This video introduces 'PolySkill', a single adapter skill that converts an agent skill between Claude Code and Codex formats (and back) so you can run the same skill in both ecosystems without manually rebuilding it each time.
Mark KashefWatchTranscript 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 Mark Kashef; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to author one provider-neutral skill and reliably convert/install it across Claude Code and Codex, accounting for each platform's structural differences.
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.
2,394 cleaned transcript words reviewed across 666 timed caption segments.
Thesis
How to INSTANTLY Run ANY Skill in Claude + Codex teaches a practical coding-agent workflow move: This video introduces 'PolySkill', a single adapter skill that converts an agent skill between Claude Code and Codex formats (and back) so you can run the same skill in both ecosystems without manually rebuilding it each time.
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.
0:26
The portability problem
“executed are pretty different. You'll end up having to recycle and recreate skills over and over again. So the point of this video is to equip you with one single skill that you can use as a universal...”
Both Claude Code and Codex support skills, but their design, structure, and execution differ enough that you end up recreating skills per provider; a universal adapter solves this by converting in both directions. List the skills you currently use and note which provider they were authored for, identifying which would need conversion to run on the other.
4:29
Provider skill nuances
“zoom in, we have the name, we have the description, which tools bash commands are allowed to be executed by the skill, and then we have this additional field that's called disable model invocation, which means do you...”
Claude Code can embed and auto-execute a terminal command mid-skill and loads full descriptions up to a character limit, while Codex caps how much of a skill's description it reads (so triggers buried at the end may never be seen) and adds a separate sidecar YAML for tools, icons, and policies. Open one Codex skill and move its trigger phrases to the very start of the description, then inspect its sidecar YAML to see which fields have no Claude Code equivalent.
7:56
PolySkill internals
“line, this tilde, just means that it's installed globally at the cloud level and the dot agents level, which is specific to Codex. Then once we have that and scroll down, you could send a prompt as simple...”
PolySkill is built from three pieces: a shared neutral structure defining what any skill needs, swappable per-provider adapters (like cartridges) that add tool support, and a CLI so adding a new provider like Gemini just means analyzing its schema and emitting a third output. Sketch the shared-structure / adapter / CLI breakdown for one of your own skills, deciding what stays neutral versus what each provider's adapter must inject.
01
Inspect context
Start with this video's job: This video introduces 'PolySkill', a single adapter skill that converts an agent skill between Claude Code and Codex formats (and back) so you can run the same skill in both ecosystems without manually rebuilding it each time. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:26, where the video says: “executed are pretty different. You'll end up having to recycle and recreate skills over and over again. So the point of this video is to equip you with one single skill that you can use as a universal...”
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 4:29, where the video says: “zoom in, we have the name, we have the description, which tools bash commands are allowed to be executed by the skill, and then we have this additional field that's called disable model invocation, which means do you...”
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: This video introduces 'PolySkill', a single adapter skill that converts an agent skill between Claude Code and Codex formats (and back) so you can run the same skill in both ecosystems without manually rebuilding it each time.
02
Explain the practical stakes without hype: New playlist item from Mark Kashef; 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: How to INSTANTLY Run ANY Skill in Claude + Codex
- URL: https://www.youtube.com/watch?v=tjjX43FoAUg
- Topic: Codex + Claude Workflows
- My current learning frame: Take one existing Claude Code skill, drop it into a fresh folder, run the PolySkill install and convert flow, then verify it renders and executes correctly in both the Codex app and Claude Code.
- Why this matters: New playlist item from Mark Kashef; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:26 / Evidence 1: "executed are pretty different. You'll end up having to recycle and recreate skills over and over again. So the point of this video is to equip you with one single skill that you can use as a universal..."
- 2:19 / Evidence 2: "them. Whereas in Cloud Code, it will ram all your descriptions as is as long as they're below a certain character limit within the context window as soon as you start a new session. And on the Codex..."
- 4:29 / Evidence 3: "zoom in, we have the name, we have the description, which tools bash commands are allowed to be executed by the skill, and then we have this additional field that's called disable model invocation, which means do you..."
- 6:12 / Evidence 4: "for both Claude as well as Codex and create this YAML file if needed for the Codex skill version. And you can think of my skill again as a form of adapter. This is a universal travel adapter,..."
- 7:56 / Evidence 5: "line, this tilde, just means that it's installed globally at the cloud level and the dot agents level, which is specific to Codex. Then once we have that and scroll down, you could send a prompt as simple..."
- 9:34 / Evidence 6: "And now you have this two-way communication between Codex and Cloud Code. And you'd have the identical experience in the Codex app where if you use dollar sign poly skill and you tell it to use one of..."
- 11:10 / Evidence 7: "see on YouTube, then check the first link down below and maybe I'll see you in my early adopters community. For the rest of you, if you found this helpful, if you found it novel, then please let..."
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 "How to INSTANTLY Run ANY Skill in Claude + Codex", not a generic Codex + Claude Workflows 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.
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 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.
Both Claude Code and Codex support skills, so what specific problem does PolySkill exist to solve?
Name two concrete mechanical differences between a Claude Code skill and a Codex skill that the video says cause skills to misfire across providers.
What are the three internal pieces PolySkill is built from, and how does that design make adding a new provider like Gemini easy?
Source shelf
Use the video as a doorway, then verify with primary sources.
