Commenters are divided on whether Jane Street's Socratic Tutor skill represents a meaningful innovation or merely repackaged, generic prompt engineering that lacks novelty. While some praise the structured approach for enhancing learning and critical thinking, others criticize it as superficial 'AI slop' that risks eroding independent thought and professional judgment.
155 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4mattpocock
skills
Shell2026–2026
mattpocock / skills
skills
Skills for Real Engineers. Straight from my .agents directory.
36Distinct people
41Mentions
0Explicit recommenders
323.4KGitHub stars
What to know before exploring
What it is
Skills for Real Engineers. Straight from my .agents directory.
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
No recommendation phrase was found in the indexed comments.
Favorable Commenters describe the repository's skills as effective for generating intuition and helping users get unstuck, though one user notes it may lack sufficient structure for comprehensive self-teaching compared to other methods. Another user explicitly cites the library as the foundation for their agent context management approach.
This week’s discussion is favorable. This is not a standing endorsement. Read the supporting reply
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Favorable
Commenters describe the repository's skills as effective for generating intuition and helping users get unstuck, though one user notes it may lack sufficient structure for comprehensive self-teaching compared to other methods. Another user explicitly cites the library as the foundation for their agent context management approach.
Supporting reply 1 · Supporting reply 2 · 2 discussions summarized
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
Read the discussion on HN. A full-thread summary is not available yet.
Developers disagree on whether agent context should be managed through lightweight, git-ignored markdown files and standardized protocols like AGENTS.md or via custom-built tools enforcing strict isolation. The strongest disagreement centers on the trade-off between simplicity and robustness, with some arguing that native LLM capabilities suffice while others insist on external systems to prevent cross-client data pollution.
60 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4Showing the three threads with the most distinct people linking this repo, from 22 threads this week.
Mentions over time
HN mentions by week41 dated mentions
Observed mentions: 2026-03-05 00:50:24 UTC to 2026-10-03 21:57:39 UTC. Weeks start Monday, UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Mar 2 | 2026-03-02 00:00:00 UTC | 2026-03-09 00:00:00 UTC | 1 | 0 | 1 |
| Mar 9 | 2026-03-09 00:00:00 UTC | 2026-03-16 00:00:00 UTC | 1 | 0 | 1 |
| Mar 16 | 2026-03-16 00:00:00 UTC | 2026-03-23 00:00:00 UTC | 0 | 0 | 0 |
| Mar 23 | 2026-03-23 00:00:00 UTC | 2026-03-30 00:00:00 UTC | 1 | 0 | 1 |
| Mar 30 | 2026-03-30 00:00:00 UTC | 2026-04-06 00:00:00 UTC | 0 | 0 | 0 |
| Apr 6 | 2026-04-06 00:00:00 UTC | 2026-04-13 00:00:00 UTC | 0 | 0 | 0 |
| Apr 13 | 2026-04-13 00:00:00 UTC | 2026-04-20 00:00:00 UTC | 0 | 0 | 0 |
| Apr 20 | 2026-04-20 00:00:00 UTC | 2026-04-27 00:00:00 UTC | 0 | 0 | 0 |
| Apr 27 | 2026-04-27 00:00:00 UTC | 2026-05-04 00:00:00 UTC | 2 | 0 | 2 |
| May 4 | 2026-05-04 00:00:00 UTC | 2026-05-11 00:00:00 UTC | 2 | 0 | 2 |
| May 11 | 2026-05-11 00:00:00 UTC | 2026-05-18 00:00:00 UTC | 1 | 0 | 1 |
| May 18 | 2026-05-18 00:00:00 UTC | 2026-05-25 00:00:00 UTC | 1 | 1 | 0 |
