taketomarket 2.2.0 → 2.3.0

package/workflows/lifecycle/brief.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-brief` is not `true`, print the explainer below verbatim, then mark this skill as seen:
+
+```bash
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run mark ttm-brief
+```
+
+Use this exact check (bash) to decide whether to print: `node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run check ttm-brief --raw` -- the JSON `seen` field is `true` once the explainer has run before.
+
+### Explainer for `/ttm-brief`
+
+`/ttm-brief` is the spec-writing step. You describe the audience, the outcome
+metric, the channel, and the angle; the skill writes a structured BRIEF.md that
+the production wave will load. It also runs a positioning sanity check against
+your `.taketomarket/POSITIONING.md` so the brief can't silently contradict the
+invariant.
+
+Why it matters: a brief is the request payload that fans out to multiple parallel
+producer subagents. Vague briefs produce inconsistent assets that fail review.
+The structured-question format is the equivalent of writing a typed function
+signature before implementing the body.
+
+(Canonical source: `references/inline-education-blurbs.md`. Embedded verbatim because workflows do not @-resolve files at runtime.)
+
+---
+
 <purpose>
 Campaign brief generation workflow with outcome metric enforcement (LIFE-04) and
 positioning check gate (LIFE-05). Collects all mandatory brief fields (D-07),
@@ -16,7 +45,7 @@ content production.
 <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 detect positioning drift:
 - In verify: use the Escalate option to launch /ttm-positioning-shift
@@ -66,27 +95,27 @@ SLUG=$(echo "$ARGUMENTS" | sed 's/--text//g' | xargs)
 ```
 
 Read 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`
 
 Read Tier 2 (full content) for:
-- `.marketing/ICP.md`
-- `.marketing/CHANNELS.md`
-- `.marketing/METRICS.md`
-- `.marketing/CALENDAR.md`
+- `.taketomarket/ICP.md`
+- `.taketomarket/CHANNELS.md`
+- `.taketomarket/METRICS.md`
+- `.taketomarket/CALENDAR.md`
 
-Read full `.marketing/POSITIONING.md` (needed for positioning check gate in Step 6).
+Read full `.taketomarket/POSITIONING.md` (needed for positioning check gate in Step 6).
 
 Read campaign-specific files (always full-load per context-loading.md rule 4):
-- `.marketing/CAMPAIGNS/${SLUG}/STATE.md`
-- `.marketing/CAMPAIGNS/${SLUG}/RESEARCH.md`
+- `.taketomarket/CAMPAIGNS/${SLUG}/STATE.md`
+- `.taketomarket/CAMPAIGNS/${SLUG}/RESEARCH.md`
 
 ---
 
@@ -103,7 +132,7 @@ Read campaign state. Check the `phase` field:
 
 - If phase is `"created"`:
   Warn the user:
-  "Research not yet completed for this campaign. Brief quality will be limited without research data. Run `/ttm-research ${SLUG}` first for better results. Proceed without research?"
+  "Research not yet completed for this campaign. Brief quality will be limited without research data. Run `/ttm-discover ${SLUG}` first for better results. Proceed without research?"
   Wait for user confirmation. If user declines, exit.
 
 - If phase is NOT `"created"` and NOT `"researched"`:
@@ -112,8 +141,8 @@ Read campaign state. Check the `phase` field:
   Wait for user confirmation. If user declines, exit.
 
 Check if RESEARCH.md has actual content (not just template placeholders):
-- Read `.marketing/CAMPAIGNS/${SLUG}/RESEARCH.md`
-- If file contains only `[GENERATED BY /ttm-research]` placeholders: set `RESEARCH_AVAILABLE=false`
+- Read `.taketomarket/CAMPAIGNS/${SLUG}/RESEARCH.md`
+- If file contains only `[GENERATED BY /ttm-discover]` placeholders: set `RESEARCH_AVAILABLE=false`
 - If file has real content beyond placeholders: set `RESEARCH_AVAILABLE=true`
 
 ---
@@ -173,12 +202,12 @@ If the user provides an empty response or declines: set `OUTPUT_METRIC_MISSING=t
 ## Step 4: Collect Remaining Brief Fields (per D-07)
 
 **ICP Segment:**
-Read the primary segment from `.marketing/ICP.md` Tier 1 summary. Present it to the user:
+Read the primary segment from `.taketomarket/ICP.md` Tier 1 summary. Present it to the user:
 "Your primary ICP segment is: [segment from ICP.md]. Is this correct for this campaign, or are you targeting a specific sub-segment?"
 Store the confirmed or adjusted segment as `ICP_SEGMENT`.
 
 **Channel Mix:**
-Read active channels from `.marketing/CHANNELS.md`.
+Read active channels from `.taketomarket/CHANNELS.md`.
 
 Use AskUserQuestion (or text-mode numbered list) with `multiSelect=true`:
 - header: "Channel Selection"
@@ -195,7 +224,7 @@ Ask: "What is the opening angle or attention-capture strategy for this campaign?
 Store as `HOOK`.
 
 **Proof Points:**
-Read proof points from `.marketing/POSITIONING.md` Proof Point Library table.
+Read proof points from `.taketomarket/POSITIONING.md` Proof Point Library table.
 Display the available proof points. Ask:
 "These are your approved proof points. Do you want to add any campaign-specific claims or evidence?"
 Store base proof points plus any additions as `PROOF_POINTS`.
@@ -287,7 +316,7 @@ Apply all 5 checks against `BRIEF_CONTENT`:
 !! POSITIONING DRIFT WARNING !!
 The following items may not align with your positioning:
 - [drift detail from each failing check, using format strings from brief-positioning-check.md]
-Review .marketing/POSITIONING.md and adjust the brief if needed.
+Review .taketomarket/POSITIONING.md and adjust the brief if needed.
 Run /ttm-positioning-check for a full audit.
 -->
 ```
@@ -298,7 +327,7 @@ The brief is written unconditionally. NEVER block brief generation on positionin
 
