skills

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.

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.

Generate images using OpenAI, Minimax, or Gemini through the hosted Skills runtime with provider-cost pricing.

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.

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.

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 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.)

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 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.

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.

Generate speech and audio using OpenAI, Minimax, or Gemini through the hosted Skills runtime with provider-cost pricing.

Extract text and structured data from images and PDFs using OpenAI Vision

Generate music using Minimax or Gemini Lyria through the hosted Skills runtime with provider-cost pricing.

Generate videos using OpenAI Sora, Minimax Hailuo, Gemini Veo, or Seedance through the hosted Skills runtime with provider-cost pricing.

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 paid-ad copy, creative concepts, image prompts, audience angles, and test matrices.

Generate premium API documentation portals from OpenAPI specs, route lists, or examples.

Generate premium transcript packages with timestamps, summaries, show notes, clip suggestions, repurposing copy, captions, and manifest metadata.

Generate one or more SEO-ready blog article packages as hosted premium artifacts.

Generate premium brand kits with logo usage, palette, typography, brand voice, sample applications, Markdown guide, and PDF guide.

Generate hosted brand or product photo shoot sets

Generate premium contract review reports with clause summaries, risk register, negotiation points, redline-style suggestions, counterparty email draft, and manifest metadata.

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.

Public contract for domain purchase workflows through hosted or external registrar connectors.

Generate premium email campaigns with subject lines, preview text, body copy, segmentation notes, CTA variants, and HTML exports.

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 invoice reconciliation reports from invoice, payment, purchase order, or CSV/XLSX-style exports with matches, discrepancies, anomaly notes, summaries, and manifest metadata.

Generate premium landing page copy, wireframes, CTA maps, experiments, and preview artifacts.

Generate premium multi-variant logo packages with transparent PNG exports, vector-style SVGs, usage notes, and a manifest.

Generate a premium market research report with competitor, audience, pricing, source, Markdown, and PDF artifacts.

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 premium migration planning packs for framework, library, database, infrastructure, or architecture upgrades with risk matrix, checklist, rollout plan, and test strategy.

Generate hosted music album packages with 7, 14, or 21 songs

Generate premium static one-page website bundles with HTML, CSS, JavaScript, copy, section map, deploy notes, and manifest.

Read and extract text from multiple PDF files with page-range selection and parallel processing

Extract tables, forms, invoices, and semi-structured PDF content into CSV and JSON datasets through the hosted Skills runtime.