
Explain budget versus actual variances with performance insights, key drivers, and recommended actions
Extract audio tracks from video files using FFmpeg with format conversion options
# deploy ## Description Deployment automation skill for EC2 instances. Automates git pull, service restart, and health checks for configured hosts. ## Category DevOps / Deployment / Automation ## Commands ### deploy Deploy to one or more hosts with git pull, service restart, and health check. ```bash bun run src/index.ts deploy <host...> [options] ``` Options: - `--all` - Deploy to all configured hosts - `--parallel, -p` - Deploy to multiple hosts in parallel - `--skip-health` - Skip hea
Generate professional audio cleanup recipes and mastering guidelines for noisy recordings
Perform brand style guide operations
Instant data science insights for CSV and JSON files with statistical summaries, quality audits, and trend detection
Generate high-quality PDF documents from markdown, HTML, or templates
Merge a GitHub pull request, merge when green, use a merge queue, or decide whether a pull request is mergeable. Use only for explicit merge intent, not ordinary review.
Generate premium customer feedback reports from reviews, support tickets, surveys, call notes, or raw feedback with clusters, sentiment, root causes, roadmap recommendations, evidence, and manifest metadata.
Generate premium performance audit reports for web apps, APIs, or SaaS surfaces with metrics, findings, budgets, remediation plans, and manifest metadata.
Compress videos while preserving quality using FFmpeg with multiple codec options and preset configurations
Generate docx with customizable options
Generate images using OpenAI, Minimax, or Gemini through the hosted Skills runtime with provider-cost pricing.
Transcribe audio, video, YouTube, Vimeo, and generic media URLs with iapp-transcriber or the hosted Skills runtime. Supports OpenAI GPT-4o transcription, OpenAI diarization, ElevenLabs Scribe v2, DeepGram, chunking, source metadata, subtitles, and JSON outputs.
Run hosted browser automation and page extraction through the Skills runtime.
Run hosted deep research with parallel search, synthesis, citations, source notes, and downloadable report artifacts.
Create and manage grouped tmux sessions where each session focuses on its own window and its own folder. Knows workspace layout, naming conventions, and both multi-project and multi-agent patterns.
Bootstrap a brand-new Hasna repo project or work project with the current `projects create`/`start` workflow, register todos/conversations, create the project's conversations channel, and preserve the intended category and naming convention.
Full session start — reuse or register an agent identity across todos, conversations, and mementos, send a heartbeat, join your duty channels per agent class, then check unread messages and pending tasks. Run this at the very start of EVERY session. (Replaces the former skill-agent-login.)
Take a high-level goal and drive it to done — break it into tasks via the todos CLI, open a goal thread in the project's conversations channel, create a plan in todos, generate the tasks under that plan, then execute them one by one until complete. Use for 'execute this goal', 'break down and do X', 'set a goal and run it'.
Full publish workflow for @hasna npm packages. Runs tests, logical commits, push, OSS checks (if hasna org), posts publish intent to git-publishing, publishes to npm, installs locally via bun, verifies via CLI, confirms in-thread. Never uses npm to install.
Use when Codewith needs to create, edit, save, verify, execute, route, or sync todos plans for local @hasna/todos work or hosted todos.md/platform-todos work. Triggers include todos plan authoring, local plan Markdown files, plan IDs, task-triggered workers, launch verification checklists, platform plan sync, dry-run plan generation, and updating Codewith workers that must use Todos CLI task IDs as source of truth.
Use when creating, validating, serving, or documenting Hasna agent-managed project dashboards and JSON Render reports with the Projects CLI, provider panels, .hasna/project layout, or
File format conversion and transformation CLI between images, PDFs, documents, CSV, and data formats.
Generate premium static one-page website bundles with HTML, CSS, JavaScript, copy, section map, deploy notes, and manifest.
Generate premium API, unit, and browser test suite packages with runnable tests and coverage notes.
Generate premium API documentation portals from OpenAPI specs, route lists, or examples.
Fetch official brand assets from a website or brand name, then return logos, palette, typography, source metadata, and a clean asset manifest. Use when a user asks to find, extract, download, package, or normalize a brand's logo and visual identity assets.