 ## Step 7: Write BRIEF.md and Update State
 
-Write `BRIEF_CONTENT` to `.marketing/CAMPAIGNS/${SLUG}/BRIEF.md`.
+Write `BRIEF_CONTENT` to `.taketomarket/CAMPAIGNS/${SLUG}/BRIEF.md`.
 
 Update campaign state:
 ```bash
@@ -321,7 +350,7 @@ Replace `[pass|warn]` with the actual gate result from Step 6.
 ```
 takeToMarket > BRIEF COMPLETE
 
-Brief saved to .marketing/CAMPAIGNS/${SLUG}/BRIEF.md
+Brief saved to .taketomarket/CAMPAIGNS/${SLUG}/BRIEF.md
 
 Outcome metric: [OUTCOME_METRIC]
 Positioning check: [pass|warn]
@@ -331,7 +360,7 @@ Assets: [count] planned
 
 [If positioning_check=warn:]
 !! Positioning drift detected -- see warning in BRIEF.md
-Review .marketing/POSITIONING.md and adjust if needed.
+Review .taketomarket/POSITIONING.md and adjust if needed.
 
 Next: Run /ttm-produce ${SLUG}
 ```
@@ -351,5 +380,12 @@ Next: Run /ttm-produce ${SLUG}
 </success_criteria>
 
 <output>
-- `.marketing/CAMPAIGNS/<slug>/BRIEF.md` (populated with all mandatory fields)
+- `.taketomarket/CAMPAIGNS/<slug>/BRIEF.md` (populated with all mandatory fields)
 </output>
+
+## What if this doesn't fit?
+
+Looks like /ttm-brief can't do that yet.
+
+- Want a new skill? /ttm-request-skill
+- Existing skill needs work? /ttm-improve-skill

package/workflows/lifecycle/{research.md → discover.md}

@@ -1,3 +1,38 @@
+## 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-discover` is not `true`, print the explainer below verbatim, then mark this skill as seen:
+
+```bash
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run mark ttm-discover
+```
+
+Use this exact check (bash) to decide whether to print: `node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run check ttm-discover --raw` -- the JSON `seen` field is `true` once the explainer has run before.
+
+### Explainer for `/ttm-discover`
+
+`/ttm-discover` is the research phase. It scans your competitors, your category,
+and your ICP's actual language to surface angles, claims, and proof points
+worth building campaigns around. Output is a structured discovery doc with
+candidate hooks, ranked by confidence, that feed into `/ttm-brief`.
+
+Why it matters: without discovery, briefs come from your own head -- which is
+how positioning drifts and how every campaign starts to sound the same. This
+step is the marketing equivalent of profiling before you optimize: do not skip
+to production until you know what's actually resonating.
+
+(Canonical source: `references/inline-education-blurbs.md`. Embedded verbatim because workflows do not @-resolve files at runtime.)
+
+---
+
+<!--
+  NOTE: This workflow was renamed `research.md` -> `discover.md` in v2.3.0.
+  The artifact filename (`RESEARCH.md`) and state-machine identifier
+  (`phase: researched`) are intentionally preserved for backward compatibility
