SkillsTV Live

SkillsTV Live

By Chris ShankuTechnology
Download on the App Store

SkillsTV Live episodes

  • We Built a Podcast Orchestrator (And It Failed Live)

    Chris and Sash open Claude Code live and run the two commands that ship this show. Chris kicks off /turnover against the previous week's recording at the top of the segment - on stream, while everything else is happening - and then walks through what's actually inside the orchestration. The episode is the messy version on purpose: a live demo with the artifacts visible, errors visible, and the human-in-the-loop checkpoints built in.

    The two skills are /episode and /turnover. /episode scaffolds next week from a topic - title, tagline, description, LinkedIn social card, OBS overlay, episode page, CouchDB record, homepage rebuild. Mid-show Chris uses it to create EP.06 "The Orchestrator Method" with Sash, which becomes the teaser for next week. /turnover is the orchestrator skill: it calls seven sub-skills (wrap, nextup, deploy, upload, deploy, promote, debrief) sequentially, each with its own job - whisper transcription, page updates, branch deploys, YouTube upload with auto-chapters, LinkedIn draft, Telegram debrief.

    The live demo trips on a real error - main and dev had diverged because EP.05 was created without turning over EP.04 first, and --ff-only refused. Chris flags it on stream: "we're getting some errors. We're getting some human resolve stuff." That's the show. The whole conversation pivots to approval gates and how trust with AI evolves over time. Sash frames the orchestrator method as defining the outcome, breaking it into tasks, telling Claude how each task should be accomplished, then putting humans in the loop at the right places. EP.06 will cover the five principles in detail.

    Key takeaways:

    • Build your orchestrator skill from sub-skills, not one giant prompt. Iteration is the path: start with one thing, break it apart when it misses the mark, then chain the parts.
    • Approval gates are not bugs - they're trust calibration. Start with 'draft this for me', graduate to 'I took a stab, look it over', end at 'I did it, here it is.'
    • 'It's just one of us.' Treat AI like a teammate that forgets things and gets overwhelmed. Don't expect perfection; build the recovery loop.
    • Skills live in the same repo as the code they ship. One git pull and either host can run /turnover on their machine.
    • The messy version is the version. Errors on stream are the show, not a failure of it.

    Watch the video version on YouTube · Full show notes, transcript + takeaways

    19 min
  • Is This The End Of Boring Admin Work? Claude Cowork Demo

    Sash demos Claude Cowork - the same engine as Claude Code, but desktop-only and task-based instead of chat-based. The pitch: knowledge workers in non-technical roles get an agentic surface for the work they actually do every day. Cowork runs sandboxed on your Mac, takes a folder for context, plans the task, and executes. Chris streams in from London on an iPad to underline the point that the show ships from anywhere with tmux.

    The live demo runs an "itemize receipts and fill expense sheet" workflow. Cowork picks up 15 PDF receipts, extracts them, and writes the data into the expense template. The conversation pivots to skill packaging - if everyone in your org has the same expense form, you can wrap the workflow as a skill and hand it around. That leads into a closer look at skill anatomy: the markdown spec, the scripts subfolder for Python helpers, the resources/examples that ground the skill in real reference material.

    The episode closes on a 90/10 reframe of "human in the loop" - the agent does most of the work, and the human shows up for the final shaping pass. Sash points at Granola for notes, and Chris flags that he's been spending too much time inside the terminal when Cowork could carry his personal-productivity load. Next week's setup: the two commands that ship this show.

    Key takeaways:

    • Try Claude Cowork for non-coding work: expense reports, document drafting, folder reorgs - it's the agentic surface for knowledge workers who don't live in a terminal.
    • Skills are packagable. If a Cowork workflow works for you, the same .md spec + scripts/ folder + resources/ folder ships to your team.
    • Skill quality is in the context. Examples and reference docs in resources/ are what make a skill reliable, not just a sharp prompt.
    • The 'last 10%' is the human pass. Let the agent do the bulk; show up to shape, edit, and approve.
    • You can stream this show from anywhere - iPad over Tailscale + tmux works fine. The setup is portable on purpose.

    Watch the video version on YouTube · Full show notes, transcript + takeaways

    18 min
  • I Built A Better Research Engine Than Perplexity

    Sash walks through a multi-agent deep research workflow he built inside Claude Code after getting burned by context-bloat and hallucinations in Perplexity and ChatGPT deep research. The system splits the job across four named agents: Oracle plans the research and decomposes a topic into angles, Hermes agents run one-per-angle in parallel to collect raw data points (with web search plus EXA semantic search), Athena applies the academic CRAAP framework - currency, relevance, authority, accuracy, purpose - to grade every data point, and Scribe (the only Opus agent in the chain) writes the final 20-30 page synthesized report.

