@growthub/cli 0.14.5 → 0.14.6

package/assets/worker-kits/growthub-video-use-studio-v1/.env.example

@@ -1,13 +0,0 @@
-# Growthub Video Use Studio — Environment Config
-# Copy this file to .env and fill in your local values.
-# Never commit .env to version control.
-
-# Absolute path to your local video-use clone.
-# Canonical env var: VIDEO_USE_HOME (uniform pattern across all worker kits)
-# Legacy alias: VIDEO_USE_FORK_PATH (still accepted by setup scripts)
-# Default when unset: $HOME/video-use
-VIDEO_USE_HOME=$HOME/video-use
-
-# ElevenLabs Scribe key — required for transcript generation.
-# Get one at https://elevenlabs.io/app/settings/api-keys
-ELEVENLABS_API_KEY=your_elevenlabs_key_here

package/assets/worker-kits/growthub-video-use-studio-v1/QUICKSTART.md

@@ -1,47 +0,0 @@
-# Video Use Studio Quickstart
-
-## 1) Prepare environment
-
-```bash
-cp .env.example .env
-bash setup/check-deps.sh
-node setup/verify-env.mjs
-```
-
-Required in `.env`:
-
-- `VIDEO_USE_HOME` — absolute path to your local video-use clone (default `$HOME/video-use`)
-- `ELEVENLABS_API_KEY` — ElevenLabs Scribe key for transcript generation
-
-## 2) Clone the video-use upstream
-
-```bash
-bash setup/clone-fork.sh
-```
-
-Clones [`browser-use/video-use`](https://github.com/browser-use/video-use) into `${VIDEO_USE_HOME:-$HOME/video-use}` and runs `pip install -e .`.
-
-## 3) Register as a Claude Code skill
-
-```bash
-bash setup/install-skill.sh
-```
-
-Symlinks the fork into `~/.claude/skills/video-use` per the upstream contract, so Claude Code can load the conversational edit pipeline from any working directory.
-
-## 4) Start work
-
-- Point your agent Working Directory to this exported folder.
-- Follow `workers/video-use-studio-operator/CLAUDE.md`.
-- Place raw footage in `${VIDEO_USE_HOME}/<project>/` and open Claude Code from that directory.
-- Write planning outputs to `output/<client-slug>/<project-slug>/`.
-- Rendered video lands at `${VIDEO_USE_HOME}/<project>/edit/final.mp4` per the upstream contract.
-
-## Execution modes
-
-| Mode | When to use |
-|---|---|
-| `claude-code-skill` | Conversational editing through Claude Code with video-use symlinked as a skill |
-| `local-cli` | Direct Python pipeline runs inside the fork (inventory → transcribe → pack → render) |
-
-See `docs/video-use-fork-integration.md` for the upstream pipeline contract.

