@growthub/cli 0.14.5 → 0.14.8

package/assets/worker-kits/creative-strategist-v1/brands/solawave/brand-kit.md

@@ -1,139 +0,0 @@
-# Brand Kit — Solawave
-> Source of truth for all Solawave ad deliverables.
-
----
-
-## IDENTITY
-
-```yaml
-client_name:       "Solawave"
-slug:              "solawave"
-industry:          "Beauty / Skincare Technology / At-Home Wellness Devices"
-primary_service:   "Red light therapy skincare wand for wrinkle reduction"
-campaign_name:     "Korean Skincare Truth — BOGO Campaign"
-date_onboarded:    "2026-04-09"
-account_owner:     "Antonio"
-```
-
----
-
-## AUDIENCE
-
-```yaml
-target_age_range:      "25–45"
-target_gender:         "Female-skewing"
-target_pain_point:     "Fine lines, wrinkles, dark circles, dull skin — wants clinical-level results at home"
-target_intent:         "Actively looking for non-invasive, tech-backed skincare alternatives to serums/creams"
-geographic_target:     "United States — national"
-do_not_attract:        "Users seeking prescription skincare, dermatology procedures, or medical-grade interventions.
-                         Not for 55+ medical skincare seekers — brand is aspirational / beauty-tech, not clinical."
-```
-
----
-
-## MESSAGING
-
-```yaml
-core_message:          "Solawave uses clinically-backed red light therapy + microcurrent to reduce wrinkles at home — no injections, no downtime."
-emotional_arc:         "Skepticism → Discovery → Proof → Action"
-tone:                  ["confident", "relatable", "science-meets-beauty", "aspirational", "no-BS"]
-approved_phrases:
-  - "red light therapy"
-  - "4-in-1 skincare wand"
-  - "microcurrent technology"
-  - "at-home anti-aging"
-  - "clinically-backed"
-  - "used by dermatologists"
-  - "fine lines and wrinkles"
-  - "glowing skin"
-  - "real results"
-  - "this is the real deal"
-messaging_guardrails:
-  - "Do NOT claim FDA-cleared or FDA-approved unless confirmed — use 'clinically-backed' instead"
-  - "No before/after photos with specific % improvement claims without clinical citations"
-  - "No 'eliminates' or 'erases' wrinkles — use 'reduces,' 'visibly reduces,' 'smooths'"
-  - "No injection or Botox comparisons that could be read as medical claims"
-  - "Do NOT say 'cures' any skin condition"
-  - "Results may vary — include if making specific outcome claims"
-cta_text:              "Shop Now — Buy 1 Get 1 FREE"
-cta_offer:             "Buy 1 Get 1 FREE"
-```
-
----
-
-## BRAND DESIGN
-
-```yaml
-colors:
-  primary:       "7C1C2F"      # Deep wine / burgundy (from website)
-  secondary:     "B5435A"      # Rose pink
-  light_accent:  "F5E6E8"      # Blush / soft rose
-  dark:          "1B1B1B"
-  white:         "FFFFFF"
-  mid_gray:      "6B7280"
-
-fonts:
-  primary:       "Arial"
-  heading_size:  56
-  body_size:     20
-
-logo_file:       "assets/logo.png"
-logo_on_dark:    "assets/logo-white.png"
-```
-
----
-
-## TALENT & PRODUCTION
-
-```yaml
-doctor_or_founder_name:  "N/A"
-founder_on_camera:       "No"
-ai_avatar_type:          "UGC Talking Head — Photoreal"
-ai_actor_age_range:      "22–32"
-ai_actor_notes:          "Female-presenting, natural/approachable look, warm skin tone — matches Korean beauty influencer energy.
-                           Bedroom or cozy desk setting. Casual outfit (oversized hoodie or neutral top).
-                           Holding mini microphone prop (silver condenser mic type) — core format signal.
-                           Must look like a real TikTok/Instagram creator, not a polished model."
-ugc_inspiration:         "@frankyshaw on Instagram/TikTok — see muse: instagram.com/reels/DU1lWOeDsdg/"
-vo_style:                "AI actor speaks on-camera — natural, direct, like texting your friend a tip. No announcer voice."
-broll_cadence:           "Cut every 2–3 seconds. Never >3s of talking head without a visual break."
-```
-
----
-
-## ASSET LINKS
-
-```yaml
-brand_assets_air:    "TBD"
-broll_library:       "TBD"
-ugc_inspiration:     "https://www.instagram.com/reels/DU1lWOeDsdg/"
-google_drive:        "TBD"
-instagram:           "https://www.instagram.com/solawave/"
-tiktok:              "https://www.tiktok.com/@solawave"
-website:             "https://www.solawave.co/"
-landing_page:        "https://www.solawave.co/"
-phone_number:        "N/A — direct to website"
-previous_ads:        []
-```
-
----
-
-## PLATFORM & FORMAT
-
-```yaml
-primary_platforms:   ["Instagram Reels", "TikTok", "Meta Feed"]
-aspect_ratios:       ["9:16", "1:1"]
-caption_default:     "ON"
-compliance_notes:    "Do not claim FDA-cleared without verification. 'Results may vary' required if making specific
-                       outcome claims. No clinical/medical treatment language. Product is a consumer beauty device."
-```
-
----
-
-## DELIVERABLES LOG
-
-> Append a new line each time a deliverable is completed.
-
-```
-- 2026-04-09 | Video Creative Brief v1 — Korean Skincare Truth BOGO | ~/Downloads/Solawave_VideoBrief_KoreanSkincaretruth_v1_20260409.docx
-```