+  with existing campaigns. Full literal rename is scheduled for v2.4.0.
+-->
+
 <purpose>
 Market and audience research workflow that generates a structured RESEARCH.md for a
 campaign. Detects WebSearch tool availability at runtime and falls back to manual paste
@@ -19,20 +54,20 @@ takeToMarket > LOADING CONTEXT
 ```
 
 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/COMPETITORS.md` (per context-loading.md loading matrix -- research loads Tier 2 COMPETITORS.md)
+- `.taketomarket/COMPETITORS.md` (per context-loading.md loading matrix -- research loads Tier 2 COMPETITORS.md)
 
 ---
 
@@ -47,7 +82,7 @@ If `$SLUG` is empty: ask the user "Which campaign should I research? Provide the
 
 Check the campaign exists:
 ```bash
-ls ".marketing/CAMPAIGNS/${SLUG}/STATE.md" 2>/dev/null && echo "exists" || echo "missing"
+ls ".taketomarket/CAMPAIGNS/${SLUG}/STATE.md" 2>/dev/null && echo "exists" || echo "missing"
 ```
 
 **If "missing":**
@@ -61,7 +96,7 @@ node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" campaign state "${SLUG}" --raw
 ```
 
 Read the full campaign STATE.md (campaign files are always full-loaded per context-loading.md rule 4):
-- `.marketing/CAMPAIGNS/${SLUG}/STATE.md`
+- `.taketomarket/CAMPAIGNS/${SLUG}/STATE.md`
 
 Store the campaign name from the state for use in RESEARCH.md generation.
 
@@ -109,7 +144,7 @@ takeToMarket > RESEARCH MODE: WEB
 - Use WebSearch for SERP queries based on `RESEARCH_TOPIC` and campaign keywords
 - Search for: market trends, competitor content, audience discussions, content gaps
 - Use WebFetch for competitor page content extraction when specific URLs are found
-- Cross-reference findings against `.marketing/COMPETITORS.md` (already loaded in Tier 2)
+- Cross-reference findings against `.taketomarket/COMPETITORS.md` (already loaded in Tier 2)
 - Tag insights with confidence levels:
   - **HIGH**: verified source URL or cited data from web search results
   - **MEDIUM**: indirect evidence or partial match from search results
@@ -209,7 +244,7 @@ opportunity, the key audience insight, and the competitive angle.
 
 Write the completed research to:
 ```
-.marketing/CAMPAIGNS/${SLUG}/RESEARCH.md
+.taketomarket/CAMPAIGNS/${SLUG}/RESEARCH.md
 ```
 
 ---
@@ -233,9 +268,9 @@ Count the total insights generated across all sections.
 
 Display summary:
 ```
-takeToMarket > RESEARCH COMPLETE
+takeToMarket > DISCOVER COMPLETE
 
-Research saved to .marketing/CAMPAIGNS/${SLUG}/RESEARCH.md
+Research saved to .taketomarket/CAMPAIGNS/${SLUG}/RESEARCH.md
 Method: [web-search|manual-paste|hybrid]
 Insights: [count] with confidence breakdown
   HIGH: [count]
@@ -260,5 +295,12 @@ Next: Run /ttm-brief ${SLUG}
 </success_criteria>
 
