PHPackages dan/ai-loom-planner - PHPackages - PHPackages [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register) 1. [Directory](/) 2. / 3. [Utility & Helpers](/categories/utility) 4. / 5. dan/ai-loom-planner ActiveLibrary[Utility & Helpers](/categories/utility) dan/ai-loom-planner =================== Generate context files and agent prompts from Loom video walkthroughs. v3.1.0(2mo ago)0240↑37.5%MITPHPPHP ^8.2 Since Apr 29Pushed 2mo agoCompare [ Source](https://github.com/DataAndNumbersOrganization/ai-loom-plan)[ Packagist](https://packagist.org/packages/dan/ai-loom-planner)[ Docs](https://github.com/DataAndNumbersOrganization/ai-loom-plan)[ RSS](/packages/dan-ai-loom-planner/feed)WikiDiscussions main Synced 1w ago READMEChangelogDependencies (5)Versions (9)Used By (0) AI Loom Planner =============== [](#ai-loom-planner) Generate ready-to-use AI agent prompts from Loom video walkthroughs — right from the command line. This Laravel package extracts a Loom transcript and screenshots, builds a structured context file, and prints a copy-pastable prompt for your preferred AI agent (Warp, Cursor, Copilot, etc.) to turn into an implementation plan. Features -------- [](#features) - **Transcript extraction** — pulls Loom transcripts via oEmbed, page scraping, API fallback, and Playwright (automatic cascade) - **Screenshot capture** — grabs frames at configurable intervals with perceptual-hash deduplication - **Prompt building** — assembles a structured context file with transcript, metadata, and screenshot references - **Prompt templates** — ships with `feature`, `bug`, `epic`, and `documentation` templates; fully customisable via publish - **Two commands** — `loom:plan` for context + prompt output; `loom:transcript` for quick transcript access Requirements ------------ [](#requirements) DependencyVersionPHP8.2+Laravel11.x, 12.x, or 13.xNode.js18+ (for Playwright scripts)Playwright`@playwright/test` installed in your projectNo AI provider or API key is required — the command builds the context and prints a prompt for you to paste into your preferred AI agent (Warp, Cursor, Copilot, etc.). Playwright is only needed if you use screenshot capture (`--screenshots`) or if static transcript scraping fails (Playwright is the final fallback for transcript extraction). The package works without it — you'll just get fewer features. Installation ------------ [](#installation) ``` composer require dan/ai-loom-planner ``` Publish the config file: ``` php artisan vendor:publish --tag=loom-planner-config ``` Optionally publish the prompt templates if you want to customise them: ``` php artisan vendor:publish --tag=loom-planner-templates ``` ### Playwright setup (optional) [](#playwright-setup-optional) If you want screenshot capture or the Playwright transcript fallback: ``` npm install @playwright/test npx playwright install chromium ``` Configuration ------------- [](#configuration) After publishing, edit `config/loom-planner.php`: ``` return [ /* |-------------------------------------------------------------------------- | Tech Stack Description |-------------------------------------------------------------------------- | | A multi-line string describing your project's tech stack. | This is injected into the AI prompt so the plan references the | correct frameworks, languages, and tools. | | Set to null to use the built-in default (Laravel + Next.js + MySQL). | */ 'tech_stack' => env('LOOM_PLAN_TECH_STACK', null), /* |-------------------------------------------------------------------------- | Application Name |-------------------------------------------------------------------------- | | Used in AI prompts to give the model project context. | Defaults to your Laravel app name. | */ 'app_name' => env('LOOM_PLAN_APP_NAME', null), // falls back to config('app.name') /* |-------------------------------------------------------------------------- | Output Directory |-------------------------------------------------------------------------- | | Where generated plans and screenshots are saved. | */ 'output_dir' => env('LOOM_PLAN_OUTPUT_DIR', 'docs-and-plans/loom'), /* |-------------------------------------------------------------------------- | Templates Directory |-------------------------------------------------------------------------- | | Path to a directory containing prompt Blade templates. | Leave as null to use the package's bundled templates. | If you publish templates with `vendor:publish --tag=loom-planner-templates`, | set this to `resource_path('views/vendor/loom-planner')` to load them. | */ 'templates_dir' => null, ]; ``` ### Environment variables [](#environment-variables) ``` # Optional overrides LOOM_PLAN_OUTPUT_DIR=docs-and-plans/loom LOOM_PLAN_TECH_STACK="- **Backend**: Laravel\n- **Frontend**: React" LOOM_PLAN_APP_NAME=MyApp ``` Usage ----- [](#usage) ### `loom:plan` — Generate an implementation plan [](#loomplan--generate-an-implementation-plan) ``` # Fetch transcript, capture screenshots, and output a copy-pastable