package/assets/worker-kits/creative-strategist-v1/bundles/creative-strategist-v1.json

@@ -1,57 +0,0 @@
-{
-  "schemaVersion": 2,
-  "bundle": {
-    "id": "creative-strategist-v1",
-    "version": "1.0.0",
-    "kitId": "creative-strategist-v1",
-    "workerId": "creative-strategist"
-  },
-  "briefType": "video-creative-brief",
-  "publicExampleBrandPaths": [
-    "brands/solawave/brand-kit.md"
-  ],
-  "requiredFrozenAssets": [
-    "skills.md",
-    "workers/creative-strategist/CLAUDE.md",
-    "brands/_template/brand-kit.md",
-    "brands/solawave/brand-kit.md",
-    "templates/brief-template.js",
-    "templates/hooks-library/500-winning-hooks.csv",
-    "templates/ad-formats/INDEX.md",
-    "templates/ad-formats/bedroom-minimic-talk.md",
-    "templates/ad-formats/frame-analysis.md",
-    "templates/ad-formats/process-specialist-medical.md",
-    "templates/ad-formats/villain-animation.md",
-    "templates/scene-modules/INDEX.md",
-    "templates/scene-modules/body/before-after-flatlay.md",
-    "templates/scene-modules/body/minimic-problem.md",
-    "templates/scene-modules/body/product-demo-glow.md",
-    "templates/scene-modules/body/tiktok-skeptic-pivot.md",
-    "templates/scene-modules/body/villain-agitation.md",
-    "templates/scene-modules/cta/bogo-meme-bookend.md",
-    "templates/scene-modules/cta/guarantee-close.md",
-    "templates/scene-modules/hooks/dollar-amount.md",
-    "templates/scene-modules/hooks/meme-overlay.md",
-    "templates/scene-modules/hooks/pov-confession.md",
-    "templates/scene-modules/hooks/tiktok-comment.md",
-    "templates/scene-modules/hooks/villain-hook.md",
-    "growthub-meta/README.md",
-    "growthub-meta/kit-standard.md",
-    "SKILL.md",
-    "templates/project.md",
-    "templates/self-eval.md",
-    "helpers/README.md",
-    "skills/README.md",
-    "helpers/grep-hooks.sh",
-    "helpers/extract-muse-frames.sh",
-    "skills/frame-analysis/SKILL.md"
-  ],
-  "optionalPresets": [],
-  "export": {
-    "folderName": "growthub-agent-worker-kit-creative-strategist-v1",
-    "zipFileName": "growthub-agent-worker-kit-creative-strategist-v1.zip"
-  },
-  "activationModes": [
-    "export"
-  ]
-}