Extract text and structured data from images and PDFs using OpenAI Vision
Generate premium contract review reports with clause summaries, risk register, negotiation points, redline-style suggestions, counterparty email draft, and manifest metadata.
Generate premium transcript packages with timestamps, summaries, show notes, clip suggestions, repurposing copy, captions, and manifest metadata.
Convert PDFs into clean markdown through the hosted Skills runtime.
Generate hosted brand or product photo shoot sets
Generate speech and audio using OpenAI, Minimax, or Gemini through the hosted Skills runtime with provider-cost pricing.
Extract tables, forms, invoices, and semi-structured PDF content into CSV and JSON datasets through the hosted Skills runtime.
Generate premium repository onboarding reports with architecture maps, setup guides, first-week plans, code inventory, risk register, and manifest metadata.
Generate premium SDK scaffolds with typed client code, package files, tests, README, usage examples, API summary, and manifest.
Generate hosted short-form video packs from a creative brief
Public contract for domain purchase workflows through hosted or external registrar connectors.
Generate premium social content calendars with daily posts, channel strategy, asset briefs, publishing schedule, and repurposing map.
Generate premium video highlight packages with clip plans, captions, thumbnails, chapter markers, social copy, edit decisions, and manifest metadata.
Generate premium migration planning packs for framework, library, database, infrastructure, or architecture upgrades with risk matrix, checklist, rollout plan, and test strategy.
Generate music using Minimax or Gemini Lyria through the hosted Skills runtime with provider-cost pricing.
Generate premium meeting artifact packs from transcripts or notes with summaries, decisions, action items, owner/deadline tables, follow-up email, project export, timeline, and manifest metadata.
Generate one or more SEO-ready blog article packages as hosted premium artifacts.
Generate a premium security hardening report covering auth, secrets, headers, webhooks, RLS, permissions, dependency risk, and prioritized fixes.
Read and extract text from multiple PDF files with page-range selection and parallel processing
Analyze PDF files with Claude document blocks. Supports page-range selection, 20-page chunking, and merged structured output.
Generate hosted themed photo albums with configurable image counts
Generate premium SEO content packages with topic clusters, articles, metadata, links, FAQs, and publishing cadence.
Generate premium brand kits with logo usage, palette, typography, brand voice, sample applications, Markdown guide, and PDF guide.
Generate premium invoice reconciliation reports from invoice, payment, purchase order, or CSV/XLSX-style exports with matches, discrepancies, anomaly notes, summaries, and manifest metadata.
Generate a coordinated icon pack and return SVGs plus transparent PNGs. Use when a user asks for an icon set, icon pack, app icons, UI icons, or a coordinated set of glyphs for a brand or product.
Generate premium email campaigns with subject lines, preview text, body copy, segmentation notes, CTA variants, and HTML exports.
Generate premium landing page copy, wireframes, CTA maps, experiments, and preview artifacts.
Generate videos using OpenAI Sora, Minimax Hailuo, Gemini Veo, or Seedance through the hosted Skills runtime with provider-cost pricing.
Generate premium multi-variant logo packages with transparent PNG exports, vector-style SVGs, usage notes, and a manifest.
# codefix ## Description Code quality skill that provides auto-linting, formatting, and code fixes through a unified CLI interface. Wraps existing tools like ESLint, Prettier, Ruff, gofmt, etc. ## Category Development Tools / Code Quality ## Commands ### fix Fix code issues in file(s) or directory. ```bash bun run src/index.ts fix <path> [options] ``` Options: - `--type <lint|format|types|all>` - Type of fix (default: all) - `--write` - Write fixes to files - `--diff` - Show diff of chan
Generate a premium market research report with competitor, audience, pricing, source, Markdown, and PDF artifacts.
Generate premium investor or sales pitch deck packages with PPTX, PDF, notes, and design direction.
Generate premium slide decks from briefs, docs, or outlines with PPTX/PDF artifacts, speaker notes, theme guidance, structured slide metadata, and manifest metadata.
Generate hosted music album packages with 7, 14, or 21 songs
Generate premium client proposal packages with proposal, SOW, pricing, timeline, assumptions, cover email, Markdown, and PDF artifacts.
Generate hosted voiceover variants and short jingles
Create a curated playlist with research, track selection, and AI-generated album art
Generate high-quality articles using parallel AI agents. Supports research, writing, and optional cover image generation. Write single articles or batch process multiple topics with configurable parallelism.