| May 25 | 2026-05-25 00:00:00 UTC | 2026-06-01 00:00:00 UTC | 1 | 0 | 1 |
| Jun 1 | 2026-06-01 00:00:00 UTC | 2026-06-08 00:00:00 UTC | 3 | 0 | 3 |
| Jun 8 | 2026-06-08 00:00:00 UTC | 2026-06-15 00:00:00 UTC | 2 | 1 | 1 |
| Jun 15 | 2026-06-15 00:00:00 UTC | 2026-06-22 00:00:00 UTC | 0 | 0 | 0 |
| Jun 22 | 2026-06-22 00:00:00 UTC | 2026-06-29 00:00:00 UTC | 1 | 0 | 1 |
| Jun 29 | 2026-06-29 00:00:00 UTC | 2026-07-06 00:00:00 UTC | 1 | 0 | 1 |
| Jul 6 | 2026-07-06 00:00:00 UTC | 2026-07-13 00:00:00 UTC | 2 | 0 | 2 |
| Jul 13 | 2026-07-13 00:00:00 UTC | 2026-07-20 00:00:00 UTC | 1 | 0 | 1 |
| Jul 20 | 2026-07-20 00:00:00 UTC | 2026-07-27 00:00:00 UTC | 0 | 0 | 0 |
| Jul 27 | 2026-07-27 00:00:00 UTC | 2026-08-03 00:00:00 UTC | 1 | 1 | 0 |
| Aug 3 | 2026-08-03 00:00:00 UTC | 2026-08-10 00:00:00 UTC | 1 | 0 | 1 |
| Aug 10 | 2026-08-10 00:00:00 UTC | 2026-08-17 00:00:00 UTC | 4 | 0 | 4 |
| Aug 17 | 2026-08-17 00:00:00 UTC | 2026-08-24 00:00:00 UTC | 2 | 0 | 2 |
| Aug 24 | 2026-08-24 00:00:00 UTC | 2026-08-31 00:00:00 UTC | 1 | 0 | 1 |
| Aug 31 | 2026-08-31 00:00:00 UTC | 2026-09-07 00:00:00 UTC | 2 | 1 | 1 |
| Sep 7 | 2026-09-07 00:00:00 UTC | 2026-09-14 00:00:00 UTC | 1 | 0 | 1 |
| Sep 14 | 2026-09-14 00:00:00 UTC | 2026-09-21 00:00:00 UTC | 2 | 0 | 2 |
| Sep 21 | 2026-09-21 00:00:00 UTC | 2026-09-28 00:00:00 UTC | 3 | 0 | 3 |
| Sep 28 | 2026-09-28 00:00:00 UTC | 2026-10-05 00:00:00 UTC | 4 | 0 | 4 |
What Hacker News says
41 sourcesISistjohn·Oct 3, 2026
Look up the grilling skill[0]. To make it even better, tell Claude to modify it to use the AskUserQuestion functionality. It's so much better than plan mode.
0. https://github.com/mattpocock/skills/blob/main/skills/produc...
In Getting the most out of Opus 5.5 in Claude and Claude Codeah yea, that is the one!
thanks for surfacing this for everyone
link: https://github.com/mattpocock/skills/blob/main/skills/engine...
In Cf: The Agentic CLI for the Cloudflare APIKudos to cloudflare on this, it looks like a great CLI, I especially like the `cf cli search`.
Related, Matt Pocock's skill for having agents generate an interactive bash script for things only humans can do (or should do), presented in the context of devops like activities
https://github.com/mattpocock/skills/blob/main/skills/produc...
I have found that having the agents write scripts to use tools like this is better (less tokens, more reliability, fewer side quests) than giving it to them directly with markdown they may or may not follow on any given day.
The other benefit to this is that you can put scripts on either side of the agent and remove all credentials from their process, removing whole classes of issues you don't want to have to tell your boss about. CLIs like this are great for read-only debug sessions, but if you are going
Read the rest
to make modifications to your cloud infra, keep doing IaC.
I saw your response before it was deleted- that you are doing multi agent persona reviews and a very intensive review process. So having fewer review items saves you money.
One thing that I have found is that as the frontier models get better there is less need for agents with specialized personas. I actually don't don't use those anymore- I just use agents that have different models and reasoning levels. I have a generated CODING_STANDARDS.md document and a skill for architecture design and a skill for implementing testing [2] that are referenced by a single reviewer. I do implement a 2-pass review though [3].