package/assets/worker-kits/creative-strategist-v1/growthub-meta/README.md

@@ -1,18 +0,0 @@
-# Growthub Agent Worker Kit Metadata
-
-This folder defines the reusable metadata contract for exporting this worker kit through the Growthub CLI.
-
-The source materials in `claude-workers` stay intact. Growthub reads the frozen machine-readable files added alongside them, then exports only the approved public kit payload declared by `kit.json` and `bundles/creative-strategist-v1.json`.
-
-For V1:
-
-- the only kit is `creative-strategist-v1`
-- the only public example brand is `solawave`
-- confidential brand kits are intentionally excluded from the frozen public payload
-- the exported artifact is a local working-directory-ready bundle, not a server install
-
-Operationally, this means local adapters use the exported kit by setting the agent `Working directory`
-to the expanded folder on disk. The kit acts as a specialized local execution environment that the
-agent can run inside directly.
-
-See `kit-standard.md` for the locked contract.

package/assets/worker-kits/creative-strategist-v1/growthub-meta/kit-standard.md

@@ -1,47 +0,0 @@
-# Growthub Agent Worker Kit Standard
-
-## Purpose
-
-Growthub Agent Worker Kits are frozen, machine-readable exports of a worker directory that can be materialized locally by the Growthub CLI.
-
-## Required Files
-
-Every kit must provide:
-
-- `kit.json` as the canonical manifest
-- `bundles/<bundle-id>.json` for each frozen downloadable bundle
-- a worker entrypoint path
-- an agent contract path
-- a brand template path
-- a declared list of frozen asset paths
-- an output standard that defines the required exported paths
-
-## `kit.json` Contract
-
-`kit.json` locks:
-
-- kit identity and version
-- entrypoint and worker ids
-- agent contract path
-- brand template path
-- frozen asset paths
-- output standard
-- bundle list
-
-## Bundle Contract
-
-Each bundle manifest locks:
-
-- bundle identity and version
-- worker identity
-- brief type
-- required frozen assets
-- optional presets array, even when empty
-- export folder and zip naming
-
-## Export Boundary
-
-- exported zips and expanded folders are generated locally at runtime
-- generated artifacts are not committed to the repo
-- kits are exported for existing Working Directory path support
-- bundle manifests must exclude confidential assets from the public payload

package/assets/worker-kits/creative-strategist-v1/helpers/README.md

@@ -1,29 +0,0 @@
-# `helpers/` — safe shell tool layer (primitive #6)
-
-A **helper** is a small, deterministic script an agent invokes via one shell call instead of reconstructing a raw pipeline inline. Helpers are reviewable, deterministic, and safer than raw commands.
-
-## Convention
-
-```
-helpers/
-├── README.md                 # this file
-├── <verb>.sh                 # single-purpose shell scripts
-├── <verb>.mjs                # optional: Node-based helper
-└── <verb>.py                 # optional: Python-based helper
-```
-
-Every helper:
-
-1. Carries a one-line header comment: what it does + how to invoke it.
-2. Uses `set -euo pipefail` (or equivalent) — no silent failures.
-3. Has a matching row in the parent `SKILL.md`'s `helpers[]` frontmatter.
-4. Is referenced from `skills.md` at the step the agent should invoke it (no duplicated shell bodies).
-
-## When to promote an inline snippet
-
-- Appears more than once in `skills.md`.
-- Has fragile quoting or path interpolation.
-- Calls a side-effecting binary (ffmpeg, git, gh, npm install).
-- Multiple sub-skills invoke it.
-
-See the parent `SKILL.md` `helpers[]` array for the current roster.