agent prompt php artisan loom:plan https://www.loom.com/share/abc123def456... # Capture screenshots every 5 seconds (default: 10) php artisan loom:plan https://www.loom.com/share/abc123... --screenshots=5 # Disable screenshots entirely php artisan loom:plan https://www.loom.com/share/abc123... --screenshots=0 # Use the "bug" plan template php artisan loom:plan https://www.loom.com/share/abc123... --template=bug # Custom output filename php artisan loom:plan https://www.loom.com/share/abc123... --output=my-feature-plan ``` #### Options [](#options) OptionDescriptionDefault`url` (argument)Loom video URL— (required)`--screenshots`Seconds between screenshot captures (1–60, 0 to disable)`10``--template`Plan template: `feature`, `bug`, `epic`, or `documentation``feature``--output`Custom output filenameAuto-generated from video title#### Workflow [](#workflow) The command fetches the transcript, captures screenshots, writes a context file, and prints a copy-pastable agent prompt: ``` 🎬 Fetching Loom video data... ✓ Video: Dashboard Redesign Walkthrough ✓ Duration: 4m 32s ✓ Transcript: 847 words 📸 Capturing screenshots at 10s intervals... ✓ Captured 27 frames, 14 unique after dedup ─── Copy below ─── I have a Loom video walkthrough for a new feature I need to implement... docs-and-plans/loom/contexts/loom-plan-dashboard-redesign-walkthrough-context.md docs-and-plans/loom/screenshots/loom-plan-dashboard-redesign-walkthrough-0010-reviewing-the-dashboard.jpg ─── End ─── ``` ### `loom:transcript` — Fetch a transcript [](#loomtranscript--fetch-a-transcript) ``` # Plain text transcript php artisan loom:transcript https://www.loom.com/share/abc123... # With timestamps php artisan loom:transcript https://www.loom.com/share/abc123... --timestamps # Raw JSON output php artisan loom:transcript https://www.loom.com/share/abc123... --json ``` #### Options [](#options-1) OptionDescriptionDefault`url` (argument)Loom video URL— (required)`--timestamps`Prefix each segment with `[M:SS]``false``--json`Output raw JSON (title, duration, transcript, segments)`false`How It Works ------------ [](#how-it-works) ### 1. Video data extraction (`LoomVideoService`) [](#1-video-data-extraction-loomvideoservice) The service tries multiple strategies in order: 1. **oEmbed API** — fetches title, thumbnail, and duration (no auth required) 2. **Page scraping** — loads the share page HTML and searches for transcript data in: - Apollo state (`__APOLLO_STATE__`) - Next.js data (`__NEXT_DATA__`) - Generic `` tags containing video JSON 3. **Transcription API** — tries Loom's direct `/v1/videos/{id}/transcriptions` endpoint 4. **Playwright** (final fallback) — launches a headless browser, loads the page with full JS execution, and extracts the transcript from the rendered DOM or intercepted API calls ### 2. Screenshot capture (`LoomScreenshotService`) [](#2-screenshot-capture-loomscreenshotservice) When screenshots are enabled, a Node.js/Playwright script: - Opens the Loom embed in a headless Chromium browser - Seeks the video to each target timestamp and takes a screenshot - Computes a perceptual hash (aHash) for each frame *in the browser* - Deduplicates consecutive identical/near-identical frames (Hamming distance ≤ 5) - Returns only unique frames as JPEG files Screenshots are saved with contextual filenames derived from the nearest transcript segment: ``` loom-plan-BBCM-1234-0012-reviewing-the-dashboard.jpg loom-plan-BBCM-1234-0047-clicking-the-save-button.jpg ``` ### 3. Context + prompt output (`LoomPlanService`) [](#3-context--prompt-output-loomplanservice) The service assembles a structured context prompt containing: - Video metadata (title, duration, URL) - Full timestamped transcript - Screenshot labels and timestamps - Your project's tech stack description This is saved as a context markdown file and its path is printed alongside a ready-to-paste agent instruction. Paste both into your AI agent of choice to generate the plan. Templates --------- [](#templates) The package ships with four prompt templates in `resources/templates/`: TemplateUse case`feature`New feature implementation (default)`bug`Bug diagnosis and fix planning`epic`Breaking down a large epic into discrete tasks`documentation`Converting a walkthrough into admin-facing documentation### Customising templates [](#customising-templates) After publishing (`vendor:publish --tag=loom-planner-templates`), templates are copied to `resources/views/vendor/loom-planner/`. Each template receives two variables: - `$planPath` — the file path where the plan should be saved - `$screenshotLine` — a sentence about attached screenshots (empty string if none) Example custom template: ``` Read the transcript below and create a migration plan for our Phoenix/Elixir app.