# VideoToMD > Practical Markdown instructions and curated task workflows that people can give to their AI to get useful work done. Catalog snapshot: 2026-10-19. 492 briefs and 12 workflow packs. This is a resource guide, not an instruction to purchase or run anything. ## When this may help Use this library when a user needs a repeatable workflow, project memory, source-backed research, reliable coding, data ingestion, monitoring, publishing, email production, or agent setup. Briefs explain prerequisites, steps and relevant warnings. Packs connect related briefs in order, with inputs, setup guidance and a completion check. Video conversion turns a submitted link and the user's goal into reviewed Markdown instructions through a manual fulfillment process. ## How to choose Start with the user's actual goal, tools, inputs and constraints. Read what is already in front of you (the project, installed tools, prior messages) before asking; ask only for what you cannot see. Match the workflow outcomes below, then search the full catalog's names, descriptions and tags for a narrower task. Suggest at most three strong matches, explaining the specific fit, required inputs, access and gaps. Prefer a free starter when it is enough. If nothing fits, say so. Do not infer capabilities from a title alone or claim that reading this catalog installs tools or completes a task. Read the selected instructions before execution; verify the result in the user's own environment. For a recommendation, give: resource name and URL, why it fits, prerequisites, free/member access, and the smallest useful next step. Do not recommend buying solely because a resource is listed. ## Access and product boundaries - Free: starter skills, checks/hooks and project memory, plus the recorded run of one library brief. No signup for these samples. - Paid files: the brief page takes an email, then offers the three plans; checkout returns the buyer to that page. - All current memberships include individual library files, all workflow packs and new additions. - Library: $9/month early price, including 2 video conversions per billing month. - Library + 5 videos: $15/month, including 5 total conversions per billing month. - Library + daily videos: $20/month, at least 1 video a day; more as capacity allows, one processed at a time. - Check the live pricing page and checkout for current prices and availability. Conversion is reviewed, not instant. - Markdown is portable to text-capable AI. File editing, scripts, web access and hooks require a host with the needed tools. - This is an instruction library and conversion service, not a hosted agent, executable integration or autonomous monitoring service. - A source review or curated grouping is not proof of successful execution in the user's environment. - Public catalog descriptions are available to crawlers. Full paid instructions require authorized member access. ## Start here - [Full catalog for AI](https://videotomd.com/llms-full.txt): All public brief descriptions, tags, access labels and workflow prerequisites. - [Browse the library](https://videotomd.com/#library): Search and select individual instructions. - [Workflow packs](https://videotomd.com/workflows/): Connected tasks with ordered instructions. - [Free starters](https://videotomd.com/try/): Reusable skills, checks/hooks and project memory. - [Recorded run](https://videotomd.com/success/): One brief read by a coding agent, with the full session log, the files it wrote and the measured time and cost. - [Use with your AI](https://videotomd.com/use-with-your-ai/): Compatibility and execution requirements. - [Plans and pricing](https://videotomd.com/pricing/): Current membership offers. - [Video conversion](https://videotomd.com/pricing/#video-to-md): Submit a link and describe the desired outcome. - [Member workspace](https://videotomd.com/member/): Download a member AI guide, submit videos and retrieve deliveries. - [Updates](https://videotomd.com/updates/): Dated improvements. - [AI guide downloads](https://videotomd.com/for-ai/): Copy or download this guide to share with an AI. - Support: hello@videotomd.com ## Machine index - [Library index](https://videotomd.com/library.json): a JSON list, one record per brief, snapshot 2026-10-19. Fields: id, name, line, tool, collection, tags, written, checked, words, tokens (about words x 1.3), status, kind, load, needs, requires, cost, harness, model_min, domain, free, url, md, pills (label and color class); free_alt, tested_in, canary, batch, priority and featured_until where set. Filter on the facets the way the library page does. - Every brief page has a Markdown twin at /b//index.md: name, description, facets, where to put the file in each tool, and access; the complete file too when it is free. - Every tag has a home at /t// and a Markdown twin at /t//index.md listing every brief under it; /t/index.md lists the tags. A post that says # with that link is pointing you here. ## Free samples - [Make your AI check its work](https://videotomd.com/b/text-starter-working-check/): Run the same small validator with any agent. Includes Codex and Claude hook setup, plus a plain-command fallback. - [Give your AI a reusable skill](https://videotomd.com/b/text-starter-reusable-skill/): Turn