package/assets/worker-kits/growthub-video-use-studio-v1/SKILL.md

@@ -1,89 +0,0 @@
----
-name: growthub-video-use-studio-v1
-description: "Self-contained workspace for conversational video editing with browser-use/video-use. Produces implementation-ready video edit plans and rendered segments. Use when the user says: \"video use\", \"browser-use video\", \"conversational video editing\". Session memory tracks edit plans, per-cut renders, and self-eval retries."
-triggers:
-  - video use studio
-  - fork growthub-video-use-studio-v1
-progressiveDisclosure: true
-sessionMemory:
-  path: .growthub-fork/project.md
-selfEval:
-  criteria:
-    - Operator contract (workers/video-use-studio-operator/CLAUDE.md) read before any material change.
-    - .growthub-fork/project.md appended to at each material change.
-    - .growthub-fork/trace.jsonl receives a typed event for each material change.
-    - Kit-specific QUICKSTART / runtime-assumptions / output-standards honoured.
-  maxRetries: 3
-  traceTo: .growthub-fork/trace.jsonl
-helpers: []
-subSkills: []
-mcpTools: []
----
-
-# Growthub Agent Worker Kit — Video Use Studio
-
-Discovery entry + routing menu for the `growthub-video-use-studio-v1` worker kit. Family: `studio`. Agent contract: `workers/video-use-studio-operator/CLAUDE.md`.
-
-## When to use this skill
-
-When the user's intent matches any of the triggers above — or when an agent has been dropped into a fork whose `.growthub-fork/fork.json` declares `kitId: "growthub-video-use-studio-v1"`.
-
-## Decision tree
-
-```
-Fork exists (this directory contains .growthub-fork/fork.json)?
-├── No  → run: growthub starter init --out <path>   (or import-repo / import-skill)
-│         then: growthub kit download growthub-video-use-studio-v1 --out <path>
-│
-└── Yes → read in this order:
-          1. .growthub-fork/project.md                         — session memory (primitive #3)
-          2. SKILL.md  (this file)                             — routing menu  (primitive #1)
-          3. skills.md                                         — operator runbook
-          4. workers/video-use-studio-operator/CLAUDE.md                              — agent contract
-          5. QUICKSTART.md                                     — first-run steps
-          6. runtime-assumptions.md                            — host expectations
-          7. .growthub-fork/policy.json                        — what you may touch
-          8. .growthub-fork/trace.jsonl (tail 20)              — recent machine history
-```
-
-## The six primitives (same shape across every Growthub worker kit)
-
-1. **`SKILL.md`** — this file.
-2. **Symlinked pointer** — repo-root `AGENTS.md` is authoritative.
-3. **`.growthub-fork/project.md`** — session memory, seeded by the CLI from `templates/project.md` at init/import time.
-4. **Self-evaluation** — generate → apply → evaluate → record; retry up to `selfEval.maxRetries` (default 3); mirrors the Fork Sync Agent's preview → apply → trace loop (primitive #4). Contract: `@growthub/api-contract/skills::SkillSelfEval`.
-5. **`skills/`** — nested sub-skills for parallel sub-agents on heavy / narrow work.
-6. **`helpers/`** — safe shell tool layer. Promote inline shell here whenever the same snippet is re-used.
-
-## Self-evaluation (primitive #4)
-
-Enforce `selfEval.maxRetries: 3`. At the ceiling, park with a `needs_confirmation` note in `project.md` and stop. Record every attempt to both `project.md` and `trace.jsonl`.
-
-## Session memory (primitive #3)
-
-`.growthub-fork/project.md` is the only cross-session continuity surface for this fork. Append at every material change, approval boundary, and self-eval outcome.
-
-## Sub-skills (primitive #5)
-
-(None declared at the baseline; populate `skills/` and the frontmatter `subSkills[]` array as specialist lanes emerge.)
-
-## Helpers (primitive #6)
-
-(None declared at the baseline; populate `helpers/` and the frontmatter `helpers[]` array as inline shell matures.)
-
-## MCP routing (optional)
-
-List concrete MCP tool IDs in `mcpTools[]` when a fork runs an MCP server for auth-heavy actions. Declarative only at v1.
-
-## Related files
-
-- `skills.md` — operator runbook (deep)
-- `QUICKSTART.md` — first-run steps
-- `runtime-assumptions.md` — host expectations
-- `output-standards.md` — output locations + manifest shape
-- `validation-checklist.md` — pre-flight checklist (if present)
-- `templates/project.md` — session-memory template
-- `templates/self-eval.md` — self-evaluation template
-- `helpers/README.md` — safe shell tool layer convention
-- `skills/README.md` — sub-skill convention
-- `workers/video-use-studio-operator/CLAUDE.md` — agent contract

package/assets/worker-kits/growthub-video-use-studio-v1/brands/NEW-CLIENT.md

@@ -1,3 +0,0 @@
-# NEW CLIENT
-
-Copy `brands/_template/brand-kit.md` into a new client folder before planning.

package/assets/worker-kits/growthub-video-use-studio-v1/brands/_template/brand-kit.md

@@ -1,7 +0,0 @@
-# Brand Kit Template
-
-- Brand:
-- Audience:
-- Voice:
-- Visual style:
-- Must avoid:

package/assets/worker-kits/growthub-video-use-studio-v1/brands/growthub/brand-kit.md

@@ -1,6 +0,0 @@
-# Growthub Brand Kit
-
-- Brand: Growthub
-- Audience: operators and builders
-- Voice: direct, practical
-- Visual style: clear typography, high contrast, low-motion transitions

package/assets/worker-kits/growthub-video-use-studio-v1/bundles/growthub-video-use-studio-v1.json

