Shadowing Practice: New Skills! v1.2 brings /wait-what, /writing-for-agents, and fixes /grill-me - Learn English Speaking with Video
Les maken...
1
Skills, skills, skills, folks.
2
We have yet more skills for you.
3
This is version 1.2.0, which adds a bunch of improvements to my already extremely popular engineering skills.
4
The skills repo is now, I think, the 24th most starred repo of all time on GitHub, up to 204k stars.
5
And as a mature project, we need some proper documentation.
6
And so we have it.
7
This is at aihero.dev forward slash skills and I've been working with my team to produce this absolutely wonderful site.
8
The best way to navigate this is by going to the main page forward slash skills
9
and then looking at the kind of groupings that we've got here.
10
For instance, we can see here the main flow where you start with grill with docs, then go to spec, then to tickets, implement and then code review.
11
And the left hand panel here, you've got a full reference of every single skill and what they do.
12
It used to be my actual full time job to write documentation.
13
So I was pretty happy to go back to it.
14
There's even a list of common questions
15
which are actually sourced from a personal wiki that I maintain of all the questions people ask me.
16
These skills are also linked to an AI coding dictionary that I've been putting together.
17
For instance, this little ticket link here is the dictionary definition for what I think of as a ticket.
18
So these docs not only can you use them to learn my skills better, you can also use them just to learn about AI coding and understand how things work at a deep level.
19
The second big change is we are now an official part of of the Claude Code official plugin marketplace.
20
What that means is you can open Claude Code, you can say plugin like this,
21
you can search for Matt Pocock here or Matt Pocock skills and then you can install it right from here.
22
This means you end up with a read only bundle.
23
There's no extra steps here and any updates I make to the skills will be automatically pulled down to you.
24
That sounds pretty good if you're a Claude Code user, but what if you're a Codex user?
25
What's in this release for you?
26
I now include openai.yaml files for every single skill, which means that it should properly work out of the box with UIs like codex UI.
27
And also it means that this allow implicit invocation false travels over to codex.
28
Before we had model invoked skills and user invoked skills.
29
And the benefit of user invoked skills, which we can see inside the main skill.md file, is these are hidden from the agent's context window until you invoke them.
30
That works for clawed code.
31
It works for pi, works for a couple of other harnesses, but it doesn't work for codex.
32
I didn't quite realize that.
33
And so now we ship these sidecar files with every single skill to mean that we have this allow implicit invocation false.
34
So that works out of the box with codex too.
35
The next thing I wanted to ship a skill for is that Opus, especially Opus 5, is talking garbage at the moment.
36
I don't understand what it is.
37
I think it might just be a new model thing.
38
But for some reason, every time interact with Opus it just goes right over my head.
39
It's incredibly verbose, it uses really weird LLM phrases
40
and I just find it really really hard to read and a lot of people feel the same.
41
The honest options are to accept it and reword the AC
42
or to persist the digest along the export so a resumed unchanged publisher can skip the read to flagging rather than picking.
43
What does that mean?
44
It is genuinely load-bearing though so that's how you know it matters.
45
I've tried all sorts of ways to fix it such as output styles
46
or adding things to my agents.md
47
but what I realized I needed was just a skill to say wait what did you just say?
48
And so the skill is called wait what?
49
It's a very, very simple skill that just does a couple of things.
50
First, it says use this specific standard, ASD STE 100 Simplified Technical English,
51
which is essentially just a leading word to the agent to say use very simple language, speak in clear declarative sentences.
52
And secondly, it also tells it to ground itself in the ubiquitous language in context.md.
53
The real cure for verbosity is not to tell it to use simple language, although we are doing a bit of that, is to tell it to use your language,
54
the stuff that you have come up with in Grill With Docs.
55
You use this skill whenever the agent just creates some random garbage and you've no idea what they just said.
56
You just say, wait, what?
57
And it should reply with a much better alternative.
58
The next thing that's changed is a pretty big one.
59
It's an update to my most popular skill, which is Grill Me.
60
Previously, Grill Me used to grill you one question at a time.
61
In other words, you get a question and then you would respond and then another question, then you would respond.
62
So one question per turn.
63
However, this has a horrible failure mode, which is when you get to the end of a grilling session and most of the hard stuff is already done, you just have a bunch of easy questions,
64
one per turn, that you're just basically saying, yeah, that sounds good.
