Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Someone built a GitHub repo because “act like a senior engineer” isn’t an engineering process. 👀 Matt Pocock’s Skills gives Claude Code a workflow: question the idea, write the spec, plan the tasks, build with tests, and review the result. Putting it to work on document sharing in ThinkFolio.... show more

Codename Poshan

17,600 subscribers

10,300 views • 11 hours ago •via TikTok

Education Science & Technology #claudecode #mattpocock #agentskills #aicoding #devtools

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

garry tan just open-sourced a 128k-star repo that basically turns claude code into your entire engineering org it’s called gstack: 23 tools that break a single claude workflow into product, engineering, qa, review, and release lanes > /office-hours turns a rough idea into a real product spec > /plan-ceo-review + /plan-eng-review try to tear the plan apart before any code ships > /review hunts for bugs and patches them > /qa spins up an actual browser and tests the app end to end > /ship runs the final checks and pushes the pr think → plan → build → review → test → ship → reflect garry says this setup let him ship 3 production services and 40+ features in 60 days while still running yc full-time one developer sets the compass. the repo runs the loop.

garry tan just open-sourced a 128k-star repo that basically turns claude code into your entire engineering org it’s called gstack: 23 tools that break a single claude workflow into product, engineering, qa, review, and release lanes > /office-hours turns a rough idea into a real product spec > /plan-ceo-review + /plan-eng-review try to tear the plan apart before any code ships > /review hunts for bugs and patches them > /qa spins up an actual browser and tests the app end to end > /ship runs the final checks and pushes the pr think → plan → build → review → test → ship → reflect garry says this setup let him ship 3 production services and 40+ features in 60 days while still running yc full-time one developer sets the compass. the repo runs the loop.

CyrilXBT

20,997 views • 3 months ago

this is f**king insane. someone built a free Claude skills library that gives you hundreds of tools, agents, and expert personas in one place. the GitHub repo already has 26k+ stars. it gives you: → 305 Python tools with zero pip installs → skills for executing specific tasks → agents for handling different workflows → personas like senior architect, CTO, and security auditor → one command to convert the library to 11 different platforms and it's completely free. MIT licensed. with the right setup, Claude can take on a lot of the work you’d normally need different tools or people for. i actually broke down how to build a workflow around this idea in my article below. save this now.

this is f**king insane. someone built a free Claude skills library that gives you hundreds of tools, agents, and expert personas in one place. the GitHub repo already has 26k+ stars. it gives you: → 305 Python tools with zero pip installs → skills for executing specific tasks → agents for handling different workflows → personas like senior architect, CTO, and security auditor → one command to convert the library to 11 different platforms and it's completely free. MIT licensed. with the right setup, Claude can take on a lot of the work you’d normally need different tools or people for. i actually broke down how to build a workflow around this idea in my article below. save this now.

MIKE

96,627 views • 1 month ago

THIS IS F**KING INSANE. someone just built a free Claude skills library that gives you thousands of tools, agents, and personas all in one place. the GitHub repo already has 47,000+ stars. it gives you: → 290+ Python tools with zero pip installs → skills for executing most tasks → agents for handling different workflows → personas like senior architect, CTO, and security auditor → one command to convert the library to 11 different platforms and it's totally free. licensed. with the right setup, Claude can take on a lot of the work you’d normally need different tools or people for. i actually broke down how to build a workflow around this idea in my article below. save this, you will need it

THIS IS F**KING INSANE. someone just built a free Claude skills library that gives you thousands of tools, agents, and personas all in one place. the GitHub repo already has 47,000+ stars. it gives you: → 290+ Python tools with zero pip installs → skills for executing most tasks → agents for handling different workflows → personas like senior architect, CTO, and security auditor → one command to convert the library to 11 different platforms and it's totally free. licensed. with the right setup, Claude can take on a lot of the work you’d normally need different tools or people for. i actually broke down how to build a workflow around this idea in my article below. save this, you will need it