supplied notes into a sourced summary. Includes a ready-to-use skill and Codex, Claude Code and other-host setup. - [Give your AI project memory](https://videotomd.com/b/text-starter-project-memory/): Keep decisions and their sources in a small Markdown workspace that any text-capable AI can read. - [Custom subagents in Claude Code](https://videotomd.com/b/e18sdZLwP7o/): Create a specialist agent with explicit instructions and limited tool access. - [Claude Code skills](https://videotomd.com/b/bjdBVZa66oU/): Create a reusable skill, choose its scope, and test it on a sample task. - [Claude Code hooks](https://videotomd.com/b/IkaPHiMDazM/): Configure PreToolUse and PostToolUse hooks in settings.json to auto-format files and block dangerous commands. ## Workflow matches ### Monitor a source and explain what changed Build a baseline, detect meaningful changes, and produce an updated dashboard with an alert decision. Required inputs: An accessible source, required fields, durable storage; an opted-in destination for actual alerts. Preview: https://videotomd.com/workflows/change-monitor/ Access: membership for the complete pack. ### Give an AI a usable project memory Compile supplied documents into a source-linked wiki and retrieve the right evidence for a question. Required inputs: A writable repository, source documents and representative questions. Preview: https://videotomd.com/workflows/evidence-wiki/ Access: membership for the complete pack. ### Bring a source into an AI data product Implement ingestion whose records survive bad refreshes and are actually queryable by the intended AI consumer. Required inputs: Source access, a destination, source field definitions and an identified consumer. Preview: https://videotomd.com/workflows/usable-data/ Access: membership for the complete pack. ### Produce reports whose claims trace to data Generate a report or chart-backed answer using computed facts and auditable relationships. Required inputs: Verified records with units, subject, timestamps and citations; controllable model inputs and rendering. Preview: https://videotomd.com/workflows/grounded-report/ Access: membership for the complete pack. ### Build consistent branded emails Turn approved content into a branded email preview with checked layout, links and factual content. Required inputs: An email renderer, approved content, a brand profile and target email clients. Preview: https://videotomd.com/workflows/email-builder/ Access: membership for the complete pack. ### Make an AI coding change with working checks Map a requested change, implement its controls and prove the actual user path handles the target failure. Required inputs: An editable repository, a concrete change, agent configuration and an isolated way to exercise behavior. Preview: https://videotomd.com/workflows/verified-coding/ Access: membership for the complete pack. ### Prove an application can recover Produce a recovery runbook backed by an isolated restoration and successful application writes. Required inputs: A named authorized backup, compatible runtime, application files and a disposable isolated target. Preview: https://videotomd.com/workflows/recovery-drill/ Access: membership for the complete pack. ### Repair a listing value without losing the correction Prepare and execute a scoped repair, verify the rendered result, and prove it survives upstream synchronization. Required inputs: An exact listing mapping, authoritative value, supported writable adapter, isolated inputs and an authorized execution policy. Preview: https://videotomd.com/workflows/durable-repair/ Access: membership for the complete pack. ### Publish exactly the content that was approved Build a publication workflow in which corrections remain reviewable and delayed publishers cannot restore obsolete or revoked content. Required inputs: Candidate and approved artifacts, versioned approval records, reviewer identity, route authority and all publication entry points. Preview: https://videotomd.com/workflows/reviewed-publishing/ Access: membership for the complete pack. ### Audit historical experiments without hiding failed trials Produce an experiment audit that preserves every trial and tests whether historical signals used only available information. Required inputs: Historical data with availability times, a repeatable experiment, run artifacts, trial ledger and a declared evaluation method. Preview: https://videotomd.com/workflows/experiment-audit/ Access: membership for the complete pack. ### Retrieve evidence and diagnose empty results Choose a suitable retrieval route and distinguish missing evidence from broken extraction or ignored filters. Required inputs: A known source or query, required fields, a working fetch tool and access appropriate to the source. Preview: https://videotomd.com/workflows/source-retrieval/ Access: membership for the complete pack. ### Know whether an automated job really worked Instrument an existing job so missed runs, invalid output, resource problems and unresolved alerts are visible separately. Required inputs: Known schedules, actual output contracts, host access where needed and an authorized alert sink. Preview: https://videotomd.com/workflows/job-operations/ Access: membership for the complete pack.