{{ $screenshotLine }} Save the plan to `{{ $planPath }}`. ``` Output Structure ---------------- [](#output-structure) All generated files are saved under the configured `output_dir` (default: `docs-and-plans/loom/`): ``` docs-and-plans/loom/ ├── contexts/ │ └── loom-plan-my-feature-context.md # Transcript + metadata (attach to AI agent) └── screenshots/ ├── loom-plan-my-feature-0000-intro-and-overview.jpg ├── loom-plan-my-feature-0010-reviewing-the-dashboard.jpg └── ... ``` Architecture ------------ [](#architecture) ``` src/ ├── LoomPlannerServiceProvider.php # Config, commands, views registration ├── Commands/ │ ├── LoomPlanCommand.php # loom:plan artisan command │ └── LoomTranscriptCommand.php # loom:transcript artisan command └── Services/ ├── LoomVideoService.php # URL parsing, oEmbed, transcript extraction ├── LoomPlanService.php # Context/prompt building └── LoomScreenshotService.php # Playwright screenshot capture & dedup ``` The Playwright helper scripts (`resources/scripts/loom-transcript.cjs` and `loom-screenshot.cjs`) intentionally use the `.cjs` extension so Node loads them as CommonJS even when the consumer project's `package.json` declares `"type": "module"`. See [Troubleshooting](#troubleshooting) for context. Troubleshooting --------------- [](#troubleshooting) ### `ReferenceError: require is not defined in ES module scope` [](#referenceerror-require-is-not-defined-in-es-module-scope) Fixed in **v1.0.1**. If you are pinned to `v1.0.0` and your project's `package.json` declares `"type": "module"`, the bundled `.js` Playwright scripts will fail with this error because Node treats every `.js` file as ESM. Bump to `^1.0.1` (`composer update dan/ai-loom-planner`) — the scripts now ship as `.cjs` so Node always parses them as CommonJS. ### `Cannot find module '@playwright/test'` [](#cannot-find-module-playwrighttest) Install Playwright in your consuming project (the package looks up `@playwright/test` via `NODE_PATH=/node_modules`): ``` npm install @playwright/test npx playwright install chromium ``` This is only required if you use `--screenshots` or hit the Playwright transcript fallback. ### `node not found — cannot run Playwright transcript extraction` [](#node-not-found--cannot-run-playwright-transcript-extraction) The package looks for `node` via `which node`, then falls back to `/usr/local/bin/node`, `/opt/homebrew/bin/node`, and `/usr/bin/node`. If your Node.js binary is somewhere else (e.g. nvm-managed), make sure that path is on the PHP process's `PATH` (Laravel Herd / valet / Octane workers may have a different `PATH` from your interactive shell). Testing ------- [](#testing) ``` composer test ``` The test suite covers: - **Unit tests** — service-level logic (URL parsing, prompt building, transcript normalisation, config) - **Feature tests** — full command execution with mocked services See [`tests/`](tests/) for the complete test suite. Versioning ---------- [](#versioning) This package follows [Semantic Versioning](https://semver.org/). The public API surface — artisan command signatures, service class signatures, config keys, and publish tags — is covered by semver from `v1.0.0` onwards. See [`CHANGELOG.md`](CHANGELOG.md) for release notes. License ------- [](#license) MIT — see [`LICENSE`](LICENSE) for the full text. ### Health Score 42 — FairBetter than 88% of packages Maintenance85 Actively maintained with recent releases Popularity15 Limited adoption so far Community6 Small or concentrated contributor base Maturity52 Maturing project, gaining track record Bus Factor1 Top contributor holds 100% of commits — single point of failure How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window. **Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores. **Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement. **Maturity (30%)** — Project age, version count, PHP version support, and release stability. ### Release Activity Cadence Every ~1 days Total 8 Last Release 75d ago Major Versions v1.0.3 → v3.0.02026-05-01 ### Community Maintainers ![](https://avatars.githubusercontent.com/u/219?v=4)[Dan Benjamin](/maintainers/dan)[@dan](https://github.com/dan) --- Top Contributors [![danrichards](https://avatars.githubusercontent.com/u/470255?v=4)](https://github.com/danrichards "danrichards (14 commits)") --- Tags laravelaiplanningtranscriptloom ### Code Quality TestsPHPUnit ### Embed Badge ![Health badge](/badges/dan-ai-loom-planner/health.svg) ``` [![Health](https://phpackages.com/badges/dan-ai-loom-planner/health.svg)](https://phpackages.com/packages/dan-ai-loom-planner) ``` ### Alternatives [psalm/plugin-laravel Psalm plugin for Laravel 3345.3M347](/packages/psalm-plugin-laravel)[laravel/mcp Rapidly build MCP servers for your Laravel applications. 77922.3M186](/packages/laravel-mcp)[spatie/laravel-export Create a static site bundle from a Laravel app 674146.0k6](/packages/spatie-laravel-export)[zidbih/laravel-deadlock Make temporary Laravel workarounds expire and fail CI when ignored. 985.4k](/packages/zidbih-laravel-deadlock)[aedart/athenaeum Athenaeum is a mono repository; a collection of various PHP packages 255.2k](/packages/aedart-athenaeum) PHPackages © 2026 [Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)