patterns
+
+```
+takeToMarket > SCANNING FOR AI PATTERNS
+```
+
+Walk `DRAFT` against every section in `${CLAUDE_PLUGIN_ROOT}/references/humanizer-patterns.md`:
+
+1. CONTENT PATTERNS (sections 1-6) -- significance inflation, notability puffery,
+   superficial -ing analyses, promotional language, vague attributions, formulaic
+   challenges sections.
+2. LANGUAGE AND GRAMMAR PATTERNS (sections 7-13) -- AI vocabulary, copula avoidance,
+   negative parallelism, rule of three, elegant variation, false ranges, passive voice.
+3. STYLE PATTERNS (sections 14-19) -- em-dash overuse, boldface overuse, inline-header
+   lists, title-case headings, emojis, curly quotes.
+4. COMMUNICATION PATTERNS (sections 20-22) -- chatbot artifacts, knowledge-cutoff
+   disclaimers, sycophantic tone.
+5. FILLER AND HEDGING (sections 23-29) -- filler phrases, excessive hedging, generic
+   positive conclusions, hyphenated word-pair overuse, persuasive authority tropes,
+   signposting, fragmented headers.
+
+For each hit, record:
+
+- Section number from the reference (e.g., `7`, `14`)
+- The offending span (a short quote)
+- The rewrite shape suggested by the section's Before/After pair
+
+Store the list as `HITS`. If `HITS` is empty AND the draft does not fail the "soulless
+writing" check from the reference, skip to Step 6 -- the asset is already clean.
+
+---
+
+## Step 4: Rewrite
+
+```
+takeToMarket > REWRITING (${N} pattern hits)
+```
+
+For each hit in `HITS`, rewrite the offending span using:
+
+- The Before/After template from the matching section of `humanizer-patterns.md`
+- The voice profile from Step 2 -- match the asset's brand cadence, not a generic
+  "natural" tone
+
+Rules:
+
+- Preserve claims, numbers, proper nouns, citations, and CTAs verbatim.
+- Do NOT introduce new claims or facts. If a vague attribution cannot be replaced with
+  a real source from POSITIONING.md proof points or the campaign brief, delete the
+  attribution rather than inventing one.
+- Do NOT remove a span that is load-bearing for positioning (anchor phrase, proof point,
+  differentiator) even if it pattern-matches. Flag it and leave it.
+- If the brand voice is itself terse and bullet-heavy, don't rewrite inline-header lists
+  into prose paragraphs -- match the brand.
+- Soulless output is a failure mode. After mechanical fixes, do one personality pass
+  using the "How to add voice" guidance in the reference: vary rhythm, allow opinion,
+  let some mess in, be specific.
+
+Store the rewritten text as `DRAFT_V2`.
+
+---
+
+## Step 5: Final Anti-AI Audit
+
+```
+takeToMarket > FINAL AUDIT
+```
+
+Run one more pass against `DRAFT_V2`:
+
+1. Re-scan against `humanizer-patterns.md`. Record any remaining tells as a short bulleted
+   list `REMAINING_TELLS` (cap at 5 items -- the goal is signal, not exhaustiveness).
+2. Apply one more revision targeting `REMAINING_TELLS` specifically. Most often this means
+   tightening rhythm, breaking up tidy parallel structure, or replacing a remaining
+   abstract noun with a concrete one.
+
+Store the result as `DRAFT_FINAL`.
+
+---
+
+## Step 6: Output
+
+Behavior depends on `MODE`:
+
+### MODE = `file` or `campaign` (write back)
+
+Write `DRAFT_FINAL` to the original asset path. Overwrite without prompting -- the previous
+draft is recoverable via git.
+
+For campaign mode, after writing the asset, append a line to
+`.taketomarket/CAMPAIGNS/${SLUG}/MANIFEST.json` under the asset's entry:
+`"humanized_at": "${ISO_TIMESTAMP}"` (use `node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs"
+timestamp --raw`).
+
+### MODE = `inline` (print only)
+
+Print `DRAFT_FINAL` to the conversation. Do not write to disk.
+
+---
+
+## Step 7: Display Summary
+
+```
+takeToMarket > HUMANIZATION COMPLETE
+
+Asset: ${TARGET_PATH or "inline"}
+Pattern hits found: ${HITS.length}
+Top patterns rewritten: ${top 3 section numbers from HITS}
+Remaining tells after audit: ${REMAINING_TELLS.length}
+
+[If MODE = file or campaign:]
+Asset rewritten in place. Diff is visible via `git diff`.
+
+[If MODE = campaign:]
+Manifest annotated with humanized_at timestamp.
+
+[If any positioning-load-bearing spans were flagged-but-not-rewritten:]
+WARNING: ${N} span(s) pattern-matched but were preserved because they carry positioning
+or proof-point load. Review manually if voice still feels off.
+```
+
+</process>
+
+<success_criteria>
+- [ ] Source asset resolved (file, campaign asset, or inline text)
+- [ ] BRAND.md voice profile loaded and applied to rewrites
+- [ ] POSITIONING.md anchors and proof points preserved verbatim
+- [ ] Every hit from the pattern scan addressed -- rewritten or flagged with reason
+- [ ] Final anti-AI audit completed with remaining tells listed (or empty)
+- [ ] Soulless-writing check passed (rhythm varied, voice present, not just clean)
+- [ ] Output written to disk (file/campaign mode) or printed (inline mode)
+- [ ] Manifest updated with humanized_at when in campaign mode
+</success_criteria>
+
+<output>
+- File/campaign mode: rewritten asset at the original path
+- Campaign mode: `humanized_at` timestamp added to MANIFEST.json asset entry
+- Inline mode: rewritten text printed to the conversation
+</output>
+
+## What if this doesn't fit?
+
+Looks like /ttm-humanize can't do that yet.
+
+- Want a new skill? /ttm-request-skill
+- Existing skill needs work? /ttm-improve-skill