 <output>
-- `.marketing/CAMPAIGNS/<slug>/RESEARCH.md` (populated with research)
+- `.taketomarket/CAMPAIGNS/<slug>/RESEARCH.md` (populated with research)
 </output>
+
+## What if this doesn't fit?
+
+Looks like /ttm-discover can't do that yet.
+
+- Want a new skill? /ttm-request-skill
+- Existing skill needs work? /ttm-improve-skill

package/workflows/lifecycle/fix.md

@@ -1,3 +1,31 @@
+## 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-fix` is not `true`, print the explainer below verbatim, then mark this skill as seen:
+
+```bash
+node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run mark ttm-fix
+```
+
+Use this exact check (bash) to decide whether to print: `node "${CLAUDE_PLUGIN_ROOT}/bin/ttm-tools.cjs" first-run check ttm-fix --raw` -- the JSON `seen` field is `true` once the explainer has run before.
+
+### Explainer for `/ttm-fix`
+
+`/ttm-fix` reads the verification findings, opens the offending asset, applies
+targeted corrections, and re-runs only the affected gates. It's deliberately
+narrow -- it does not regenerate from scratch, it patches. The fix-verify loop
+continues until either all gates pass or you escalate.
+
+Why it matters: regenerating an asset for a small drift wastes context and
+loses good prose that was almost right. Fix is the surgical tool; produce is
+the hammer. Most assets need one or two fix passes before shipping, and that
+loop is where positioning drift gets caught before it leaves the repo.
+
+(Canonical source: `references/inline-education-blurbs.md`. Embedded verbatim because workflows do not @-resolve files at runtime.)
+
+---
+
 <purpose>
 Fix workflow for /ttm-fix. Performs root cause analysis on assets marked
 "needs-fix" during review, generates targeted fix briefs, re-produces in
@@ -16,7 +44,7 @@ Auto-approves to ship-ready on successful fix (D-14).
 <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 detect positioning drift:
 - In verify: use the Escalate option to launch /ttm-positioning-shift
@@ -66,37 +94,37 @@ SLUG=$(echo "$ARGUMENTS" | sed 's/--text//g' | xargs)
 If SLUG is empty, error: "Usage: /ttm-fix [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 gate evaluation (same as verify per context-loading.md):
-- `.marketing/POSITIONING.md` (needed for GATE-01 Positioning Drift)
-- `.marketing/BRAND.md` (needed for GATE-02 Claim Accuracy, GATE-03 Voice Drift)
-- `.marketing/ICP.md` (needed for GATE-09 ICP Fit)
-- `.marketing/COMPETITORS.md` (needed for GATE-08 Competitor Collision)
-- `.marketing/CHANNELS.md` (needed for GATE-06 UTM Hygiene)
+- `.taketomarket/POSITIONING.md` (needed for GATE-01 Positioning Drift)
+- `.taketomarket/BRAND.md` (needed for GATE-02 Claim Accuracy, GATE-03 Voice Drift)
+- `.taketomarket/ICP.md` (needed for GATE-09 ICP Fit)
+- `.taketomarket/COMPETITORS.md` (needed for GATE-08 Competitor Collision)
+- `.taketomarket/CHANNELS.md` (needed for GATE-06 UTM Hygiene)
 
 **Load 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`
 
 **Load MANIFEST.json:**
-Read `.marketing/CAMPAIGNS/${SLUG}/MANIFEST.json`. If the file does not exist, error:
+Read `.taketomarket/CAMPAIGNS/${SLUG}/MANIFEST.json`. If the file does not exist, error:
 "No production manifest found for campaign '${SLUG}'. Run /ttm-produce first." Exit.
 
 **Load VERIFICATION.md:**
-Read `.marketing/CAMPAIGNS/${SLUG}/VERIFICATION.md`. If the file does not exist, error:
+Read `.taketomarket/CAMPAIGNS/${SLUG}/VERIFICATION.md`. If the file does not exist, error:
 "No verification report found for campaign '${SLUG}'. Run /ttm-verify first." Exit.
 