Innopro

34,290 views • 1 month ago

got Claude Agent SDK working in Cloudflare Developers containers and built my own code fixer agent, check it out!👇 uses the github mcp/git cli/skills to clone the repo, understand, make the fix, and open a pr when done. planning on more agents focused on non-code tasks 👀

got Claude Agent SDK working in Cloudflare Developers containers and built my own code fixer agent, check it out!👇 uses the github mcp/git cli/skills to clone the repo, understand, make the fix, and open a pr when done. planning on more agents focused on non-code tasks 👀

Thomas Gauvin

18,454 views • 10 months ago

My whole company runs on skills I bundled into a GitHub repo. Here's how to build the same thing for your team: - Put your skills in a GitHub repo - Get Claude to write the couple of JSON files that make it readable as a plugin - In Claude Code, type /plugin, go to marketplaces, add marketplace, paste your repo URL - Split the plugins by department, so your copywriter isn't installing the finance skills It works in Codex too. I've got the same team skills installed there and I use them the same way. Now when I build something like my Notion formatting skill, I add it to the repo and it lands on everyone's Claude and Codex. If someone wrecks a skill, we roll it back to an older version. The key is enabling auto-update, so when someone improves a skill everyone benefits. I don't have a clue how the JSON works. I got Claude to set the whole thing up for me. Start with one skill and before you know it your whole team will be AI pilled.

My whole company runs on skills I bundled into a GitHub repo. Here's how to build the same thing for your team: - Put your skills in a GitHub repo - Get Claude to write the couple of JSON files that make it readable as a plugin - In Claude Code, type /plugin, go to marketplaces, add marketplace, paste your repo URL - Split the plugins by department, so your copywriter isn't installing the finance skills It works in Codex too. I've got the same team skills installed there and I use them the same way. Now when I build something like my Notion formatting skill, I add it to the repo and it lands on everyone's Claude and Codex. If someone wrecks a skill, we roll it back to an older version. The key is enabling auto-update, so when someone improves a skill everyone benefits. I don't have a clue how the JSON works. I got Claude to set the whole thing up for me. Start with one skill and before you know it your whole team will be AI pilled.

The Startup Ideas Podcast (SIP) 🧃

19,962 views • 2 months ago

You can now use Claude Code and GitHub CLI directly inside Perplexity Computer. We gave it an open issue on Openclaw. Computer: → Forked the repo → Wrote a plan to fix the bug → Opened Claude Code and implemented it → Submitted a PR via GitHub CLI

You can now use Claude Code and GitHub CLI directly inside Perplexity Computer. We gave it an open issue on Openclaw. Computer: → Forked the repo → Wrote a plan to fix the bug → Opened Claude Code and implemented it → Submitted a PR via GitHub CLI

Computer

417,250 views • 8 months ago

I asked GitHub Copilot with Work IQ to compare my PowerToys search spec in SharePoint to the implementation on the GitHub repo and it worked seamlessly. Being able to pair work context with code in the repo using Copilot is an absolute game changer for development💥💥💥

I asked GitHub Copilot with Work IQ to compare my PowerToys search spec in SharePoint to the implementation on the GitHub repo and it worked seamlessly. Being able to pair work context with code in the repo using Copilot is an absolute game changer for development💥💥💥

Kayla Cinnamon ☕️

41,234 views • 9 months ago

AI coding isn't about writing code faster. it's about designing a workflow where your agent can reliably ship the code for you. Matt Pocock's full workshop breaks down the entire process : • 00:14 - The thesis of AI engineering • 00:12:45 - Research and prototype ambiguous requirements • 00:22:10 - Stress-test the idea and write the PRD • 00:35:50 - Slice work into thin tracer-bullet issues • 00:48:15 - Let AI agents implement with TDD • 01:18:45 - Deploy, monitor, and review the result • 01:28:10 - Design codebases agents actually work well in the key shift is simple: Vague Brief → PRD → Vertical Slices → AI Agent → Tests → Review → Production once the workflow is right, autonomous coding stops being a gimmick and starts becoming an engineering system. watch the video then read Andrew Ng's guide on AI Engineering Skills Map.

