Every Claude Code Skill I Use to Drive My Entire Development Process
Cole Medin walks through his full AI-driven development system built as a plug-and-play library of Claude Code skills organized into an outer loop (PRD, spec, epic-slicing) run once per feature and an inner loop (prime, plan, implement) run once per ticket, and argues the single most important element is writing a validation strategy into the plan before any code is written so the agent can test and correct its own work.
Cole Medin23 minTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.
New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to structure an AI coding workflow into an outer planning loop and an inner ticket loop, using skills with defined templates and argument hints, so that validation strategy is specified upfront and the agent can self-correct instead of producing unreviewed first-pass code.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Inspect context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step
Deep lesson
Turn this video into working knowledge.
5,015 cleaned transcript words reviewed across 1,400 timed caption segments.
Thesis
Every Claude Code Skill I Use to Drive My Entire Development Process teaches a practical coding-agent workflow move: Cole Medin walks through his full AI-driven development system built as a plug-and-play library of Claude Code skills organized into an outer loop (PRD, spec, epic-slicing) run once per feature and an inner loop (prime, plan, implement) run once per ticket, and argues the single most important element is writing a validation strategy into the plan before any code is written so the agent can test and correct its own work.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:27
Skills, not a framework
“collection of skills at its core. And skills for your coding agents like Claude Code or Codeex, it's just a reusable prompt. It's a workflow to guide your coding agent through a certain process. And so, I just...”
Cole hasn't written code himself in over a year and runs everything through a minimalistic, plug-and-play collection of Claude Code skills (installable as a marketplace plugin or copied into any coding agent) rather than adopting an all-or-nothing framework like GitHub Spec Kit or Gastown, so users can take just one or two skills and customize them to their own codebase. List your current AI coding workflow's weakest step, then identify one skill from this system (PRD, spec, slice-epic, prime, plan, implement) you could adopt just for that step.
13:25
Outer loop vs. inner loop
“a markdown file for that next piece of work, it'll explore the codebase as it relates to, you know, what you want to build next. Regardless, the important thing here is that your coding agent, it has its...”
The outer loop (run once per epic/ticket batch) produces a PRD skill output (the what and why, via an agent interview), a separate spec/architecture document (the how), and then a slice-epic skill that maps dependencies across the PRD and spec into bite-sized tickets that can run in parallel or point at Confluence/markdown sources; the inner loop (prime codebase, then plan implementation in the same conversation, then implement in a new conversation) is run per ticket. For your next feature, explicitly separate a 'what and why' conversation (PRD) from a 'how' conversation (spec) before touching implementation, and note whether that split reduces agent scope creep.
16:28
Validation-first plans
“integration testing, the manual validation as well. How can we drive the application as a user also would using tools like you know the agent browser so it can perform browser automation. This is the most important part...”
The plan document's most important section is the testing strategy: unit, integration, edge cases, exact lint/typecheck/test commands, and manual/browser-automation validation, all defined before the agent writes a line of code; Cole calls this 'TDD for agents' and quotes Claude Code creator Boris Turney's advice to describe the task, guardrails, and exit criteria (including validation) and then let the model cook, arguing this is what reduces AI slop because the agent can iterate and self-correct against its own defined tests. In your next implementation plan, write the full validation strategy (exact test/lint commands and edge cases) before writing any implementation steps, then check the plan yourself before handing it to the agent.
01
Inspect context
Start with this video's job: Cole Medin walks through his full AI-driven development system built as a plug-and-play library of Claude Code skills organized into an outer loop (PRD, spec, epic-slicing) run once per feature and an inner loop (prime, plan, implement) run once per ticket, and argues the single most important element is writing a validation strategy into the plan before any code is written so the agent can test and correct its own work. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:27, where the video says: “collection of skills at its core. And skills for your coding agents like Claude Code or Codeex, it's just a reusable prompt. It's a workflow to guide your coding agent through a certain process. And so, I just...”
02
Route tool
Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 13:25, where the video says: “a markdown file for that next piece of work, it'll explore the codebase as it relates to, you know, what you want to build next. Regardless, the important thing here is that your coding agent, it has its...”
03
Plan work
Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.
04
Edit safely
Use "Edit safely" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Verify behavior
Use "Verify behavior" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Report next step
Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
Example
Coding-agent workflow proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.
Example
Teach-back module
Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
choosing tools by hype
losing context across agents
letting parallel sessions become invisible
Letting the lesson drift into generic Codex vs Claude comparison.
Letting the lesson drift into feature lists without task routing.
Letting the lesson drift into claims that ignore limits or recovery.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: Cole Medin walks through his full AI-driven development system built as a plug-and-play library of Claude Code skills organized into an outer loop (PRD, spec, epic-slicing) run once per feature and an inner loop (prime, plan, implement) run once per ticket, and argues the single most important element is writing a validation strategy into the plan before any code is written so the agent can test and correct its own work.
02
Explain the practical stakes without hype: New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: Every Claude Code Skill I Use to Drive My Entire Development Process
- URL: https://www.youtube.com/watch?v=MbiMwgbGdxw
- Topic: Creative Automation
- My current learning frame: Pick one upcoming ticket, run it through prime-codebase then plan-implementation in the same conversation, focus your review entirely on the validation strategy section, and only then send the plan to an implement step in a fresh conversation.
- Why this matters: New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:27 / Evidence 1: "collection of skills at its core. And skills for your coding agents like Claude Code or Codeex, it's just a reusable prompt. It's a workflow to guide your coding agent through a certain process. And so, I just..."
- 3:11 / Evidence 2: "the description. A majority of you are using Claude Code. So I do have this as a Claude Code marketplace plugin. I'll talk about other coding agents in just a second here. And so you copy this first..."
- 5:26 / Evidence 3: "agents? So, my AI coding workflow consists of two loops. This is the dead simple framework that makes it easier for me to build anything. The outer loop is the highest level planning, building your PRDS and spec..."
- 8:58 / Evidence 4: "install. Give this prompt to your coding agent, and then it builds this for you. Take a look. >> Hey Cole, I'm your Agora voice agent. Ask me anything. >> Hey, how's it going? >> Hello. >> Very,..."
- 13:25 / Evidence 5: "a markdown file for that next piece of work, it'll explore the codebase as it relates to, you know, what you want to build next. Regardless, the important thing here is that your coding agent, it has its..."
- 16:28 / Evidence 6: "integration testing, the manual validation as well. How can we drive the application as a user also would using tools like you know the agent browser so it can perform browser automation. This is the most important part..."
- 22:03 / Evidence 7: "implementation for example. Copy this. Go in here and I'll just say, "Hey Claude, I want to change XYZ about this skill, right? Like I'm never handwriting these skills or making the tweaks by hand. I'm always having..."
Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
- answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
- 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
- a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
- one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "Every Claude Code Skill I Use to Drive My Entire Development Process", not a generic Creative Automation essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
A reusable artifact with a done signal and one verification step.03
Coding-agent workflow teach-back card
Explain the coding-agent workflow mechanism to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
Why does Cole prefer a minimalistic skills library over frameworks like GitHub Spec Kit or Gastown?
What are the three main outputs of the outer loop, and what does each answer?
What does Cole say is the most important part of an implementation plan, and why?
Source shelf
Use the video as a doorway, then verify with primary sources.