@@ -1,54 +0,0 @@
-{
-  "schemaVersion": 2,
-  "bundle": {
-    "id": "growthub-video-use-studio-v1",
-    "version": "1.0.0",
-    "kitId": "growthub-video-use-studio-v1",
-    "workerId": "video-use-studio-operator"
-  },
-  "briefType": "video-use-conversational-edit",
-  "publicExampleBrandPaths": [
-    "brands/growthub/brand-kit.md"
-  ],
-  "requiredFrozenAssets": [
-    "QUICKSTART.md",
-    ".env.example",
-    "skills.md",
-    "output-standards.md",
-    "runtime-assumptions.md",
-    "validation-checklist.md",
-    "workers/video-use-studio-operator/CLAUDE.md",
-    "brands/_template/brand-kit.md",
-    "brands/growthub/brand-kit.md",
-    "brands/NEW-CLIENT.md",
-    "setup/clone-fork.sh",
-    "setup/install-skill.sh",
-    "setup/verify-env.mjs",
-    "setup/check-deps.sh",
-    "output/README.md",
-    "templates/video-brief.md",
-    "templates/edit-strategy.md",
-    "templates/edit-decision-list.md",
-    "templates/render-plan.md",
-    "templates/qa-checklist.md",
-    "examples/video-brief-sample.md",
-    "docs/video-use-fork-integration.md",
-    "docs/provider-adapter-layer.md",
-    "docs/video-use-discovery-path.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"
-  ],
-  "optionalPresets": [],
-  "export": {
-    "folderName": "growthub-agent-worker-kit-video-use-studio-v1",
-    "zipFileName": "growthub-agent-worker-kit-video-use-studio-v1.zip"
-  },
-  "activationModes": [
-    "export"
-  ]
-}

package/assets/worker-kits/growthub-video-use-studio-v1/docs/provider-adapter-layer.md

@@ -1,15 +0,0 @@
-# Provider Adapter Layer
-
-This kit is a custom workspace package and does not add a new server adapter or agent harness.
-
-It relies on:
-
-- Worker kit export contract
-- Working Directory execution
-- Upstream `browser-use/video-use` fork
-- ElevenLabs Scribe (transcription) via `ELEVENLABS_API_KEY`
-- Local FFmpeg for render
-- Optional `yt-dlp` for pulling online sources
-- Claude Code skill loader at `~/.claude/skills/video-use`
-
-No credentials are stored in this repo. All secrets live in the per-export `.env`.

package/assets/worker-kits/growthub-video-use-studio-v1/docs/video-use-discovery-path.md

@@ -1,13 +0,0 @@
-# Video Use Discovery Path
-
-Discovery path:
-
-- `growthub discover` → `Worker Kits` → `Custom Workspaces`
-- `growthub kit list --family studio`
-- `growthub kit download video-use`
-
-Feature branch demo checks:
-
-- `bash scripts/demo-cli.sh cli kit list --family studio`
-- `bash scripts/demo-cli.sh cli kit inspect video-use`
-- `bash scripts/demo-cli.sh cli kit download video-use`

package/assets/worker-kits/growthub-video-use-studio-v1/docs/video-use-fork-integration.md

@@ -1,35 +0,0 @@
-# Video Use Fork Integration
-
-Upstream repository:
-
-- `https://github.com/browser-use/video-use`
-
-Primary execution flow:
-
-1. Clone + install with `setup/clone-fork.sh` (runs `pip install -e .` inside the fork).
-2. Register as a Claude Code skill with `setup/install-skill.sh` (symlinks the fork into `~/.claude/skills/video-use`).
-3. Stage raw footage under `${VIDEO_USE_HOME}/<project>/`.
-4. Launch `claude` from the project directory and start the conversational edit loop.
-
-Pipeline contract (upstream):
-
-```
-inventory → transcribe (ElevenLabs Scribe) → pack phrase-level transcript
-         → converse + propose strategy (4–8 sentences)
-         → user confirmation
-         → EDL generation (word-boundary cuts)
-         → render (FFmpeg + Manim / Remotion / PIL overlays)
-         → self-evaluation (up to 3 iterations)
-         → final.mp4 at <project>/edit/final.mp4
-```
-
-Session persistence:
-
-- Every confirmed decision is appended to `project.md` inside the source video directory.
-
-Two-layer architecture:
-
-- Layer 1 — ElevenLabs Scribe transcript (word-level, speaker-tagged, audio-event markers). The packed transcript is the editor's primary reading view (≈12 KB text + occasional PNGs).
-- Layer 2 — Visual composites (filmstrip / waveform / word labels) generated on-demand for ambiguous decision points only.
-
-Token budget: orders of magnitude lower than raw frame processing.