I would be interested to know if you have found anything similar as models get better. It seems though that you are sharing a single exploration and then sharing the context across the specialized reviewers to dramatically reduce t
Read the rest
he cost of your approach. Does this have to be in the harness- that is if you write out the shared context to a file does that increase your costs a lot?
I also wonder how intensively are the models able to test their changes? The number one quality improvement I have found is not review but having the model properly test its code. I have a skill that is helping [4], but I also have to spend time to establish a pattern of testing with tools beyond just unit tests. The testing takes significant effort, and this is again where the cost savings of DeepSeek shine.
[1] https://github.com/mattpocock/skills/blob/main/skills/engineering/codebase-design/…
[2] https://github.com/gregwebs/skills-sdlc/blob/main/skills/verify/SKILL.md
[3] https://github.com/mattpocock/skills/blob/main/skills/engineering/code-review/SKIL…
[4] https://github.com/gregwebs/skills-sdlc/blob/main/skills/verify/SKILL.md
I've found Opus 5.5 is quite good at surfacing and clarifying these issues using Grilling[0]. Often I find that I want to expand the scope of work much larger than Claude would consider based on my original request.
0. https://github.com/mattpocock/skills/blob/main/skills/produc...
In Plan mode is deadI realised I linked super cringe docs instead of the actual skill:
https://github.com/mattpocock/skills/blob/main/skills/produc...
In Plan mode is deadI have been using this super simple skill[0] to make Claude ask exhaustive questions about the implementation of larger features. It has been absolutely amazing and felt like a step change in the output quality.
For complex features there can be 10 or more questions but I have a very strong sense of understanding the changes about to be made and Claude is very good at following all the decisions exactly. It's like working with an engineer who is both excellent at soliciting requirements and fast at implementation.
[0]https://github.com/mattpocock/skills/blob/main/docs/producti...
In Plan mode is deadThere's a skill for that (haven't tried myself but intend to; other of author's skills I've used have been a game changer).
- https://github.com/mattpocock/skills/blob/main/skills/produc...
- https://www.youtube.com/watch?v=s5T5oQJcJ6U
In I vibed a proof of Conway's conjectureThey are generally portable.
Eg. /wait-what https://github.com/mattpocock/skills/blob/main/skills/produc...
In Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipherTIMTOWTDI. "[T]hings shared with the team (in the repo)" implies project-specific skills. See e.g. https://github.com/mattpocock/skills for a stellar example of third-party skills for battle-hardened workflows.
In Ask HN: How do you manage skills files?Aside from the fact that Matt Pocock spends a lot of time with LLMS (only Claude really), he has a hand-wavy approach to engineering in a silo. He then uses that output as a foundation for other tools, while touting them as the best way to do things on youtube. Claude promotes this kind of developer and it's harmful.
Anyone who uses LLMs notices (intrinsically or through investigation) that there are a small number of useful instructions for LLMs, which is distilled from the language.
* Invariants (always/must, never)
* Precedence
* Guidelines/Opportunistic Inspection (softest instruction)
* Patterns
* Concrete commands/actions
- all of which can be mixed and matched.
The prose he writes often has very little utility, wrapped up in a ball of wax. I would at least expect that an engineer would run AI skill files through an impartial LLM to
Read the rest
look for cruft.
eg
"if this document is for an LLM to consume, is there any noise in the instructions? https://github.com/mattpocock/skills/blob/main/skills/engine..."
AI Coding Agent Skills for Real Engineers
43 points · Open discussionWell, I think this idea is pretty cool — it feels very similar to Matt's domain-modeling:
https://github.com/mattpocock/skills/blob/main/skills/engine..."
In Domain-Driven AgentsI believe these are called Architectural Decision Records. Matt Pocock's skills [0] make use of them. They're one of the more useful things I've gotten out them.
[0] https://github.com/mattpocock/skills
In Show HN: Huzzah – a novel approach to coding with AIIt seems to me he could have use an skill like using-agent-skills from https://github.com/addyosmani/agent-skills go generate the specs and use a validator like oracle or something along the same lines.
Also, a skill like grill-me from Matt P. https://github.com/mattpocock/skills.
In Sol Loves to CheatShowing the 15 most recent of 41 sources. Enable JavaScript to search and browse every indexed mention.