 **Load LEARNINGS.md Tier 2** (for root-cause taxonomy categories):
-- `.marketing/LEARNINGS.md` (full content -- needed for root-cause category matching)
+- `.taketomarket/LEARNINGS.md` (full content -- needed for root-cause category matching)
 
 ---
 
@@ -136,7 +164,7 @@ Parse MANIFEST.json for assets where `review_status == "needs-fix"`.
 
 Collect from both `hero` and `derivatives` entries. For each matching asset, record:
 - `asset_id`, `name`, `file`, `type`, `channel`, `playbook`
-- Load its review feedback file: `.marketing/CAMPAIGNS/${SLUG}/REVIEW-FEEDBACK-${NAME}.md`
+- Load its review feedback file: `.taketomarket/CAMPAIGNS/${SLUG}/REVIEW-FEEDBACK-${NAME}.md`
   If the feedback file does not exist, log warning and use VERIFICATION.md failures only.
 
 If no assets need fix:
@@ -157,7 +185,7 @@ Assets needing fix: ${COUNT}
 ## Step 4: Initialize Fix Log
 
 Check if FIX-LOG.md exists in campaign directory:
-`.marketing/CAMPAIGNS/${SLUG}/FIX-LOG.md`
+`.taketomarket/CAMPAIGNS/${SLUG}/FIX-LOG.md`
 
 If not, create it from `${CLAUDE_PLUGIN_ROOT}/templates/fix-log.md` template:
 - Replace `[SLUG]` with campaign slug
@@ -209,7 +237,7 @@ Initialize `attempt_count` from prior attempts in FIX-LOG.md (0 if no prior atte
   - `[ATTEMPT_NUMBER]` -> current attempt (1, 2, or 3)
   - `[ROOT_CAUSE_CATEGORY]` -> confirmed root cause category
   - `[ROOT_CAUSE_EXPLANATION]` -> explanation text
-  - `[BRIEF_PATH]` -> `.marketing/CAMPAIGNS/${SLUG}/BRIEF.md`
+  - `[BRIEF_PATH]` -> `.taketomarket/CAMPAIGNS/${SLUG}/BRIEF.md`
   - `[FAILURE_LIST]` -> extract all WARN/FAIL findings for this asset from VERIFICATION.md,
     plus review feedback items from REVIEW-FEEDBACK-${NAME}.md
   - `[PASSING_LIST]` -> extract all PASS findings for this asset from VERIFICATION.md
@@ -217,19 +245,19 @@ Initialize `attempt_count` from prior attempts in FIX-LOG.md (0 if no prior atte
   - `[CORRECTIONS_LIST]` -> derive specific corrections from root cause + review feedback
   - `[ISO_TIMESTAMP]` -> current timestamp
 
-  Write fix brief to: `.marketing/CAMPAIGNS/${SLUG}/FIX-BRIEF-${ASSET_ID}-attempt-${N}.md`
+  Write fix brief to: `.taketomarket/CAMPAIGNS/${SLUG}/FIX-BRIEF-${ASSET_ID}-attempt-${N}.md`
 
   ### 5c. Re-Produce Asset (Task() subagent)
 
   Read agent prompt template from `${CLAUDE_PLUGIN_ROOT}/agents/ttm-producer.md`.
   Fill placeholders -- **CRITICAL: use the FIX BRIEF path as `[BRIEF_PATH]`**, NOT the
   original BRIEF.md:
-  - `[BRIEF_PATH]` -> `.marketing/CAMPAIGNS/${SLUG}/FIX-BRIEF-${ASSET_ID}-attempt-${N}.md`
-  - `[POSITIONING_PATH]` -> `.marketing/POSITIONING.md`
-  - `[BRAND_PATH]` -> `.marketing/BRAND.md`
-  - `[ICP_PATH]` -> `.marketing/ICP.md`
+  - `[BRIEF_PATH]` -> `.taketomarket/CAMPAIGNS/${SLUG}/FIX-BRIEF-${ASSET_ID}-attempt-${N}.md`
+  - `[POSITIONING_PATH]` -> `.taketomarket/POSITIONING.md`
+  - `[BRAND_PATH]` -> `.taketomarket/BRAND.md`
+  - `[ICP_PATH]` -> `.taketomarket/ICP.md`
   - `[PLAYBOOK_PATH]` -> playbook path from MANIFEST.json or `"none"`
-  - `[OUTPUT_PATH]` -> `.marketing/CAMPAIGNS/${SLUG}/${ASSET_FILE}` (overwrite failing version)
+  - `[OUTPUT_PATH]` -> `.taketomarket/CAMPAIGNS/${SLUG}/${ASSET_FILE}` (overwrite failing version)
   - `[ASSET_TYPE]` -> from MANIFEST.json
   - `[CHANNEL]` -> from MANIFEST.json
   - `[HERO_PATH]` -> hero asset path if this is a derivative, else `"none"`
@@ -238,7 +266,7 @@ Initialize `attempt_count` from prior attempts in FIX-LOG.md (0 if no prior atte
 