package/assets/worker-kits/growthub-video-use-studio-v1/examples/video-brief-sample.md

@@ -1,11 +0,0 @@
-# Sample Video Brief
-
-- Goal: Cut founder interview into a 60-second launch teaser
-- Audience: prospective operators browsing the landing page
-- Source footage directory: `${VIDEO_USE_HOME}/launch-teaser/raw/`
-- Duration target: 00:60
-- Aspect ratio: 9:16 (vertical)
-- Delivery format: MP4 (h264 / aac)
-- Aesthetic direction: high-contrast, minimal overlays, captions on every beat
-- Speakers / on-camera subjects: 1 (founder)
-- External sources to pull via `yt-dlp`: none

package/assets/worker-kits/growthub-video-use-studio-v1/growthub-meta/README.md

@@ -1,3 +0,0 @@
-# Video Use Workspace Meta
-
-This directory stores metadata and standards for `growthub-video-use-studio-v1`.

package/assets/worker-kits/growthub-video-use-studio-v1/growthub-meta/kit-standard.md

@@ -1,6 +0,0 @@
-# Kit Standard
-
-- schemaVersion: 2
-- family: studio
-- executionMode: export
-- activationModes: export

package/assets/worker-kits/growthub-video-use-studio-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/growthub-video-use-studio-v1/kit.json

@@ -1,115 +0,0 @@
-{
-  "schemaVersion": 2,
-  "kit": {
-    "id": "growthub-video-use-studio-v1",
-    "version": "1.0.0",
-    "name": "Growthub Agent Worker Kit \u2014 Video Use Studio",
-    "description": "Self-contained local execution environment for conversational video editing with browser-use/video-use. Produces implementation-ready video briefs, transcript-driven edit strategies, edit decision lists, render plans, and QA handoff artifacts for ElevenLabs Scribe + FFmpeg workflows.",
-    "type": "worker",
-    "visibility": "public-open-source",
-    "sourceRepo": "growthub-local",
-    "family": "studio"
-  },
-  "entrypoint": {
-    "workerId": "video-use-studio-operator",
-    "path": "workers/video-use-studio-operator/CLAUDE.md"
-  },
-  "workerIds": [
-    "video-use-studio-operator"
-  ],
-  "agentContractPath": "workers/video-use-studio-operator/CLAUDE.md",
-  "brandTemplatePath": "brands/_template/brand-kit.md",
-  "publicExampleBrandPaths": [
-    "brands/growthub/brand-kit.md"
-  ],
-  "frozenAssetPaths": [
-    "QUICKSTART.md",
-    ".env.example",
-    "skills.md",
-    "output-standards.md",
-    "runtime-assumptions.md",
-    "validation-checklist.md",
-    "workers/video-use-studio-operator/CLAUDE.md",
-    "brands/_template/brand-kit.md",
-    "brands/growthub/brand-kit.md",
-    "brands/NEW-CLIENT.md",
-    "setup/clone-fork.sh",
-    "setup/install-skill.sh",
-    "setup/verify-env.mjs",
-    "setup/check-deps.sh",
-    "output/README.md",
-    "templates/video-brief.md",
-    "templates/edit-strategy.md",
-    "templates/edit-decision-list.md",
-    "templates/render-plan.md",
-    "templates/qa-checklist.md",
-    "examples/video-brief-sample.md",
-    "docs/video-use-fork-integration.md",
-    "docs/provider-adapter-layer.md",
-    "docs/video-use-discovery-path.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"
-  ],
-  "setupPaths": {
-    "quickstart": "QUICKSTART.md",
-    "envExample": ".env.example",
-    "setupDir": "setup/",
-    "outputDir": "output/"
-  },
-  "outputStandard": {
-    "type": "working-directory",
-    "description": "Exported folder is intended to be pointed at directly by the agent Working Directory. All planning outputs are markdown files written to output/<client-slug>/<project-slug>/. Rendered video artifacts land at ${VIDEO_USE_HOME}/<videos_dir>/edit/final.mp4 per the upstream video-use contract.",
-    "requiredPaths": [
-      "QUICKSTART.md",
-      ".env.example",
-      "kit.json",
-      "bundles/growthub-video-use-studio-v1.json",
-      "skills.md",
-      "workers/video-use-studio-operator/CLAUDE.md",
-      "brands/_template/brand-kit.md",
-      "brands/growthub/brand-kit.md",
-      "brands/NEW-CLIENT.md",
-      "setup/clone-fork.sh",
-      "setup/install-skill.sh",
-      "setup/verify-env.mjs",
-      "setup/check-deps.sh",
-      "output/README.md",
-      "templates",
-      "docs",
-      "growthub-meta",
-      "SKILL.md",
-      "templates/project.md",
-      "templates/self-eval.md",
-      "helpers",
-      "helpers/README.md",
-      "skills",
-      "skills/README.md"
-    ]
-  },
-  "bundles": [
-    {
-      "id": "growthub-video-use-studio-v1",
-      "version": "1.0.0",
-      "path": "bundles/growthub-video-use-studio-v1.json"
-    }
-  ],
-  "executionMode": "export",
-  "activationModes": [
-    "export"
-  ],
-  "compatibility": {
-    "cliMinVersion": "0.4.3"
-  },
-  "provenance": {
-    "sourceRepo": "growthub-local",
-    "frozenAt": "2026-04-23T00:00:00.000Z"
-  },
-  "workspaceVisibility": "addon",
-  "workspaceCompatible": false,
-  "workspaceCategory": "studio"
-}