package/assets/worker-kits/creative-strategist-v1/helpers/extract-muse-frames.sh

@@ -1,81 +0,0 @@
-#!/usr/bin/env bash
-# extract-muse-frames.sh — deterministic muse-video frame extraction.
-#
-# Use: bash helpers/extract-muse-frames.sh <path-to-video.mp4> [--interval <seconds>]
-#
-# Replaces the inline ffprobe+ffmpeg block in skills.md Step 2b. Writes
-# /tmp/muse_frames/frame_%ds.jpg and prints the first 3 frame paths so an
-# agent can immediately read them via its file-read tool.
-#
-# Interval defaults to 3s for videos >=30s, 2s for videos <30s (matches the
-# runbook guidance for TikTok-format short muses).
-
-set -euo pipefail
-
-if [[ $# -lt 1 ]]; then
-  echo "usage: bash helpers/extract-muse-frames.sh <path-to-video> [--interval N]" >&2
-  exit 2
-fi
-
-VIDEO="$1"
-shift
-
-if [[ ! -f "${VIDEO}" ]]; then
-  echo "Video not found: ${VIDEO}" >&2
-  exit 1
-fi
-
-INTERVAL=""
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --interval)
-      INTERVAL="$2"
-      shift 2
-      ;;
-    *)
-      echo "unknown arg: $1" >&2
-      exit 2
-      ;;
-  esac
-done
-
-for bin in ffprobe ffmpeg python3; do
-  if ! command -v "$bin" >/dev/null 2>&1; then
-    echo "Missing required binary on PATH: $bin" >&2
-    exit 1
-  fi
-done
-
-DURATION="$(ffprobe -v quiet -print_format json -show_format -show_streams "${VIDEO}" \
-  | python3 -c 'import sys, json
-d = json.load(sys.stdin)
-for s in d.get("streams", []):
-    if s.get("codec_type") == "video":
-        print(s.get("duration", 0))
-        break
-')"
-DURATION_INT="$(python3 -c "print(int(float('${DURATION:-0}')))")"
-
-if [[ -z "${INTERVAL}" ]]; then
-  if [[ "${DURATION_INT}" -lt 30 ]]; then
-    INTERVAL=2
-  else
-    INTERVAL=3
-  fi
-fi
-
-OUT_DIR="/tmp/muse_frames"
-mkdir -p "${OUT_DIR}"
-# Clear prior run so downstream `ls` stays deterministic.
-rm -f "${OUT_DIR}"/frame_*.jpg
-
-echo "video:    ${VIDEO}"
-echo "duration: ${DURATION_INT}s"
-echo "interval: ${INTERVAL}s"
-echo "out:      ${OUT_DIR}"
-
-ffmpeg -loglevel error -y -i "${VIDEO}" -vf "fps=1/${INTERVAL}" "${OUT_DIR}/frame_%ds.jpg"
-
-echo ""
-echo "First frames (read these with your file-read tool):"
-ls "${OUT_DIR}"/frame_*.jpg | sort | head -3