   Verify the re-produced file exists and has content:
   ```bash
-  test -s ".marketing/CAMPAIGNS/${SLUG}/${ASSET_FILE}"
+  test -s ".taketomarket/CAMPAIGNS/${SLUG}/${ASSET_FILE}"
   ```
   If file missing/empty: log as failed attempt in FIX-LOG.md, continue loop.
 
@@ -306,7 +334,7 @@ Initialize `attempt_count` from prior attempts in FIX-LOG.md (0 if no prior atte
 
   ### 5f. Log Attempt to FIX-LOG.md
 
-  Append to `.marketing/CAMPAIGNS/${SLUG}/FIX-LOG.md`:
+  Append to `.taketomarket/CAMPAIGNS/${SLUG}/FIX-LOG.md`:
   ```markdown
   ## Asset: [ASSET_NAME]
 
@@ -373,7 +401,7 @@ Set asset `review_status` to `"needs-human-fix"` in memory.
 
 ## Step 7: Update MANIFEST.json
 
-Read MANIFEST.json from `.marketing/CAMPAIGNS/${SLUG}/MANIFEST.json`.
+Read MANIFEST.json from `.taketomarket/CAMPAIGNS/${SLUG}/MANIFEST.json`.
 
 Update `review_status` for each processed asset:
 - `"ship-ready"` if fix succeeded or user approved anyway
@@ -457,7 +485,7 @@ Assets processed: ${TOTAL}
   Fixed (ship-ready): ${FIXED_COUNT}
   Needs human fix: ${ESCALATED_COUNT}
 
-Fix log: .marketing/CAMPAIGNS/${SLUG}/FIX-LOG.md
+Fix log: .taketomarket/CAMPAIGNS/${SLUG}/FIX-LOG.md
 ```
 
 **If any ship-ready assets:**
@@ -488,8 +516,15 @@ Edit the flagged files manually, then run /ttm-verify ${SLUG} to re-check
 </success_criteria>
 
 <output>
-- `.marketing/CAMPAIGNS/${SLUG}/FIX-LOG.md` (fix attempt history -- append-only)
-- `.marketing/CAMPAIGNS/${SLUG}/FIX-BRIEF-*-attempt-*.md` (fix briefs per attempt -- persistent)
-- `.marketing/CAMPAIGNS/${SLUG}/MANIFEST.json` (updated with fix results per asset)
-- `.marketing/CAMPAIGNS/${SLUG}/VERIFICATION.md` (updated with latest gate results)
+- `.taketomarket/CAMPAIGNS/${SLUG}/FIX-LOG.md` (fix attempt history -- append-only)
+- `.taketomarket/CAMPAIGNS/${SLUG}/FIX-BRIEF-*-attempt-*.md` (fix briefs per attempt -- persistent)
+- `.taketomarket/CAMPAIGNS/${SLUG}/MANIFEST.json` (updated with fix results per asset)
+- `.taketomarket/CAMPAIGNS/${SLUG}/VERIFICATION.md` (updated with latest gate results)
 </output>
+
+## What if this doesn't fit?
+
+Looks like /ttm-fix can't do that yet.
+
+- Want a new skill? /ttm-request-skill
+- Existing skill needs work? /ttm-improve-skill