package/assets/worker-kits/growthub-video-use-studio-v1/output/README.md

@@ -1,9 +0,0 @@
-# Output Directory
-
-Save planning outputs under:
-
-- `output/<client-slug>/<project-slug>/`
-
-Rendered video artifacts are produced by the upstream pipeline at:
-
-- `${VIDEO_USE_HOME}/<project>/edit/final.mp4`

package/assets/worker-kits/growthub-video-use-studio-v1/output-standards.md

@@ -1,19 +0,0 @@
-# Output Standards
-
-Planning deliverables — write to:
-
-- `output/<client-slug>/<project-slug>/`
-
-Minimum required planning artifacts:
-
-- `video-brief.md`
-- `edit-strategy.md`
-- `edit-decision-list.md`
-- `render-plan.md`
-- `qa-checklist.md`
-
-Rendered video artifact — produced by the upstream pipeline:
-
-- `${VIDEO_USE_HOME}/<project>/edit/final.mp4`
-
-Every decision appended to `project.md` inside the source video directory per the upstream video-use session-persistence contract.

package/assets/worker-kits/growthub-video-use-studio-v1/runtime-assumptions.md

@@ -1,9 +0,0 @@
-# Runtime Assumptions
-
-- Upstream project: `https://github.com/browser-use/video-use`
-- Python `>=3.11` with `pip` available
-- `ffmpeg` available in PATH (required)
-- `yt-dlp` available in PATH (optional — only for downloading online sources)
-- `ELEVENLABS_API_KEY` set in `.env` — required for transcript generation via ElevenLabs Scribe
-- `~/.claude/skills/video-use` symlink present — set up by `setup/install-skill.sh`
-- Commands run from an exported working directory; raw footage lives under `${VIDEO_USE_HOME}/<project>/`

package/assets/worker-kits/growthub-video-use-studio-v1/setup/check-deps.sh

@@ -1,21 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-need_cmd() {
-  command -v "$1" >/dev/null 2>&1 || {
-    echo "Missing dependency: $1" >&2
-    exit 1
-  }
-}
-
-optional_cmd() {
-  if ! command -v "$1" >/dev/null 2>&1; then
-    echo "Optional dependency not found: $1 (only needed for downloading online sources)" >&2
-  fi
-}
-
-need_cmd python3
-need_cmd pip3
-need_cmd git
-need_cmd ffmpeg
-optional_cmd yt-dlp

package/assets/worker-kits/growthub-video-use-studio-v1/setup/clone-fork.sh

@@ -1,18 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-REPO_URL="${VIDEO_USE_REPO_URL:-https://github.com/browser-use/video-use}"
-# Canonical: VIDEO_USE_HOME. Legacy alias: VIDEO_USE_FORK_PATH.
-LOCAL_PATH="${VIDEO_USE_HOME:-${VIDEO_USE_FORK_PATH:-$HOME/video-use}}"
-
-if [ -d "${LOCAL_PATH}/.git" ]; then
-  git -C "${LOCAL_PATH}" fetch origin
-  git -C "${LOCAL_PATH}" pull --ff-only
-else
-  git clone "${REPO_URL}" "${LOCAL_PATH}"
-fi
-
-# Install the upstream package in editable mode so the CLI + skill resolve correctly.
-if command -v pip3 >/dev/null 2>&1; then
-  (cd "${LOCAL_PATH}" && pip3 install -e .)
-fi