65
Yeah, that sounds good too.
66
This is incredibly frustrating and it feels dead slow.
67
So for a while, I've wanted to find a way to speed this up.
68
The thing that makes most sense to me is to have multiple questions per turn.
69
So if you have lots of easy ones, you can just say, yes, yes, yes, yes, yes.
70
But what happens when the answer to question three depends on the answer in question one?
71
Before you never had that problem because you would just answer them one at a time.
72
So if a question depended on an earlier question, then that one had already been answered.
73
But in this new setup, surely that's more confusing because you're going to be answering erroneous questions
74
or questions at the wrong time or questions that need to be answered before other questions.
75
How is that going to work?
76
Well, if you think about it, these questions are really like a graph.
77
There might be one critical question at the very start that needs answering first, that opens up a whole raft of other questions, and maybe they lead on to other questions themselves.
78
And so now GrillMe is designed to follow this graph, to answer only the questions that are available now, but to ask them in rounds.
79
And so you get the first round of questions, which might be as little as one critical question.
80
Then you go to the next round of the questions
81
that opens up and it's always pushing you as fast as possible down the frontier of questions.
82
And this is what it looks like.
83
You can see I'm at round one here and we have Q1 and then we get this little recommendation here.
84
I've decided to use, I know, I know you probably don't like it, but I love it, emojis here for a little pop of color.
85
This makes it super easy to navigate with my eyes.
86
I can see, okay, this is Q1 and then I can see the recommended answer.
87
Q2, see the recommended answer.
88
And because I'm using dictation, I just get to blast out, okay, Q1, I agree.
89
Q2, I agree.
90
Q3, we need something to change there.
91
Q4, we need something to change.
92
And then further down, we can see round two came in and the same setup.
93
So we answered the first round of questions
94
and then we got another round of questions and we kept pushing the frontier back.
95
The next big change is that I've modified my writing great skills skill
96
because I noticed that I was using it for stuff other than skills.
97
I was using it for anything that an agent read to make the agent better, to make the doc more concise, and to make the output a bit more predictable.
98
And so now we have writing for agents, where you can modify it for agents.md, or claw.md, or when you're creating editing skills.
99
And it has some extra skill mechanics stapled on inside this reference file.
100
So you can use it for writing skills.
101
You can use it crucially for taking your agents.md, pulling it out into skills to stop that horrible front loading.
102
So overall, I find myself using this skill so, so often whenever I need to write any agent configuration and I want it to read well, I want the agent to perform well with it,
103
writing for agents is the right call.
104
And it's also model invokable as well.
105
And it's a really clean description here.
106
So it should pull it in whenever it's modifying agents.md, which is just great.
107
The next one is a new skill, one that I've been keeping under wraps for a little while.
108
This is the wizard skill.
109
I found myself recently having to provision a bunch of infrastructure and walk through a bunch of AWS stuff, and I just hated it.
110
And I thought, surely there's a way that the agent can help me here.
111
And so I created this wizard skill that generates an interactive bash wizard
112
that walks the human through steps only they can perform.
113
In other words, I probably could have got the agent to, okay, go into AWS and provision the stuff with computer use or something, but it just felt pretty icky.
114
I wanted to have control over all of it but I wanted it to be as easy as possible.
115
And here is what one looks like.
116
This was for I think migrating to a remote box setup.
117
So you just kick it off and then you say ready to start.
118
Yes please.
119
And then it sends me off to exactly the page I need to go.
120
That opened the script by the way.
121
I didn't need to do anything there.
122
Sends me off, gets me to log in, gets me to change the exact thing we need to.
123
I can then paste in my API keys.
124
And remember, this is a deterministic script, so nothing's touching an agent here.
125
It's not sending it off to Anthropic or anything.
126
So I paste it in here.
127
It saves it into the files it needs to.
128
It's even saving them into GitHub Secrets if it needs to.
129
And it walks through these separate stages with me, keeping going with this nice little UI until we end up with what we need.
130
I found that this takes provisioning services from incredibly painful to weirdly joyful, because I just know how long it took me before.
131
So Wizard has become an essential part of my skillset.
132
I had it in In Progress for a couple of months, and I just think, okay, it's time for you guys to see it.