    The live demo researches AI agent adoption in knowledge work. While Hermes fans out five parallel agents, Sash and Chris dig into the model-selection tradeoffs he learned the hard way: Haiku was too weak as a research agent, Opus as the analyst burned tokens without beating Sonnet, so only the final writer stays on Opus. A concrete data point surfaces mid-run - Microsoft Copilot sits at 15-16M paid seats but only 35.8% active usage, meaning 64% of purchased seats are dormant. Education is the number one enterprise response to AI right now, not restructuring.

    Chris connects the workflow to his own future-thinker agent experiment - a weekly check against obsolescence risk before building anything new - and Sash confirms the framework generalizes to market, strategy, or any research where the data exists on the web. The honest caveat: this workflow is token-heavy and has to be used strategically, not casually.

    Key takeaways:

    • Split deep research into discrete agents (plan / fetch / evaluate / write) so each context window stays clean - that alone cuts hallucinations dramatically.
    • Pick models per-agent role, not per-project. Sonnet is good enough for planning, research, and analysis; reserve Opus for the final writer where prose quality matters.
    • Try Sonnet 4.6 before reaching for Opus 4.5 - benchmarks are comparable at roughly half the token cost.
    • Grade sources with an explicit rubric (CRAAP: currency, relevance, authority, accuracy, purpose) so only high-quality data points make it into the final report.
    • Deep research is a strategic tool, not a daily-driver. It burns tokens - run it when you need depth, not when a web search would do.

    Watch the video version on YouTube · Full show notes, transcript + takeaways

    18 min
  • We Built Our AI Systems Apart. They Came Out Identical.

    # EP.001 - The Tools We Actually Use

    ## Show Notes

    Chris Shanku and Sash Mohapatra kicked off Human in the Loop by doing what the show is built around: opening their actual systems and walking through them live. No slides, no pitch decks, no sanitized demos. Just the real thing.

    Sash showed Nuro - his Claude Code-based personal assistant that runs on his Mac. CLAUDE.md as a master identity file, Claude-managed memory, domain-organized working files, and real integrations: email, Granola for meeting notes, n8n for automations, Perplexity and X for search. The newsletter automation alone was worth the episode - Nuro drafts his Sunday edition on Saturday night and posts it to Slack for review. The whole thing runs while he is asleep.

    Chris showed TheGrove - a personal AI operating system running on a Mac Mini. Organized into domains covering everything from client work to life admin to co-parenting. A full SDLC workflow baked in: scope, plan, build, test, close. Specialized agents for front-end, back-end, design, red team breaking, and fresh-eyes review. Every sprint auto-documented and pushed to GitHub. What made this interesting was the reveal: Sash and Chris had never seen each other's systems before going live. They independently landed on nearly identical architectures - central agent identity, domain organization, specialized sub-agents, skills in Git. That was not planned. That was the whole point of the episode.

    ## Takeaways

    - Structure your AI system around domains that match how your life actually works, not how a productivity book says it should - Use a CLAUDE.md or equivalent identity file as your central agent's source of truth - it holds context everything else inherits from - Automate the review step, not just the output - Nuro writes the newsletter, but Sash reviews it in Slack before it sends - Put your skills and working files in Git - it keeps multiple machines in sync and gives you a recoverable history of how your system evolved - Build specialized agents for distinct roles rather than asking one agent to do everything; a red team agent with no context will catch what a helpful agent never will

    ## Key Moments

    - 05:20 - Sash walks through the Nuro system architecture: CLAUDE.md, memory files, project organization - 07:30 - Nuro's newsletter automation - Saturday night draft, Slack review, Sunday send - 09:50 - Chris shows TheGrove, starting with the domain structure and the Mac Mini setup - 11:30 - The SDLC workflow and agent roster, including the red team breaker agent - 13:30 - Neither host had previewed the other's system - they compare them live and find near-identical designs

    Key takeaways:

    • Structure your AI system around domains that match how your life actually works
    • Use a CLAUDE.md or equivalent identity file as your central agent source of truth
    • Automate the review step, not just the output
    • Put your skills and working files in Git for sync and history
    • Build specialized agents for distinct roles rather than one agent for everything

    Watch the video version on YouTube · Full show notes, transcript + takeaways

    17 min

About SkillsTV Live

From the publisher's feed

Learn AI skills every week on SkillsTV Live, a live show that demos Claude Skills, agent skills, and MCP with real tools - no slides, no hype. Hosted by Chris Shanku and Sash Mohapatra. Upgrading…