package/workflows/lifecycle/learn.md

@@ -1,3 +1,33 @@
+## Step 0: First-run inline education
+
+Read `.taketomarket/CONFIG.md`. Parse `first_run_seen` (object) and `inline_education` (boolean, default true).
+
+If `inline_education` is false: skip this step. Else if `first_run_seen.ttm-learn` is not `true`, print the explainer below verbatim, then mark this skill as seen:
+
+```bash
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run mark ttm-learn
+```
+
+Use this exact check (bash) to decide whether to print: `node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run check ttm-learn --raw` -- the JSON `seen` field is `true` once the explainer has run before.
+
+### Explainer for `/ttm-learn`
+
+`/ttm-learn` reads finished campaigns -- briefs, gate results, ship records,
+measurement output -- and extracts compound learnings into
+`.taketomarket/LEARNINGS.md`: what positioning angles converted, which
+channels under- or over-delivered, which playbook variants worked. Future
+briefs auto-load this file.
+
+Why it matters: marketing learnings without a structured store dissolve into
+folklore inside three months. Learn turns each campaign's data into a
+versioned doc that biases the next brief toward what actually worked --
+the marketing equivalent of a postmortem doc plus a regression suite of
+tactics.
+
+(Canonical source: `references/inline-education-blurbs.md`. Embedded verbatim because workflows do not @-resolve files at runtime.)
+
+---
+
 <purpose>
 Learn workflow for /ttm-learn. Extracts lessons from campaign measurement data
 and campaign history. Proposes reference file edits as narratives with per-edit
@@ -19,7 +49,7 @@ better. LEARNINGS.md is already loaded as Tier 1 context in the brief workflow
 <constraints>
 ## POSITIONING.md is READ-ONLY
 
-**Do NOT modify `.marketing/POSITIONING.md` during this workflow.**
+**Do NOT modify `.taketomarket/POSITIONING.md` during this workflow.**
 
 POSITIONING.md is an architectural invariant. If you identify a lesson that implies
 a POSITIONING.md edit:
@@ -34,12 +64,12 @@ POSITIONING.md edits directly even if the user approves. Instead, display:
 ## Reference File Edit Targets
 
 Only the following files may be edited via this workflow (per D-09):
-- `.marketing/BRAND.md`
-- `.marketing/ICP.md`
-- `.marketing/CHANNELS.md`
-- `.marketing/POSITIONING.md` (via /ttm-positioning-shift only -- never directly)
-- `.marketing/METRICS.md`
-- `.marketing/COMPETITORS.md`
+- `.taketomarket/BRAND.md`
+- `.taketomarket/ICP.md`
+- `.taketomarket/CHANNELS.md`
+- `.taketomarket/POSITIONING.md` (via /ttm-positioning-shift only -- never directly)
+- `.taketomarket/METRICS.md`
+- `.taketomarket/COMPETITORS.md`
 
 ## Append-Only LEARNINGS.md
 
@@ -89,36 +119,36 @@ SLUG=$(echo "$ARGUMENTS" | sed 's/--text//g' | xargs)
 If SLUG is empty, error: "Usage: /ttm-learn [campaign-slug]. Provide a campaign slug." Exit.
 