133
The next one is certainly the most boring skill name that I've ever produced, but I found myself really,
134
really needing it, and I realized it would be useful for more than what I had just used it for.
135
It is called To Questionnaire and its purpose is
136
that you take the decisions inside a grilling session
137
and you pull them out into a document that you can walk through with someone else.
138
I was doing a Wayfinder session to try to build a garden office in my back garden
139
and I realised that the agent was grilling me
140
but the person I really needed to speak to about it was my wife
141
because my wife obviously was going to use this space too and so we're going to design it together.
142
And so I got the agent to take the stuff it was going to ask in the grilling session
143
and turn it into a markdown document.
144
I then put that into a Google Doc, I sent that over to my wife, and we walked through it together.
145
And then we pulled the answers back in to the agent.
146
Now, this is a skill that I hope someday to delete
147
because it's sort of like a patch for the fact that agents are kind of hard to collaborate with at the moment.
148
Some teams who have like what I consider a really good setup is they have the agent in Slack
149
and they have these conversations they can then tag the agent in.
150
So they can collaborate together, answer questions together, especially with stakeholders.
151
And then the agent can actually pile in and go, okay, I'll implement it based on that.
152
But a lot of people are not in that world right now.
153
A lot of people are not AI native.
154
Maybe they don't even have Slack or Microsoft Teams or something.
155
And so actually having a document that you can just pull out, give to someone, they can comment on it on Google Docs or whatever, is actually really useful.
156
And so that, folks, is basically it.
157
We've got a tranche of new skills.
158
I'm especially looking forward to your reactions to wait what?
159
Because I think it will actually save your ass a couple of times when Opus is doing strange things.
160
There were a few things that were just a bit too small to mention here.
161
And so you can go to V1.2.0 in the GitHub releases to take a look at the full changelog.
162
And if you're digging this stuff, then I'm putting out an AI coding crash course, which is pretty different to the paid courses that I've put out before.
163
Instead of being a cohort where you do it over a couple of weeks and everyone's doing it together.
164
This is going to be a cheaper course that's available throughout the year.
165
My personal opinion about AI coding is that it's kind of settling down a little bit.
166
There's not actually that much has changed since about December last year.
167
And so I now feel confident enough
168
that I can put out a self-paced course that hopefully won't change too much even as things develop.
169
I'm hoping to give you a stable foundation from which you can work and actually ship amazing stuff.
170
And the link to this is down below and you can join the waitlist.
171
It should be coming out only in a couple of weeks, I think.
172
So thank you so much for watching.
173
Enjoy the new skills and I will see you very soon.
📺 Zelfde Kanaal
C13
New Skills! v1.3 brings /pr, /implement-spec, and /retro
Business EnglishUniversity StudentsWorking Adults
B23
Most devs don't understand what agents are
British AccentBusiness EnglishUniversity StudentsWorking Adults
C12
Most devs don't understand how LLM tokens work
British AccentBusiness EnglishUniversity StudentsWorking Adults
C14
New Skills! v1.1 brings /wayfinder, /research, /implement, /to-spec, /to-tickets
British AccentBusiness EnglishUniversity StudentsWorking Adults
C13
mattpocock/skills: A complete AI Coding workflow, end-to-end
British AccentBusiness EnglishUniversity StudentsWorking Adults
B23
I was an AI skeptic. Then I tried plan mode
British AccentBusiness EnglishUniversity StudentsWorking Adults
B23
/wayfinder: Nothing is too big to plan anymore
British AccentBusiness EnglishUniversity StudentsWorking Adults
C15
The 7 phases of AI-driven development
British AccentBusiness EnglishUniversity StudentsWorking Adults
C12
How to actually force Claude Code to use the right CLI (don't use CLAUDE.md)
British AccentBusiness EnglishUniversity StudentsWorking Adults
C13
Learn anything with the /teach skill
British AccentBusiness EnglishUniversity StudentsWorking Adults
C16
5 Claude Code skills I use every single day
British AccentBusiness EnglishUniversity StudentsWorking Adults
C15
Can Cursor's HARDCORE Review Skill Stop The Slop?