package/assets/worker-kits/creative-strategist-v1/helpers/grep-hooks.sh

@@ -1,62 +0,0 @@
-#!/usr/bin/env bash
-# grep-hooks.sh — 3-pass search over the frozen 500-hook CSV.
-#
-# Use: bash helpers/grep-hooks.sh "<keyword>" [--limit <n>]
-#
-# Runs the same 3-pass method documented in skills.md Step 2d against
-# ${CREATIVE_STRATEGIST_HOME:-$HOME/creative-strategist}/templates/hooks-library/500-winning-hooks.csv.
-# Prints an Example / Structure pair for each match. Deterministic; no network.
-
-set -euo pipefail
-
-if [[ $# -lt 1 ]]; then
-  echo "usage: bash helpers/grep-hooks.sh <keyword> [--limit N]" >&2
-  exit 2
-fi
-
-KEYWORD="$1"
-shift
-
-LIMIT=20
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --limit)
-      LIMIT="$2"
-      shift 2
-      ;;
-    *)
-      echo "unknown arg: $1" >&2
-      exit 2
-      ;;
-  esac
-done
-
-KIT_HOME="${CREATIVE_STRATEGIST_HOME:-$HOME/creative-strategist}"
-CSV="${KIT_HOME}/templates/hooks-library/500-winning-hooks.csv"
-
-if [[ ! -f "${CSV}" ]]; then
-  echo "Hooks CSV not found at: ${CSV}" >&2
-  echo "Set CREATIVE_STRATEGIST_HOME to the kit root, or download the kit to \$HOME/creative-strategist." >&2
-  exit 1
-fi
-
-python3 - "${CSV}" "${KEYWORD}" "${LIMIT}" <<'PY'
-import csv, sys
-
-path, kw, limit = sys.argv[1], sys.argv[2].lower(), int(sys.argv[3])
-printed = 0
-with open(path, newline="", encoding="utf-8") as f:
-    for idx, row in enumerate(csv.reader(f)):
-        if len(row) < 2:
-            continue
-        example, structure = row[0], row[1]
-        if kw in example.lower() or kw in structure.lower():
-            print(f"[{idx}] EXAMPLE:   {example[:90]}")
-            print(f"    STRUCTURE: {structure[:100]}\n")
-            printed += 1
-            if printed >= limit:
-                break
-if printed == 0:
-    print(f"No matches for '{kw}' in {path}", file=sys.stderr)
-    sys.exit(3)
-PY

package/assets/worker-kits/creative-strategist-v1/kit.json

@@ -1,106 +0,0 @@
-{
-  "schemaVersion": 2,
-  "kit": {
-    "id": "creative-strategist-v1",
-    "version": "1.0.0",
-    "name": "Growthub Agent Worker Kit \u2014 Creative Strategist",
-    "description": "Frozen Creative Strategist worker kit for exporting a working-directory-ready video creative brief worker.",
-    "type": "worker",
-    "visibility": "public-open-source",
-    "sourceRepo": "claude-workers",
-    "family": "workflow"
-  },
-  "entrypoint": {
-    "workerId": "creative-strategist",
-    "path": "workers/creative-strategist/CLAUDE.md"
-  },
-  "workerIds": [
-    "creative-strategist"
-  ],
-  "agentContractPath": "workers/creative-strategist/CLAUDE.md",
-  "brandTemplatePath": "brands/_template/brand-kit.md",
-  "publicExampleBrandPaths": [
-    "brands/solawave/brand-kit.md"
-  ],
-  "frozenAssetPaths": [
