Muratcan Koylan ✓
@muratcan · Toronto, Canada 🇨🇦 · joined 16 Dec 2022
MTS, AI Research @sullyai Building AI medical workforce Prev/ AI Persona Development @ 99Ravens
22 135Followers
3 806Following
12 915Posts total
1.1MViews on collected posts
Latest posts
Looking for new posts…
There is a deep convergence between human persuasion and LLMs. Because LLMs are trained on human text, Cialdini’s principles of influence are not just applicable but inherently valid for human-to-human and human-to-agent interactions, as well as inter-agent communication.
A http
966 views · 12 likes
· 2 reposts · 0 replies
Open on X →
Finally acquired a 3D printer
I need to know how people are actually using agents to design CAD and hardware. Also drop any good papers, blogs, or embodied AI projects I should be looking pls. https://t.co/u0ymTKSVRV
3.2K views · 31 likes
· 1 reposts · 7 replies
Open on X →
Don’t make the model solve the entire complex problem.
Make the harness turn the complex problem into a collection of simple problems.
1. Start with the dumbest system that can work.
2. Build a good eval.
3. Add complexity only where the eval shows that you need it.
I love htt
29.2K views · 560 likes
· 42 reposts · 20 replies
Open on X →
100%. To me, mastering prompt & context engineering is less about becoming an expert in an engineering domain and more about knowing how to activate the right neural nets of the model for an unfamiliar problem.
It is extremely undervalued how important (and challenging) it is to
7.4K views · 78 likes
· 6 reposts · 3 replies
Open on X →
if you can master the meta-skill of figuring out what problems in arbitrary domains are computationally tractable, you will have the opportunity, for at least a year two, and maybe longer, to be a kind of meta-genius. you will not know the answer to anything, or even how to find
231.2K views · 2.2K likes
· 153 reposts · 81 replies
Open on X →
Fixed the Claude Code plugin marketplace structure.
The skills are now properly discoverable and installable.
Restructured the marketplace.json to match the official Anthropic format and organized the 10 skills into 4 plugin groups.
If you previously added this marketplace, h
5K views · 8 likes
· 0 reposts · 1 replies
Open on X →
The Agent Skills for Context Engineering library is now available as a Claude Code plugin.
You can try it out here:
/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering
@AnthropicAI @claudeai https://t.co/FxSA0sdu5L
1.1K views · 9 likes
· 1 reposts · 1 replies
Open on X →
Agent Skills for Context Engineering repo is growing faster than I expected.
I have started receiving great suggestions like Claude Plugin versions and new skill requests.
If you find this useful and want to collaborate on this open-source project, send a DM. https://t.co/vaCEu
161.4K views · 111 likes
· 5 reposts · 0 replies
Open on X →
Added an `examples/` folder showing how the skills work together in practice. First example is a complete PRD for a multi-agent system that monitors X accounts and generates daily synthesized books.
I just tagged the repo and asked Opus 4.5 in Cursor to use them to build the htt
3K views · 4 likes
· 0 reposts · 3 replies
Open on X →
Well, I wasn’t expecting 200 GitHub stars in 12 hours.
Have you guys tried it? Any feedback? Should I keep working on this? https://t.co/Sb5GGi8kas
2.9K views · 11 likes
· 0 reposts · 1 replies
Open on X →
Most of the reference documents I used are from these or similar context engineering learnings.
https://t.co/TS0yhfJM0d
7.8K views · 8 likes
· 0 reposts · 1 replies
Open on X →
I’m excited to share a new repo: Agent Skills for Context Engineering
Instead of just offering a library of black-box tools, it acts as a "Meta-Agent" knowledge base. It provides a standard set of skills, written in markdown and code, that you can feed to an agent so it https://
317.3K views · 1.5K likes
· 154 reposts · 53 replies
Open on X →
It’s actually a good question; the difference is subtle but structural.
I usually frame it like this:
AGENTS[.]md acts as the declarative context. You write this for every repo (and nested directories) to define the project structure, persona, and coding rules.
Skills are the
206.2K views · 136 likes
· 7 reposts · 9 replies
Open on X →
Manus was one of the few experiences for me that showed what can be achieved with well-designed agent architecture.
As @peakji mentioned in the LangChain webinar, they have changed the agent design several times, so their learnings in context engineering are very valuable. ht
93.1K views · 646 likes
· 66 reposts · 15 replies
Open on X →
Against accounts of the same size
5 posts from the last 90 days, next to the 10K–100K follower range. shown to more people than peers of the same size.
Median views7 363this account924median for 10K–100K
Reach, %33.26%this account3.62%median for 10K–100K
Engagement, %1.25%this account1.52%median for 10K–100K
| Metric | This account | Median for 10K–100K | Ratio |
|---|---|---|---|
| Median views per post | 7 363 | 924 | 7.97× |
| Reach (views ÷ followers) | 33.26% | 3.62% | 9.19× |
| Engagement rate | 1.25% | 1.52% | 0.82× |
Others in this range → Compare with another account → How these benchmarks are built →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
206.2K21 Dec
317.3K
7.8K
2.1K
2.9K22 Dec
3K
161.4K24 Dec
1.1K26 Dec
5K31 Dec
231.2K8 Aug
7.4K
29.2K10 Aug
3.2K
96619 Aug
Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
0.07%21 Dec
0.53%
0.11%
0.34%
0.42%22 Dec
0.23%
0.07%24 Dec
1.00%26 Dec
0.20%31 Dec
1.07%8 Aug
1.18%
2.13%10 Aug
1.25%
1.45%19 Aug
Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.
What the audience does
Likes55.9%5 276 in total
Reposts4.6%437 in total
Replies2.1%196 in total
Quotes0.7%69 in total
Bookmarks36.7%3 462 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
Similar accounts
Airbnb México ✓
@airbnb_mx
44.3K followers
· 9.1K posts
NSSF_ke ✓
@NSSF_ke
44.3K followers
· 7.5K posts
Professor Anthony ✓
@ProfAnthony0114
44.3K followers
· 16K posts
Justin Steele
@J_Steele21
44.3K followers
· 5.8K posts
Ming ✓
@tslaming
44.3K followers
· 36.6K posts
Alex Vollo ✓
@AlexVolloFPL
44.3K followers
· 35.4K posts
ulala🇫🇷エンジニア視点の時事解説：日仏の思考の違いを解く ✓
@ulala_go
44.3K followers
· 180.5K posts
PaniG ✓
@jaijagannath081
44.3K followers
· 383.6K posts