British AccentBusiness EnglishUniversity StudentsWorking Adults
C1New Skills! /handoff, /prototype, /review and /writing-* | Skills Changelog
British AccentBusiness EnglishUniversity StudentsWorking Adults
✨ Aanbevolen Video
B21
311 zinnen
I bought Black Market AI Tokens on Chinese Amazon
Business EnglishUniversity StudentsWorking Adults
B21
157 zinnen
Claude Design just got MASSIVE Upgrades (2.0 Update)
Business EnglishUniversity StudentsWorking Adults
B21
583 zinnen
Episode 531: Shallow feedback and my coworker is a huge sloperator
Business EnglishUniversity StudentsWorking Adults
B23
63 zinnen
How To Land Your First Junior Dev Role
Business EnglishInterview EnglishUniversity Students
![How to friction-max your learning with software engineer Jessica Rose [Podcast #216]](https://img.youtube.com/vi/pxMUG3gcoik/mqdefault.jpg)
B21
730 zinnen
How to friction-max your learning with software engineer Jessica Rose [Podcast #216]
Business EnglishDaily ConversationUniversity Students
B21
92 zinnen
Obsidian Narrator Full Demo
Business EnglishUniversity StudentsWorking Adults
B21
282 zinnen
What Stanford students actually use ChatGPT for
Business EnglishUniversity StudentsWorking Adults
B21
247 zinnen
"This Doesn't Lie" | Build Your Own English Level Checker with Google AI Studio
Business EnglishUniversity StudentsWorking Adults
B223 zinnen
AI Made the Most Passive Side Hustle Even Easier
Business EnglishUniversity StudentsWorking Adults
B21
564 zinnen
AI-First Playbook: Do a Team's Work With AI (2026) | Peter Yang
Business EnglishUniversity StudentsWorking Adults
Woordenschat en spreektips bij deze les
Deze spreekles op niveau B2 is gebaseerd op de video “New Skills! v1.2 brings /wait-what, /writing-for-agents, and fixes /grill-me”. Deze video bevat 173 zinnen en 2493 woorden om na te spreken. Het gesproken deel duurt 11:37. De spreker praat snel, ongeveer 215 woorden per minuut, dus reken op verbonden en ingeslikte klanken. 83% van de woorden hoort bij de 3.000 meest gebruikte Engelse woorden; de rest kun je beter vooraf bekijken.
Belangrijke woorden in deze video
De 15 moeilijkste woorden uit de video, met uitspraak en betekenis:
| Woord | Uitspraak | Betekenis |
|---|---|---|
| grill zelfstandig naamwoord | /ɡɹɪl/ | raster, rooster |
| invoke werkwoord | /ɪnˈvoʊk/ | aanroepen |
| wizard zelfstandig naamwoord | /ˈwɪzɚd/ | tovenaar, magiër |
| modify werkwoord | /ˈmɑ.dɪˌfaɪ/ | modificeren, veranderen |
| provision zelfstandig naamwoord | /pɹəˈvɪʒ.ən/ | provisie, bevoorrading |
| implicit bijvoeglijk naamwoord | /ɪmˈplɪsɪt/ | impliciet |
| collaborate werkwoord | /kəˈlæb.ə.ɹeɪt/ | samenwerken |
| claw zelfstandig naamwoord | /klɔ/ | klauw |
| navigate werkwoord | /ˈnæv.ɪ.ɡeɪt/ | navigeren |
| pasta zelfstandig naamwoord | /ˈpɑ.stə/ | deegwaren, pasta |
| frontier zelfstandig naamwoord | /ˈfɹʌntɪə/ | grens, landgrens |
| dictionary zelfstandig naamwoord | /ˈdɪk.ʃəˌnɛ.ɹi/ | woordenboek |
| graph zelfstandig naamwoord | /ɡɹæf/ | grafiek |
| garbage zelfstandig naamwoord | /ˈɡɑɹ.bɪd͡ʒ/ | huisvuil, vuilnis |
| implement werkwoord | /ˈɪmpləmənt/ | implementeren, (in de praktijk) toepassen |
Phrasal verbs die je zult horen
| Woord | Uitspraak | Betekenis |
|---|---|---|
| put out werkwoord | buitenzetten, uitwerpen | |
| come out werkwoord | /ˌkʌm ˈaʊt/ | uitkomen |
| come up with werkwoord | bedenken, verzinnen | |
| look forward to werkwoord | uitkijken naar, zich verheugen op |
Zinnen om te herhalen
Korte, volledige zinnen uit de video die je in alledaagse gesprekken kunt gebruiken:
- What's in this release for you?