Generate premium product mockup packages with SVG visual variants, image direction prompts, scene planning, usage notes, asset metadata, and manifest.
Generate premium paid-ad copy, creative concepts, image prompts, audience angles, and test matrices.
# skill-siteanalyze Analyze any website's design system — detects shadcn/ui, Tailwind, extracts colors, typography, and components via Playwright + Claude Vision. ## Usage ```bash skill-siteanalyze <url> ``` ## What It Does - Navigates to the target URL using Playwright - Takes a screenshot and analyzes it with Claude Vision - Detects UI framework (shadcn/ui, Tailwind CSS, etc.) - Extracts color palette, typography scale, and component patterns - Outputs an open-styles compatible design pro
Generate images using AI providers (OpenAI DALL-E 3, Google Gemini 3.0, xAI Aurora)
AI-powered browser automation using Browser-Use Cloud API
Read and extract text from DOCX files with section parsing, metadata extraction, and multiple file support
Perform brand style guide operations
Perform deep research on any topic using Exa.ai for parallel semantic search and Claude/OpenAI for synthesis. Use when you need comprehensive research reports with citations, analysis of topics from multiple angles, or thorough investigation of technical subjects.
Create Claude Code hooks with standardized structure. Generates complete hook scaffolds with setup commands, logging, and Claude config integration. Just run `skill-hook` to create a new hook template.
Compress videos while preserving quality using FFmpeg with multiple codec options and preset configurations
Explain budget versus actual variances with performance insights, key drivers, and recommended actions
Analyze PDF files with Claude document blocks. Supports page-range selection, 20-page chunking, and merged structured output.
Create logical commits from all staged and unstaged changes, then push directly to main. Groups related changes into separate commits with conventional commit messages. Use when you want to commit and push without creating a PR.
Extract color palettes from screenshots and images using Claude Vision. Outputs open-styles-compatible profiles.
Create logical commits from all changes, push to a new branch, and open a pull request on GitHub. Groups related changes into separate commits with conventional commit messages. Use when you want to submit changes for review via PR instead of pushing directly to main.
Read and extract text from DOCX files with section parsing, metadata extraction, and multiple file support
Generate emoji packs using AI-powered prompt generation and image creation
Extract text and structured data from images and PDFs using OpenAI Vision
Scan repo for all changes, group them into logical commits with conventional messages, and push to GitHub. Use when the user says "commit", "push", or invokes /commit. Does NOT create a pull request.
Analyze an image from a local path or URL with Claude vision. Supports prompt-controlled description, OCR, object counting, and brand/visual extraction.
Publish npm packages with sensible defaults. Automatically sets private access and bumps patch version (0.0.1). Use when publishing packages to npm, especially for internal/private packages.
Interact with the open-monitor MCP — check machine health, list processes, kill memory hogs, run doctor, manage cron jobs, trigger cache cleanup
Generate music tracks using AI models (Minimax Music-01)
Generate professional audio cleanup recipes and mastering guidelines for noisy recordings
Extract audio tracks from video files using FFmpeg with format conversion options
# skill-codefix ## Description Code quality skill that provides auto-linting, formatting, and code fixes through a unified CLI interface. Wraps existing tools like ESLint, Prettier, Ruff, gofmt, etc. ## Category Development Tools / Code Quality ## Commands ### fix Fix code issues in file(s) or directory. ```bash bun run src/index.ts fix <path> [options] ``` Options: - `--type <lint|format|types|all>` - Type of fix (default: all) - `--write` - Write fixes to files - `--diff` - Show diff o
Extract color palettes from screenshots and images using Claude Vision. Outputs open-styles-compatible profiles.
Purchase and manage domains via GoDaddy API with CLI and HTTP server
Generate emoji packs using AI-powered prompt generation and image creation
Read and extract text from multiple PDF files with page-range selection and parallel processing
Parse XLS and XLSX workbooks into structured JSON with sheet metadata, named ranges, and formatted cell snapshots.
Generate sound effects using AI models (Minimax)
Create and manage grouped tmux sessions where each session focuses on its own window and its own folder. Knows workspace layout, naming conventions, and both multi-project and multi-agent patterns.