-    "skills.md",
-    "workers/creative-strategist/CLAUDE.md",
-    "brands/_template/brand-kit.md",
-    "brands/solawave/brand-kit.md",
-    "templates/brief-template.js",
-    "templates/hooks-library/500-winning-hooks.csv",
-    "templates/ad-formats/INDEX.md",
-    "templates/ad-formats/bedroom-minimic-talk.md",
-    "templates/ad-formats/frame-analysis.md",
-    "templates/ad-formats/process-specialist-medical.md",
-    "templates/ad-formats/villain-animation.md",
-    "templates/scene-modules/INDEX.md",
-    "templates/scene-modules/body/before-after-flatlay.md",
-    "templates/scene-modules/body/minimic-problem.md",
-    "templates/scene-modules/body/product-demo-glow.md",
-    "templates/scene-modules/body/tiktok-skeptic-pivot.md",
-    "templates/scene-modules/body/villain-agitation.md",
-    "templates/scene-modules/cta/bogo-meme-bookend.md",
-    "templates/scene-modules/cta/guarantee-close.md",
-    "templates/scene-modules/hooks/dollar-amount.md",
-    "templates/scene-modules/hooks/meme-overlay.md",
-    "templates/scene-modules/hooks/pov-confession.md",
-    "templates/scene-modules/hooks/tiktok-comment.md",
-    "templates/scene-modules/hooks/villain-hook.md",
-    "growthub-meta/README.md",
-    "growthub-meta/kit-standard.md",
-    "SKILL.md",
-    "templates/project.md",
-    "templates/self-eval.md",
-    "helpers/README.md",
-    "skills/README.md",
-    "helpers/grep-hooks.sh",
-    "helpers/extract-muse-frames.sh",
-    "skills/frame-analysis/SKILL.md"
-  ],
-  "outputStandard": {
-    "type": "working-directory",
-    "description": "Exported folder is intended to be pointed at directly by existing Working Directory path support.",
-    "requiredPaths": [
-      "kit.json",
-      "bundles/creative-strategist-v1.json",
-      "skills.md",
-      "workers/creative-strategist/CLAUDE.md",
-      "brands/_template/brand-kit.md",
-      "brands/solawave/brand-kit.md",
-      "templates",
-      "growthub-meta",
-      "SKILL.md",
-      "templates/project.md",
-      "templates/self-eval.md",
-      "helpers",
-      "helpers/README.md",
-      "skills",
-      "skills/README.md",
-      "helpers/grep-hooks.sh",
-      "helpers/extract-muse-frames.sh",
-      "skills/frame-analysis/SKILL.md"
-    ]
-  },
-  "bundles": [
-    {
-      "id": "creative-strategist-v1",
-      "version": "1.0.0",
-      "path": "bundles/creative-strategist-v1.json"
-    }
-  ],
-  "executionMode": "export",
-  "activationModes": [
-    "export"
-  ],
-  "compatibility": {
-    "cliMinVersion": "0.3.35"
-  },
-  "provenance": {
-    "sourceRepo": "claude-workers",
-    "frozenAt": "2026-04-09T00:00:00.000Z"
-  },
-  "workspaceVisibility": "addon",
-  "workspaceCompatible": true,
-  "workspaceCategory": "creative-strategy"
-}