AI coding isn't about writing code faster. it's about designing a workflow where your agent can reliably ship the code for you. Matt Pocock's full workshop breaks down the entire process : • 00:14 - The thesis of AI engineering • 00:12:45 - Research and prototype ambiguous requirements • 00:22:10 - Stress-test the idea and write the PRD • 00:35:50 - Slice work into thin tracer-bullet issues • 00:48:15 - Let AI agents implement with TDD • 01:18:45 - Deploy, monitor, and review the result • 01:28:10 - Design codebases agents actually work well in the key shift is simple: Vague Brief → PRD → Vertical Slices → AI Agent → Tests → Review → Production once the workflow is right, autonomous coding stops being a gimmick and starts becoming an engineering system. watch the video then read Andrew Ng's guide on AI Engineering Skills Map.

Dami-Defi

13,962 views • 2 months ago

How to install a Claude skill from GitHub — even if you have no idea how GitHub works. Download the repo, let Claude check the files for risks, customise the skill around how you actually work, then package it as a Claude-ready ZIP and upload it. GitHub looks technical. This part really isn’t. Save this for the next Claude skill someone sends you. #claude #claudeskills #github #aitools #claudetips

How to install a Claude skill from GitHub — even if you have no idea how GitHub works. Download the repo, let Claude check the files for risks, customise the skill around how you actually work, then package it as a Claude-ready ZIP and upload it. GitHub looks technical. This part really isn’t. Save this for the next Claude skill someone sends you. #claude #claudeskills #github #aitools #claudetips

The AI Impact | AI Workflows

23,100 views • 2 months ago

BREAKING 🚨: Early look at Claude Task Mode agent workflow. What do we know so far? - Claude Tasks will operate various Skills and MCPs to achieve the goal. - Claude will ask clarifying questions before the execution or skip it after a timeout. - Claude will generate an action plan for complex tasks. - Users will be able to modify the plan on the fly or send additional context to the workflow while Claude is working. - Generated artefacts can be previewed in a separate panel. - All artefacts, Skills, scripts and generated files will be stored in the working files directory. - And more details in the post 👀 NotebookLM on Skills 🔥

BREAKING 🚨: Early look at Claude Task Mode agent workflow. What do we know so far? - Claude Tasks will operate various Skills and MCPs to achieve the goal. - Claude will ask clarifying questions before the execution or skip it after a timeout. - Claude will generate an action plan for complex tasks. - Users will be able to modify the plan on the fly or send additional context to the workflow while Claude is working. - Generated artefacts can be previewed in a separate panel. - All artefacts, Skills, scripts and generated files will be stored in the working files directory. - And more details in the post 👀 NotebookLM on Skills 🔥

🚨 AI News | TestingCatalog

77,586 views • 10 months ago

Anthropic engineer, Addy Osmani (ex-Google): "Google hired me at $500K–$1.2M a year because I know how to make AI agents write code that doesn’t break." In this 41-minute workshop he shows exactly how to build that system from scratch. Prompts → Agent Skills → Harness → Agents That Ship Without You step 1 → Refine the idea - drop in a vague thought, the agent interviews you and comes back with 3 directions step 2 → Write the spec - success criteria, stack and open questions locked before a single line of code step 3 → Plan in small tasks - each one gets acceptance criteria and a list of files it's allowed to touch step 4 → Build test-first - red to green, slice by slice, so nothing that already works breaks step 5 → Verify and review - the agent opens the app in a browser, checks security and simplifies its own code He open-sourced all 24 skills, and the repo is close to 100K stars Google calls this "agentic engineering" Most people spend weeks building this by hand You don't have to Bookmark it and watch it tonight Then read the full Opus 5.5 harness engineering guide below ↓

Anthropic engineer, Addy Osmani (ex-Google): "Google hired me at $500K–$1.2M a year because I know how to make AI agents write code that doesn’t break." In this 41-minute workshop he shows exactly how to build that system from scratch. Prompts → Agent Skills → Harness → Agents That Ship Without You step 1 → Refine the idea - drop in a vague thought, the agent interviews you and comes back with 3 directions step 2 → Write the spec - success criteria, stack and open questions locked before a single line of code step 3 → Plan in small tasks - each one gets acceptance criteria and a list of files it's allowed to touch step 4 → Build test-first - red to green, slice by slice, so nothing that already works breaks step 5 → Verify and review - the agent opens the app in a browser, checks security and simplifies its own code He open-sourced all 24 skills, and the repo is close to 100K stars Google calls this "agentic engineering" Most people spend weeks building this by hand You don't have to Bookmark it and watch it tonight Then read the full Opus 5.5 harness engineering guide below ↓