 **Load Tier 1 summaries** from all 9 reference files (lines 1 to `<!-- END_SUMMARY -->`):
-- `.marketing/POSITIONING.md`
-- `.marketing/BRAND.md`
-- `.marketing/ICP.md`
-- `.marketing/CHANNELS.md`
-- `.marketing/STATE.md` (frontmatter only)
-- `.marketing/CALENDAR.md`
-- `.marketing/COMPETITORS.md`
-- `.marketing/METRICS.md`
-- `.marketing/LEARNINGS.md`
+- `.taketomarket/POSITIONING.md`
+- `.taketomarket/BRAND.md`
+- `.taketomarket/ICP.md`
+- `.taketomarket/CHANNELS.md`
+- `.taketomarket/STATE.md` (frontmatter only)
+- `.taketomarket/CALENDAR.md`
+- `.taketomarket/COMPETITORS.md`
+- `.taketomarket/METRICS.md`
+- `.taketomarket/LEARNINGS.md`
 
 **Load Tier 2 (full content)** for learning analysis:
-- `.marketing/LEARNINGS.md` (existing lessons and patterns)
-- `.marketing/METRICS.md` (metric definitions for delta interpretation)
-- `.marketing/BRAND.md` (brand guidelines for edit proposals)
-- `.marketing/ICP.md` (ICP data for edit proposals)
-- `.marketing/CHANNELS.md` (channel data for edit proposals)
-- `.marketing/COMPETITORS.md` (competitor data for edit proposals)
-- `.marketing/POSITIONING.md` (read-only -- for positioning drift detection)
+- `.taketomarket/LEARNINGS.md` (existing lessons and patterns)
+- `.taketomarket/METRICS.md` (metric definitions for delta interpretation)
+- `.taketomarket/BRAND.md` (brand guidelines for edit proposals)
+- `.taketomarket/ICP.md` (ICP data for edit proposals)
+- `.taketomarket/CHANNELS.md` (channel data for edit proposals)
+- `.taketomarket/COMPETITORS.md` (competitor data for edit proposals)
+- `.taketomarket/POSITIONING.md` (read-only -- for positioning drift detection)
 
 **Load campaign artifacts** per the scan order from learnings-extraction.md:
-- `.marketing/CAMPAIGNS/${SLUG}/STATE.md` (frontmatter for gate results, run counts)
-- `.marketing/CAMPAIGNS/${SLUG}/MEASUREMENT.md` (measurement report with outcome data)
-- `.marketing/CAMPAIGNS/${SLUG}/BRIEF.md` (original strategy and targets)
-- `.marketing/CAMPAIGNS/${SLUG}/VERIFICATION.md` (gate details if it exists)
-- `.marketing/CAMPAIGNS/${SLUG}/FIX-BRIEF-*.md` (fix details if they exist)
-- `.marketing/CAMPAIGNS/${SLUG}/REVIEW-FEEDBACK-*.md` (reviewer comments if they exist)
+- `.taketomarket/CAMPAIGNS/${SLUG}/STATE.md` (frontmatter for gate results, run counts)
+- `.taketomarket/CAMPAIGNS/${SLUG}/MEASUREMENT.md` (measurement report with outcome data)
+- `.taketomarket/CAMPAIGNS/${SLUG}/BRIEF.md` (original strategy and targets)
+- `.taketomarket/CAMPAIGNS/${SLUG}/VERIFICATION.md` (gate details if it exists)
+- `.taketomarket/CAMPAIGNS/${SLUG}/FIX-BRIEF-*.md` (fix details if they exist)
+- `.taketomarket/CAMPAIGNS/${SLUG}/REVIEW-FEEDBACK-*.md` (reviewer comments if they exist)
 
-If `.marketing/CAMPAIGNS/${SLUG}/` does not exist, error: "Campaign '${SLUG}' not found. Check the slug and try again." Exit.
+If `.taketomarket/CAMPAIGNS/${SLUG}/` does not exist, error: "Campaign '${SLUG}' not found. Check the slug and try again." Exit.
 
-If `.marketing/CAMPAIGNS/${SLUG}/MEASUREMENT.md` does not exist, error: "No measurement data found for '${SLUG}'. Run /ttm-measure first." Exit.
+If `.taketomarket/CAMPAIGNS/${SLUG}/MEASUREMENT.md` does not exist, error: "No measurement data found for '${SLUG}'. Run /ttm-measure first." Exit.
 