- I didn't quite realize that.
- I don't understand what it is.
- You just say, wait, what?
- I'm especially looking forward to your reactions to wait what?
Grammatica in deze video
De structuren die de spreker het meest gebruikt, met de exacte woorden uit de video:
| Structuur | In de video |
|---|---|
| Present perfect continuous have/has been + -ing — iets dat eerder begon en nog bezig is | I've been working · I've been putting · I've been keeping |
| “Used to” used to + werkwoord — een vroegere gewoonte of toestand die niet meer klopt | used to be · used to grill |
| Present perfect have/has + voltooid deelwoord — iets uit het verleden dat nu nog telt | I've tried · have come · I've wanted |
| Lijdende vorm be + voltooid deelwoord — het gaat om wat er gebeurt, niet om wie het doet | are actually sourced · are also linked · are hidden |
Uitspraak om op te letten
De spreker gebruikt 33 samentrekkingen en verkorte vormen, zoals I've, you're, I'm. Spreek ze kort uit, zoals je ze hoort.
- De klanken “sh” en “zh”: provision /pɹəˈvɪʒ.ən/, invocation /ˌɪn.voʊˈkeɪ.ʃən/, documentation /ˌdɑkjəmɛnˈteɪʃən/, dictionary /ˈdɪk.ʃəˌnɛ.ɹi/, crucially /ˈkɹuːʃəli/
- Lange woorden — let op de klemtoon: invocation /ˌɪn.voʊˈkeɪ.ʃən/, collaborate /kəˈlæb.ə.ɹeɪt/, documentation /ˌdɑkjəmɛnˈteɪʃən/, dictionary /ˈdɪk.ʃəˌnɛ.ɹi/, declarative /dɪˈklæɹ.ə.tɪv/
Klanken die Nederlandstaligen lastig vinden:
- Stemhebbende eindmedeklinker — /b/, /d/, /g/, /z/, /v/ niet verscherpen: wizard /ˈwɪzɚd/, garbage /ˈɡɑɹ.bɪd͡ʒ/, depend /dɪˈpɛnd/, changelog /ˈtʃeɪndʒˌlɒɡ/, declarative /dɪˈklæɹ.ə.tɪv/
- /æ/ — opener dan de Nederlandse “e”: collaborate /kəˈlæb.ə.ɹeɪt/, navigate /ˈnæv.ɪ.ɡeɪt/, graph /ɡɹæf/, declarative /dɪˈklæɹ.ə.tɪv/, mechanic /mɪˈkænɪk/
- /g/ — een harde plofklank, geen Nederlandse “g”: grill /ɡɹɪl/, navigate /ˈnæv.ɪ.ɡeɪt/, graph /ɡɹæf/, garbage /ˈɡɑɹ.bɪd͡ʒ/, changelog /ˈtʃeɪndʒˌlɒɡ/
Zo oefen je met deze video
- Luister de hele video één keer zonder te spreken en noteer de woorden die je niet kent.
- Begin op 0,75× snelheid, spreek zin voor zin na en ga terug naar normale snelheid zodra het makkelijk gaat.
- Neem jezelf op en vergelijk met het origineel; let daarbij op woorden als grill, invoke, wizard.
Wat is de Shadowing-techniek?
Shadowing is een wetenschappelijk onderbouwde taalleermethode die oorspronkelijk is ontwikkeld voor professionele tolkentraining en gepopulariseerd door polyglot Dr. Alexander Arguelles. De methode is eenvoudig maar krachtig: je luistert naar native Engelse audio en herhaalt het onmiddellijk hardop — als een schaduw die de spreker volgt met slechts 1–2 seconden vertraging. In tegenstelling tot passief luisteren of grammaticadrills, dwingt shadowing je hersenen en mondspieren om echte spraakpatronen tegelijkertijd te verwerken en te reproduceren. Onderzoek toont aan dat het de uitspraaknauwkeurigheid, intonatie, ritme, verbonden spraak, luisterbegrip en spreekvaardigheid aanzienlijk verbetert — waardoor het een van de meest effectieve methoden is voor IELTS Speaking-voorbereiding en echte Engelse communicatie.