package/assets/worker-kits/growthub-video-use-studio-v1/setup/install-skill.sh

@@ -1,23 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# Register the video-use fork as a Claude Code skill per the upstream README contract.
-# Canonical: VIDEO_USE_HOME. Legacy alias: VIDEO_USE_FORK_PATH.
-LOCAL_PATH="${VIDEO_USE_HOME:-${VIDEO_USE_FORK_PATH:-$HOME/video-use}}"
-SKILLS_DIR="${CLAUDE_SKILLS_DIR:-$HOME/.claude/skills}"
-LINK_PATH="${SKILLS_DIR}/video-use"
-
-if [ ! -d "${LOCAL_PATH}" ]; then
-  echo "video-use fork not found at ${LOCAL_PATH}. Run setup/clone-fork.sh first." >&2
-  exit 1
-fi
-
-mkdir -p "${SKILLS_DIR}"
-
-if [ -L "${LINK_PATH}" ] || [ -e "${LINK_PATH}" ]; then
-  echo "Skill entry already present at ${LINK_PATH}. Leaving as-is." >&2
-  exit 0
-fi
-
-ln -s "${LOCAL_PATH}" "${LINK_PATH}"
-echo "Linked ${LOCAL_PATH} -> ${LINK_PATH}"

package/assets/worker-kits/growthub-video-use-studio-v1/setup/verify-env.mjs

@@ -1,23 +0,0 @@
-import fs from "node:fs";
-import path from "node:path";
-
-const envPath = path.resolve(process.cwd(), ".env");
-if (!fs.existsSync(envPath)) {
-  console.error(".env not found. Run: cp .env.example .env");
-  process.exit(1);
-}
-
-const raw = fs.readFileSync(envPath, "utf8");
-
-// Canonical: VIDEO_USE_HOME. Legacy alias: VIDEO_USE_FORK_PATH.
-if (!raw.includes("VIDEO_USE_HOME=") && !raw.includes("VIDEO_USE_FORK_PATH=")) {
-  console.error("VIDEO_USE_HOME (or legacy VIDEO_USE_FORK_PATH) is required in .env");
-  process.exit(1);
-}
-
-if (!/ELEVENLABS_API_KEY=\S/.test(raw) || /ELEVENLABS_API_KEY=your_elevenlabs_key_here/.test(raw)) {
-  console.error("ELEVENLABS_API_KEY is required in .env (for ElevenLabs Scribe transcription)");
-  process.exit(1);
-}
-
-console.log("Environment check passed.");

package/assets/worker-kits/growthub-video-use-studio-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/growthub-video-use-studio-v1/skills.md

@@ -1,21 +0,0 @@
-# Video Use Studio Skills
-
-1. Read `runtime-assumptions.md`.
-2. Read `docs/video-use-fork-integration.md`.
-3. Confirm target format: content type, target length, aesthetic direction.
-4. Produce, in order:
-   - `templates/video-brief.md` — source inventory, goal, audience, duration
-   - `templates/edit-strategy.md` — 4–8 sentence proposed approach, wait for confirmation
-   - `templates/edit-decision-list.md` — transcript-anchored EDL with word-boundary cuts
-   - `templates/render-plan.md` — FFmpeg commands, overlay tool choice (Manim / Remotion / PIL)
-   - `templates/qa-checklist.md` — twelve production rules pass, subtitles-last validation
-
-Non-negotiable rules enforced by this kit:
-
-- Subtitles are applied last, after all overlays.
-- 30 ms audio fades at every segment boundary.
-- Word-boundary snapping for every cut; never cut inside a word.
-- Overlays use `setpts=PTS-STARTPTS+T/TB` for timing.
-- Cached transcripts are reused; never re-transcribe a source twice.
-
-Use deterministic command paths. Resolve workspace with `${VIDEO_USE_HOME:-$HOME/video-use}`. Never expose `ELEVENLABS_API_KEY` in output artifacts.