How Anthropic Engineers ACTUALLY Prompt Claude Code
This video distills four rules Anthropic engineers reportedly use for Claude Code: prompt named skills instead of one-off prompts, invest in a skill's tools layer (not just its prompt), build small composable skills that chain together, and update skills after every session so they compound.
Austin MarcheseWatchTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, plan, edit, verify, summarize, and route the next task to the right tool.
New playlist item from Austin Marchese; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: Designing reusable Claude Code skills (description, instructions, and tools layers) and maintaining them as a compounding library rather than writing disposable prompts.
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
02Plan
03Edit
04Verify
05Review
06Route
Deep lesson
Turn this video into working knowledge.
2,394 cleaned transcript words reviewed across 702 timed caption segments.
Thesis
How Anthropic Engineers ACTUALLY Prompt Claude Code teaches a practical codex + claude workflows move: This video distills four rules Anthropic engineers reportedly use for Claude Code: prompt named skills instead of one-off prompts, invest in a skill's tools layer (not just its prompt), build small composable skills that chain together, and update skills after every session so they compound.
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.
0:54
Prompt skills, not Claude
“actually creating these skills, which we'll cover in rules two, three, and four. But, first you need to have the mental shift. Stop thinking in traditional prompts, start thinking in prompting Claude skills. This may sound complicated, but...”
Most work is repetitive, so instead of writing fresh prompts each time you package the task into a reusable skill (a folder of files) and invoke it like /draft-email; skills live across the three-layer stack as the 'application' layer above the model and raw prompts. List three repetitive tasks you do in chat and rewrite one of them as a named slash-skill instead of a from-scratch prompt.
3:00
Build the tools layer
“Claude grabs the skill, this is the playbook it follows. This is a step-by-step process on how to actually complete the task. And layer three are the tools it has access to. This is code scripts, API calls,...”
A skill has three layers: a description Claude reads to decide when to use it, step-by-step instructions, and tools (scripts, API calls, reference files); most people pour effort into the prompt and ship bare-bones tools, but the tools layer is where the real leverage lives. Take a skill you have and add a concrete tool to it (a verification script or API call), then sharpen its description so Claude auto-selects it without being asked.
8:14
Control invocation flags
“you're designing these skills. Here's a prompt you can run to audit your setup to make sure that you're properly applying these things into your skills. Screenshot this and just send the photo into Claude and I highly...”
Two skill flags govern access: setting user-invocable to false hides a skill from the slash menu so only agents can run it, while disable-model-invocation stops the model from running it so only you can trigger higher-risk actions like deploying or sending a message. Audit your skills and tag each as agent-only or human-only, applying the right flag to anything risky such as a deploy or send-message skill.
01
Inspect
Start with this video's job: This video distills four rules Anthropic engineers reportedly use for Claude Code: prompt named skills instead of one-off prompts, invest in a skill's tools layer (not just its prompt), build small composable skills that chain together, and update skills after every session so they compound. Treat "Inspect" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:54, where the video says: “actually creating these skills, which we'll cover in rules two, three, and four. But, first you need to have the mental shift. Stop thinking in traditional prompts, start thinking in prompting Claude skills. This may sound complicated, but...”
02
Plan
Use "Plan" to locate the part of the codex + claude workflows workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 3:00, where the video says: “Claude grabs the skill, this is the playbook it follows. This is a step-by-step process on how to actually complete the task. And layer three are the tools it has access to. This is code scripts, API calls,...”
03
Edit
Turn "Edit" into the reusable artifact for this lesson: A routing matrix for when to use Codex, Claude, browser checks, or manual review. This is where watching becomes something you can inspect and reuse.
04
Verify
Use "Verify" 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
Review
Use "Review" 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
Route
Use "Route" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a routing matrix for when to use codex, claude, browser checks, or manual review..
Example
Claim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
Example
Teach-back module
Transform the lesson into a definition, a mechanism 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.
Letting the prompt drift into generic advice that could apply to any video in the playlist.
Copying the tool setup without identifying the operating principle that transfers to your own stack.
Skipping the artifact, which means the learning never becomes operational or inspectable.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This video distills four rules Anthropic engineers reportedly use for Claude Code: prompt named skills instead of one-off prompts, invest in a skill's tools layer (not just its prompt), build small composable skills that chain together, and update skills after every session so they compound.
02
Explain the practical stakes without hype: New playlist item from Austin Marchese; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect -> Plan -> Edit -> Verify -> Review -> Route sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A routing matrix for when to use Codex, Claude, browser checks, or manual review.
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: How Anthropic Engineers ACTUALLY Prompt Claude Code
- URL: https://www.youtube.com/watch?v=qOvc9IUKEIc
- Topic: Codex + Claude Workflows
- My current learning frame: Pick one repetitive workflow, split it into small composable skills with a real tools-layer script, then after running it once review your chat history and fold the corrections back into the skill so the next session starts smarter.
- Why this matters: New playlist item from Austin Marchese; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:54 / Evidence 1: "actually creating these skills, which we'll cover in rules two, three, and four. But, first you need to have the mental shift. Stop thinking in traditional prompts, start thinking in prompting Claude skills. This may sound complicated, but..."
- 3:00 / Evidence 2: "Claude grabs the skill, this is the playbook it follows. This is a step-by-step process on how to actually complete the task. And layer three are the tools it has access to. This is code scripts, API calls,..."
- 4:44 / Evidence 3: "composable, portable, efficient, and powerful. Composability means multiple skills can work together with Claude automatically coordinating which to use. What this means is you should have small, focused, and reusable skills that can work together, versus having a..."
- 6:26 / Evidence 4: "of these come from directly how Anthropic engineers actually use them. So pattern one is save scripts inside of skills. This is part of the tools layer of a skill and it's how you actually make them sharper."
- 8:14 / Evidence 5: "you're designing these skills. Here's a prompt you can run to audit your setup to make sure that you're properly applying these things into your skills. Screenshot this and just send the photo into Claude and I highly..."
- 10:09 / Evidence 6: "itself. Just say, "Review the back and forth I just had after using this skill. Can we enhance the skill so this is handled automatically or we don't make the same mistake again?" So, zooming out, these four..."
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, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A routing matrix for when to use Codex, Claude, browser checks, or manual review.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect -> Plan -> Edit -> Verify -> Review -> Route
- 3 concrete examples that apply the video idea to real agentic work
- 2 failure modes the video helps prevent
- a checklist I can use the next time I run Codex or Claude
- one practical exercise with a clear done signal
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 "How Anthropic Engineers ACTUALLY Prompt Claude Code", not a generic Codex + Claude Workflows essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, 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.
One agent should do every task.
Different tools have different strengths. Routing is part of the workflow.
More context is always better.
Relevant context helps; stale context causes drift and cost.
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 routing matrix for when to use codex, claude, browser checks, or manual review..
A reusable artifact with a done signal and one verification step.03
Teach-back card
Explain the lesson 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.
A Claude skill is described as more than a prompt. What are its three layers, and which one does the video say most people neglect even though it holds the most leverage?
The engineers favor 'composable, not custom' skills. What concrete failure did the presenter hit with a single giant skill, and what three benefits did splitting it up provide?
The video describes two skill flags that control invocation. What does each flag do?
Source shelf
Use the video as a doorway, then verify with primary sources.