shikamaru

196,860 views • 3 days ago

SPEC IS BECOMING THE PRODUCT An Anthropic engineer gave Claude a spec, pointed it to an Asana board and left for the weekend. Claude broke it into tickets and spun up a team of agents. The agents started picking up tasks on their own. No one told them to. They just did.

SPEC IS BECOMING THE PRODUCT An Anthropic engineer gave Claude a spec, pointed it to an Asana board and left for the weekend. Claude broke it into tickets and spun up a team of agents. The agents started picking up tasks on their own. No one told them to. They just did.

Shubham Saboo

285,777 views • 8 months ago

Everyone demos Claude Code the same way plan, review, accept The engineer who built it doesn't work like that anymore "I don't prompt Claude I write loops that prompt Claude for me" 5–10 sessions at once sub-agents by the hundreds phone, not laptop You're one level behind the guy who built the tool Full breakdown below

Everyone demos Claude Code the same way plan, review, accept The engineer who built it doesn't work like that anymore "I don't prompt Claude I write loops that prompt Claude for me" 5–10 sessions at once sub-agents by the hundreds phone, not laptop You're one level behind the guy who built the tool Full breakdown below

Skaly_Bull

30,426 views • 3 months ago

GStack is an open-source toolkit built by YC President & CEO Garry Tan that turns Claude Code into an AI engineering team — with skills for office hours, design, code review, QA, and browser testing. In this video, Garry walks through how GStack works, starting with Office Hours, a skill modeled after real YC partner sessions that pressure-tests your idea before you write a line of code. He demos it live, going from idea through adversarial review, design mockups, and automated QA in a single session.

GStack is an open-source toolkit built by YC President & CEO Garry Tan that turns Claude Code into an AI engineering team — with skills for office hours, design, code review, QA, and browser testing. In this video, Garry walks through how GStack works, starting with Office Hours, a skill modeled after real YC partner sessions that pressure-tests your idea before you write a line of code. He demos it live, going from idea through adversarial review, design mockups, and automated QA in a single session.

Y Combinator

926,643 views • 6 months ago

Your team writes the spec in Notion. You build with Codex. Notion MCP brings them together. Try it: ask Codex to read the spec, find where the code diverged, and write those gaps back into the page. The work happens in the repo. Then writes the update back to Notion.

Your team writes the spec in Notion. You build with Codex. Notion MCP brings them together. Try it: ask Codex to read the spec, find where the code diverged, and write those gaps back into the page. The work happens in the repo. Then writes the update back to Notion.

Notion

54,719 views • 3 months ago

New course: Spec-Driven Development with Coding Agents, built in partnership with JetBrains, and taught by Paul Everitt | @pauleveritt@fosstodon.org. Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way. A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity. Skills you'll gain: - Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start - Plan, implement, and validate features in iterative loops using a spec as your agent's guide - Apply the same repeatable workflow to both new and legacy codebases - Package your workflow into a portable agent skill that works across agents and IDEs Join and write specs that keep your coding agent on track!

New course: Spec-Driven Development with Coding Agents, built in partnership with JetBrains, and taught by Paul Everitt | @[email protected]. Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way. A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity. Skills you'll gain: - Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start - Plan, implement, and validate features in iterative loops using a spec as your agent's guide - Apply the same repeatable workflow to both new and legacy codebases - Package your workflow into a portable agent skill that works across agents and IDEs Join and write specs that keep your coding agent on track!

Andrew Ng

467,452 views • 7 months ago

mattpocock/skills v1.1 is out! - /wayfinder helps you plan more ambitious work than ever - /to-spec and /to-tickets replace /to-prd and /to-issues - /implement + /code-review complete the whole lifecycle - /research and /prototype help support wayfinder, or can be used independently - Crucial fixes to /grill-me Run npx skills@latest add mattpocock/skills to update!

mattpocock/skills v1.1 is out! - /wayfinder helps you plan more ambitious work than ever - /to-spec and /to-tickets replace /to-prd and /to-issues - /implement + /code-review complete the whole lifecycle - /research and /prototype help support wayfinder, or can be used independently - Crucial fixes to /grill-me Run npx skills@latest add mattpocock/skills to update!