 ---
 
@@ -226,7 +256,7 @@ Based on campaign "${SLUG}" results, [specific observation from measurement data
 [Reasoning derived from the data and campaign artifacts].
 Therefore, [specific edit proposal describing the change].
 
-File: .marketing/${TARGET_FILE}.md
+File: .taketomarket/${TARGET_FILE}.md
 Section: [section name where the edit applies]
 Change: [specific addition, modification, or removal]
 ```
@@ -243,7 +273,7 @@ Use AskUserQuestion with options:
 
 **If TEXT_MODE=true:**
 ```
-Apply this edit to .marketing/${TARGET_FILE}.md?
+Apply this edit to .taketomarket/${TARGET_FILE}.md?
   1. Apply -- Update ${TARGET_FILE}.md with this change
   2. Skip -- Keep ${TARGET_FILE}.md unchanged, log lesson only
   3. Modify -- Edit the proposed change before applying
@@ -284,7 +314,7 @@ Track counts: `edits_proposed` (total proposed), `edits_applied` (Apply + Modify
 
 ## Step 6: Append Lessons to LEARNINGS.md (per LRNG-01, LIFE-17)
 
-1. Read `.marketing/LEARNINGS.md`
+1. Read `.taketomarket/LEARNINGS.md`
 2. Find the marker line: `<!-- LESSONS BELOW THIS LINE -->`
 3. Insert new lesson rows immediately after the marker, one row per lesson from Step 4:
    ```
@@ -379,7 +409,7 @@ Reference edits proposed: ${PROPOSED_COUNT}
 Reference edits applied: ${APPLIED_COUNT}
 Pattern extraction: ${PATTERN_STATUS}
 
-Lessons appended to: .marketing/LEARNINGS.md
+Lessons appended to: .taketomarket/LEARNINGS.md
 
 Next: Run /ttm-archive ${SLUG} to finalize the campaign, or start a new campaign.
 Future campaigns will load these lessons via /ttm-brief to prevent repeating mistakes.
@@ -403,3 +433,10 @@ Where `${PATTERN_STATUS}` is one of:
 - [ ] Pattern extraction runs only if 3+ campaign slugs in lessons log
 - [ ] Campaign state updated with learn.* fields
 </checklist>
+
+## What if this doesn't fit?
+
+Looks like /ttm-learn can't do that yet.
+
+- Want a new skill? /ttm-request-skill
+- Existing skill needs work? /ttm-improve-skill

package/workflows/lifecycle/measure.md

@@ -1,3 +1,32 @@
+## Step 0: First-run inline education
+
+Read `.taketomarket/CONFIG.md`. Parse `first_run_seen` (object) and `inline_education` (boolean, default true).
+
+If `inline_education` is false: skip this step. Else if `first_run_seen.ttm-measure` is not `true`, print the explainer below verbatim, then mark this skill as seen:
+
+```bash
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run mark ttm-measure
+```
+
+Use this exact check (bash) to decide whether to print: `node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run check ttm-measure --raw` -- the JSON `seen` field is `true` once the explainer has run before.
+
+### Explainer for `/ttm-measure`
+
+`/ttm-measure` ingests analytics data (pasted in manually for the MVP) and
+matches it against the outcome metric declared in the brief. Output is a
+pass/fail per campaign plus a per-asset performance summary written to
+MEASURE.md.
+
+Why it matters: every brief committed to an outcome metric, and measure is
+where that commitment gets checked. Skipping measure means you never learn
+which positioning angles, channels, or hooks actually moved the number --
+the production loop becomes vibes-driven. This is the closing parenthesis on
+the spec-driven cycle.
+
+(Canonical source: `references/inline-education-blurbs.md`. Embedded verbatim because workflows do not @-resolve files at runtime.)
+
+---
+
 <purpose>
 Measurement workflow for /ttm-measure. Accepts analytics data via 3 pathways
 (MCP tools, CSV/Markdown paste, structured batch questions). Applies 3 attribution
@@ -16,7 +45,7 @@ data is available for the measurement window.
 
 ## Positioning Constraint (Read-Only)
 
-`.marketing/POSITIONING.md` is loaded for context only. This workflow MUST NOT modify
+`.taketomarket/POSITIONING.md` is loaded for context only. This workflow MUST NOT modify
 POSITIONING.md. Positioning changes require `/ttm-positioning` -- never alter positioning
 as a side effect of measurement.
 