package/assets/worker-kits/creative-strategist-v1/skills/README.md

@@ -1,23 +0,0 @@
-# `skills/` — nested sub-skill convention (primitive #5)
-
-A **sub-skill** is a full `SKILL.md`-addressable lane that a parent skill can spawn as a parallel sub-agent.
-
-## Convention
-
-```
-skills/
-├── README.md                        # this file
-└── <slug>/                          # kebab-case; matches the SKILL.md name
-    ├── SKILL.md                     # frontmatter + routing body (≤ 500 lines)
-    ├── references/                  # optional — long docs loaded on demand
-    ├── templates/                   # optional — reusable text/JS templates
-    └── scripts/                     # optional — deterministic helpers
-```
-
-Each sub-skill's frontmatter follows `@growthub/api-contract/skills::SkillManifest`. Sub-skills share the parent's `.growthub-fork/project.md` journal — they do not branch it.
-
-## Parallelism
-
-Spawn a sub-skill sub-agent when (a) the sub-skill's work is fully scoped by its own criteria, and (b) the parent's next step does not depend on intermediate state from the sub-skill. Each sub-skill run appends a row to `project.md::subSkillRuns` so the parent can read the outcome on return.
-
-See the parent `SKILL.md` `subSkills[]` array for the current roster.

package/assets/worker-kits/creative-strategist-v1/skills/frame-analysis/SKILL.md

@@ -1,88 +0,0 @@
----
-name: creative-strategist-frame-analysis
-description: Sub-skill of creative-strategist-v1 — runs the muse-video frame-extraction pass when no frozen ad-format matches the brief. Invokes helpers/extract-muse-frames.sh and returns a scene-map draft. Meant to be spawned as a parallel sub-agent by the parent creative-strategist skill when Step 2b of the brief runbook is triggered.
-triggers:
-  - muse frame extraction
-  - muse analysis
-  - new muse format
-  - frame-by-frame analysis
-progressiveDisclosure: true
-sessionMemory:
-  path: .growthub-fork/project.md
-selfEval:
-  criteria:
-    - Frame count in the brief matches the muse scene count (if muse has 9 scenes, brief has 9).
-    - Each frame read via the agent's file-read tool, batched at most 3 per call.
-    - Tone-flip boundary (problem → solution) identified and recorded in the scene map.
-    - Output scene map references helpers/extract-muse-frames.sh invocation, not inline shell.
-  maxRetries: 3
-  traceTo: .growthub-fork/trace.jsonl
-helpers:
-  - path: ../../helpers/extract-muse-frames.sh
-    description: Deterministic ffprobe + ffmpeg wrapper — replaces the inline Step 2b shell block.
-subSkills: []
-mcpTools: []
----
-
-# Creative Strategist — Frame Analysis Sub-Skill
-
-Spawned by `creative-strategist-v1` when Step 2b of the brief runbook triggers (no frozen ad-format matches the new muse). Runs in parallel to the parent agent so the parent retains the brief's full context while this sub-agent focuses on frame extraction + scene mapping.
-
-Source of truth for the methodology: `templates/ad-formats/frame-analysis.md` in the parent kit (loaded on demand — this SKILL.md is the routing menu, not the methodology).
-
-## When to spawn this sub-skill
-
-- The brief's muse does not match any entry in `templates/ad-formats/INDEX.md`.
-- A new muse is being frozen into a reusable ad-format.
-- The operator wants the frame-extraction work isolated so the main agent can continue drafting the brief's narrative.
-
-## Decision tree
-
-```
-No frozen ad-format matches?
-├── Yes → parent spawns this sub-skill → parallel execution:
-│         1. bash helpers/extract-muse-frames.sh <muse.mp4>
-│         2. Agent Read-tool over /tmp/muse_frames/*.jpg (batch ≤ 3)
-│         3. Produce scene-map draft with 4 answers:
-│              • scene count
-│              • tone-flip boundary
-│              • character / visual format
-│              • text rhythm
-│         4. Self-eval against criteria above; if pass, return to parent.
-│
-└── No → do not spawn. Parent uses the frozen ad-format directly.
-```
-
-## Sub-skill run protocol
-
-1. Append a `subSkillRuns` row to the fork's `.growthub-fork/project.md` frontmatter: `subSkill: creative-strategist-frame-analysis`, `startedAt`, target muse path.
-2. Run the helper: `bash helpers/extract-muse-frames.sh <muse.mp4>`.
-3. Batch-Read up to 3 frames at a time. Do not dump raw pixel data back to the parent — summarise into the 4-answer scene map.
-4. Self-evaluate against `selfEval.criteria`. Each attempt recorded to `project.md` + `trace.jsonl` via the `growthub-local` `recordSelfEval` primitive (`cli/src/skills/self-eval.ts`).
-5. When `attempt === maxRetries` without pass, park with `needs_confirmation` in `project.md` and return control to the parent.
-
-## Parent-facing return value
-
-Return to the parent agent:
-
-```yaml
-sceneMap:
-  sceneCount: <int>
-  toneFlipAt: <scene index or "none">
-  visualFormat: <short description>
-  textRhythm: <short description>
-selfEval:
-  attempts: <int>
-  result: pass | parked
-framesDir: /tmp/muse_frames
-```
-
-## Freeze-after-run (when brief ships)
-
-After the parent brief ships with this new muse, freeze the format by adding a row to `templates/ad-formats/INDEX.md` + a new `templates/ad-formats/<new-id>.md`. This sub-skill is only re-spawned when a new muse does not match the growing frozen set.
-
-## What this sub-skill does NOT do
-
-- It does not write the brief. The parent skill owns the brief.
-- It does not install ffmpeg / ffprobe. Those are runtime assumptions (see `runtime-assumptions.md` at the kit root, when present).
-- It does not read outside `/tmp/muse_frames/`. Agents running this sub-skill should not probe other tmp paths.