Matt Pocock

257,257 views • 4 months ago

We're open-sourcing CesiumJS Skills. Try them out to give your AI coding assistants deep knowledge of the CesiumJS API so they can help you write correct, performant geospatial code from the start. #OpenSource #AI #GitHub #ClaudeCode #AgentSkills

We're open-sourcing CesiumJS Skills. Try them out to give your AI coding assistants deep knowledge of the CesiumJS API so they can help you write correct, performant geospatial code from the start. #OpenSource #AI #GitHub #ClaudeCode #AgentSkills

Cesium

12,740 views • 5 months ago

Claude Code built roughly 95% of this procedural pixel creature engine from a single detailed prompt. No premade sprites. No AI-generated textures. Just Godot, C#, and code generating body plans, rigs, animations, mutations, and pixel art across 9 creature families. The prompt wasn’t a vibe. It was an engineering spec. Check the repo in the comments.

Claude Code built roughly 95% of this procedural pixel creature engine from a single detailed prompt. No premade sprites. No AI-generated textures. Just Godot, C#, and code generating body plans, rigs, animations, mutations, and pixel art across 9 creature families. The prompt wasn’t a vibe. It was an engineering spec. Check the repo in the comments.

Jurly

30,659 views • 1 month ago

Opus 5.5 + Jev make this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 claude-code-router ▸ → routes every request to the model you pick, Opus only where it counts 02 litellm ▸ → one gateway in front of 100+ models, spend tracked per call 03 spec-kit ▸ → spec first, plan second, code last 04 claude-task-master ▸ → your PRD becomes tasks the agent works through one by one 05 superpowers ▸ → a full dev method built from skills: plan, test, then call it done 06 skills ▸ → Anthropic's own skills, folders Claude loads only when the job needs them 07 graphiti ▸ → memory as a temporal knowledge graph, not a dump 08 langgraph ▸ → agents as graphs: state, branches, back edges 09 E2B ▸ → AI-written code runs in isolated cloud sandboxes, not on your machine 10 promptfoo ▸ → evals and red teaming before anything ships the architecture: route → spec → tasks → skills → memory → graph → sandbox → evals I'd split the stack like this: route: claude-code-router → litellm plan: spec-kit → claude-task-master work: superpowers → skills state: graphiti → langgraph safety: E2B → promptfoo Opus 5.5 plans and ships. the forks in between, which file, which tool, retry or stop, go to Jev everyone posts the model and the prompt pack the stack around it decides whether your agent is still running next week ⭣

Opus 5.5 + Jev make this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 claude-code-router ▸ → routes every request to the model you pick, Opus only where it counts 02 litellm ▸ → one gateway in front of 100+ models, spend tracked per call 03 spec-kit ▸ → spec first, plan second, code last 04 claude-task-master ▸ → your PRD becomes tasks the agent works through one by one 05 superpowers ▸ → a full dev method built from skills: plan, test, then call it done 06 skills ▸ → Anthropic's own skills, folders Claude loads only when the job needs them 07 graphiti ▸ → memory as a temporal knowledge graph, not a dump 08 langgraph ▸ → agents as graphs: state, branches, back edges 09 E2B ▸ → AI-written code runs in isolated cloud sandboxes, not on your machine 10 promptfoo ▸ → evals and red teaming before anything ships the architecture: route → spec → tasks → skills → memory → graph → sandbox → evals I'd split the stack like this: route: claude-code-router → litellm plan: spec-kit → claude-task-master work: superpowers → skills state: graphiti → langgraph safety: E2B → promptfoo Opus 5.5 plans and ships. the forks in between, which file, which tool, retry or stop, go to Jev everyone posts the model and the prompt pack the stack around it decides whether your agent is still running next week ⭣

Chen

35,223 views • 1 month ago