@@ -61,25 +90,25 @@ SLUG=$(echo "$ARGUMENTS" | sed 's/--text//g' | xargs)
 If SLUG is empty, error: "Usage: /ttm-measure [campaign-slug]. Provide a campaign slug." Exit.
 
 Read Tier 1 summary blocks (content between `<!-- _SUMMARY -->` and `<!-- END_SUMMARY -->`)
-from all 9 `.marketing/` reference files:
-
-- `.marketing/POSITIONING.md` (lines 1 to `<!-- END_SUMMARY -->`)
-- `.marketing/BRAND.md` (lines 1 to `<!-- END_SUMMARY -->`)
-- `.marketing/ICP.md` (lines 1 to `<!-- END_SUMMARY -->`)
-- `.marketing/CHANNELS.md` (lines 1 to `<!-- END_SUMMARY -->`)
-- `.marketing/STATE.md` (frontmatter only)
-- `.marketing/CALENDAR.md` (lines 1 to `<!-- END_SUMMARY -->`)
-- `.marketing/COMPETITORS.md` (lines 1 to `<!-- END_SUMMARY -->`)
-- `.marketing/METRICS.md` (lines 1 to `<!-- END_SUMMARY -->`)
-- `.marketing/LEARNINGS.md` (lines 1 to `<!-- END_SUMMARY -->`)
+from all 9 `.taketomarket/` reference files:
+
+- `.taketomarket/POSITIONING.md` (lines 1 to `<!-- END_SUMMARY -->`)
+- `.taketomarket/BRAND.md` (lines 1 to `<!-- END_SUMMARY -->`)
+- `.taketomarket/ICP.md` (lines 1 to `<!-- END_SUMMARY -->`)
+- `.taketomarket/CHANNELS.md` (lines 1 to `<!-- END_SUMMARY -->`)
+- `.taketomarket/STATE.md` (frontmatter only)
+- `.taketomarket/CALENDAR.md` (lines 1 to `<!-- END_SUMMARY -->`)
+- `.taketomarket/COMPETITORS.md` (lines 1 to `<!-- END_SUMMARY -->`)
+- `.taketomarket/METRICS.md` (lines 1 to `<!-- END_SUMMARY -->`)
+- `.taketomarket/LEARNINGS.md` (lines 1 to `<!-- END_SUMMARY -->`)
 
 Read Tier 2 (full content) for:
-- `.marketing/METRICS.md` (needed for metric definitions and outcome/output classification)
-- `.marketing/CHANNELS.md` (needed for channel attribution mapping)
+- `.taketomarket/METRICS.md` (needed for metric definitions and outcome/output classification)
+- `.taketomarket/CHANNELS.md` (needed for channel attribution mapping)
 
 Read campaign-specific files (always full-load per context-loading.md rule 4):
-- `.marketing/CAMPAIGNS/${SLUG}/STATE.md`
-- `.marketing/CAMPAIGNS/${SLUG}/BRIEF.md`
+- `.taketomarket/CAMPAIGNS/${SLUG}/STATE.md`
+- `.taketomarket/CAMPAIGNS/${SLUG}/BRIEF.md`
 
 Extract from brief:
 - **Outcome metric:** name, target value, measurement window, data source
@@ -322,7 +351,7 @@ Preserve the original pasted/collected data for audit trail.
 
 Write completed report to:
 ```
-.marketing/CAMPAIGNS/${SLUG}/MEASUREMENT.md
+.taketomarket/CAMPAIGNS/${SLUG}/MEASUREMENT.md
 ```
 
 ---
@@ -359,7 +388,7 @@ Display the Outcome Assessment section inline (the metrics table from Step 6).
 ```
 takeToMarket > MEASUREMENT COMPLETE
 
-Report written to: .marketing/CAMPAIGNS/${SLUG}/MEASUREMENT.md
+Report written to: .taketomarket/CAMPAIGNS/${SLUG}/MEASUREMENT.md
 Analytics source: ${ANALYTICS_MODE}
 Outcome metric: ${OUTCOME_METRIC_NAME}
 Result: ${OUTCOME_MET} (${OUTCOME_DELTA} from target)
@@ -377,3 +406,10 @@ Next: Run /ttm-learn ${SLUG} to extract lessons and improve future campaigns.
 - [ ] MEASUREMENT.md written with outcome-first ordering
 - [ ] Campaign state updated with measure.* fields
 </checklist>
+
+## What if this doesn't fit?
+
+Looks like /ttm-measure can't do that yet.
+
+- Want a new skill? /ttm-request-skill
+- Existing skill needs work? /ttm-improve-skill