Create logical commits from all staged and unstaged changes, then push directly to main. Groups related changes into separate commits with conventional commit messages. Use when you want to commit and push without creating a PR.
Generate Excel spreadsheets with tables, formulas, multiple sheets, styling, and optional AI-generated data.
Search domain availability and suggestions via GoDaddy API
Publish npm packages with sensible defaults. Automatically sets private access and bumps patch version (0.0.1). Use when publishing packages to npm, especially for internal/private packages.
Generate high-quality audio using ElevenLabs, OpenAI TTS, and Google Text-to-Speech APIs. Support for text-to-speech, voice cloning, multiple languages, and various voice options.
File format conversion and transformation CLI between images, PDFs, documents, CSV, and data formats.
Generate docx with customizable options
Creates .implementation scaffold for project development tracking. Run at the start of any project to set up structured folders for plans, todos, audits, architecture, and documentation.
Parse CSV files into structured JSON with delimiter auto-detection, header handling, common encoding support, and streaming reads for large files.
Creates .implementation scaffold for project development tracking. Run at the start of any project to set up structured folders for plans, todos, audits, architecture, and documentation.
Scan repo for all changes, group them into logical commits, push to GitHub, and optionally create a pull request. Only creates a PR when the user explicitly asks for one.
Parse XLS and XLSX workbooks into structured JSON with sheet metadata, named ranges, and formatted cell snapshots.
Scan repo for all changes, group them into logical commits with conventional messages, and push to GitHub. Use when the user says "commit", "push", or invokes /commit. Does NOT create a pull request.
Parse CSV files into structured JSON with delimiter auto-detection, header handling, common encoding support, and streaming reads for large files.
Analyze an image from a local path or URL with Claude vision. Supports prompt-controlled description, OCR, object counting, and brand/visual extraction.
Generate sound effects using AI models (Minimax)
# siteanalyze Analyze any website's design system — detects shadcn/ui, Tailwind, extracts colors, typography, and components via Playwright + Claude Vision. ## Usage ```bash siteanalyze <url> ``` ## What It Does - Navigates to the target URL using Playwright - Takes a screenshot and analyzes it with Claude Vision - Detects UI framework (shadcn/ui, Tailwind CSS, etc.) - Extracts color palette, typography scale, and component patterns - Outputs an open-styles compatible design profile ## Out
Instant data science insights for CSV and JSON files with statistical summaries, quality audits, and trend detection
Create logical commits from all changes, push to a new branch, and open a pull request on GitHub. Groups related changes into separate commits with conventional commit messages. Use when you want to submit changes for review via PR instead of pushing directly to main.
Generate high-quality PDF documents from markdown, HTML, or templates
Generate videos using AI providers like Google Veo 3.1, OpenAI Sora, and Runway. Supports text-to-video generation with professional cinematography controls.
Generate high-quality articles using parallel AI agents. Supports research, writing, and optional cover image generation. Write single articles or batch process multiple topics with configurable parallelism.
Transcribe audio and video files using ElevenLabs Scribe, OpenAI Whisper, or Google Gemini. Supports automatic chunking for large files, speaker diarization, timestamps, and multiple output formats (text, SRT, VTT, JSON).
Scan repo for all changes, group them into logical commits, push to GitHub, and optionally create a pull request. Only creates a PR when the user explicitly asks for one.
Create Claude Code hooks with standardized structure. Generates complete hook scaffolds with setup commands, logging, and Claude config integration. Just run `hook` to create a new hook template.
Search domain availability and suggestions via GoDaddy API
# skill-deploy ## Description Deployment automation skill for EC2 instances. Automates git pull, service restart, and health checks for configured hosts. ## Category DevOps / Deployment / Automation ## Commands ### deploy Deploy to one or more hosts with git pull, service restart, and health check. ```bash bun run src/index.ts deploy <host...> [options] ``` Options: - `--all` - Deploy to all configured hosts - `--parallel, -p` - Deploy to multiple hosts in parallel - `--skip-health` - Sk
Interact with the open-monitor MCP — check machine health, list processes, kill memory hogs, run doctor, manage cron jobs, trigger cache cleanup
Generate Excel spreadsheets with tables, formulas, multiple sheets, styling, and optional AI-generated data.