Offshore
Photo
God of Prompt
RT @alex_prompter: 🚨 Anthropic just dropped a complete guide on how to build Skills like a pro.
And if you’re building AI agents, this is required reading.
It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design.
Here’s the big idea:
A Skill isn’t just a prompt.
It’s a structured system.
You package instructions inside a https://t.co/NFHAROW040 file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat.
But the real unlock is something they call progressive disclosure.
Instead of dumping everything into context:
• A lightweight YAML frontmatter tells Claude when to use the skill
• Full instructions load only when relevant
• Extra files are accessed only if needed
Less context bloat. More precision.
They also introduce a powerful analogy:
MCP gives Claude the kitchen.
Skills give it the recipe.
Without skills: users connect tools and don’t know what to do next.
With skills: workflows trigger automatically, best practices are embedded, API calls become consistent.
They outline 3 major patterns:
1) Document & asset creation
2) Workflow automation
3) MCP enhancement
And they emphasize something most builders ignore: testing.
Trigger accuracy.
Tool call efficiency.
Failure rate.
Token usage.
This isn’t about clever wording.
It’s about designing an execution layer on top of LLMs.
Skills work across https://t.co/6tb6ixQpca, Claude Code, and the API. Build once, deploy everywhere.
The era of “just write a better prompt” is ending.
Anthropic just handed everyone a blueprint for turning chat into infrastructure.
tweet
RT @alex_prompter: 🚨 Anthropic just dropped a complete guide on how to build Skills like a pro.
And if you’re building AI agents, this is required reading.
It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design.
Here’s the big idea:
A Skill isn’t just a prompt.
It’s a structured system.
You package instructions inside a https://t.co/NFHAROW040 file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat.
But the real unlock is something they call progressive disclosure.
Instead of dumping everything into context:
• A lightweight YAML frontmatter tells Claude when to use the skill
• Full instructions load only when relevant
• Extra files are accessed only if needed
Less context bloat. More precision.
They also introduce a powerful analogy:
MCP gives Claude the kitchen.
Skills give it the recipe.
Without skills: users connect tools and don’t know what to do next.
With skills: workflows trigger automatically, best practices are embedded, API calls become consistent.
They outline 3 major patterns:
1) Document & asset creation
2) Workflow automation
3) MCP enhancement
And they emphasize something most builders ignore: testing.
Trigger accuracy.
Tool call efficiency.
Failure rate.
Token usage.
This isn’t about clever wording.
It’s about designing an execution layer on top of LLMs.
Skills work across https://t.co/6tb6ixQpca, Claude Code, and the API. Build once, deploy everywhere.
The era of “just write a better prompt” is ending.
Anthropic just handed everyone a blueprint for turning chat into infrastructure.
tweet
Offshore
Photo
DAIR.AI
RT @omarsar0: MiniMax just dropped M2.5, a top-tier open-weight model.
Already competitive with models like Opus 4.6.
The speed at which open-weight models are improving is wild.
It's fast and surprisingly fluent at generating and operating Word, Excel, and PowerPoint files.
But the bigger deal for me is using M2.5 for long-horizon agents.
@MiniMax_AI's M2.5 is one of the first open models I've seen that show serious signs of improvement on long-running tasks.
M2.5 was trained with RL across hundreds of thousands of complex real-world environments.
The model learned to optimize its actions through planning, which is a meaningful difference from models that are merely prompted to plan.
When your agent runs for hours across multi-step tasks, a model that plans natively will drift less and waste fewer tokens.
You can try it on coding tasks, but I think the bigger unlock is using it as the backbone for an agent that operates across your full workspace (code, docs, spreadsheets, browser)
Benchmark results are nice too:
80.2% on SWE-Bench Verified. 76.3% on BrowseComp. 76.8% on BFCL for agentic tool-calling. 51.3% on Multi-SWE-Bench.
All of these map directly to what long-running agents need, which are coding, searching, tool use, and multi-step execution.
And here is what makes it practical:
$1 per hour at 100 tps!
With only 10B activated parameters, it's the smallest Tier-1 model, which makes self-hosting real. 37% faster execution times on complex tasks.
Find all the resources below:
tweet
RT @omarsar0: MiniMax just dropped M2.5, a top-tier open-weight model.
Already competitive with models like Opus 4.6.
The speed at which open-weight models are improving is wild.
It's fast and surprisingly fluent at generating and operating Word, Excel, and PowerPoint files.
But the bigger deal for me is using M2.5 for long-horizon agents.
@MiniMax_AI's M2.5 is one of the first open models I've seen that show serious signs of improvement on long-running tasks.
M2.5 was trained with RL across hundreds of thousands of complex real-world environments.
The model learned to optimize its actions through planning, which is a meaningful difference from models that are merely prompted to plan.
When your agent runs for hours across multi-step tasks, a model that plans natively will drift less and waste fewer tokens.
You can try it on coding tasks, but I think the bigger unlock is using it as the backbone for an agent that operates across your full workspace (code, docs, spreadsheets, browser)
Benchmark results are nice too:
80.2% on SWE-Bench Verified. 76.3% on BrowseComp. 76.8% on BFCL for agentic tool-calling. 51.3% on Multi-SWE-Bench.
All of these map directly to what long-running agents need, which are coding, searching, tool use, and multi-step execution.
And here is what makes it practical:
$1 per hour at 100 tps!
With only 10B activated parameters, it's the smallest Tier-1 model, which makes self-hosting real. 37% faster execution times on complex tasks.
Find all the resources below:
tweet
Dimitry Nakhla | Babylon Capital®
15 Quality Stocks With Forward FCF Yields Above the Risk-Free Rate (3-Month T-Bill: 3.60%) 💵
1. $FICO 3.61%
2. $NFLX 3.61%
3. $TDG 3.65%
4. $MA 3.78%
5. $MCO 3.84%
6. $MSCI 4.03%
7. $CPRT 4.07%
8. $NVO 4.09%
9. $V 4.12%
10. $APP 4.32%
11. $MANH 4.53%
12. $SPGI 5.04%
13. $NOW 5.30%
14. $INTU 6.22%
15. $CSU 7.10%
tweet
15 Quality Stocks With Forward FCF Yields Above the Risk-Free Rate (3-Month T-Bill: 3.60%) 💵
1. $FICO 3.61%
2. $NFLX 3.61%
3. $TDG 3.65%
4. $MA 3.78%
5. $MCO 3.84%
6. $MSCI 4.03%
7. $CPRT 4.07%
8. $NVO 4.09%
9. $V 4.12%
10. $APP 4.32%
11. $MANH 4.53%
12. $SPGI 5.04%
13. $NOW 5.30%
14. $INTU 6.22%
15. $CSU 7.10%
tweet
Offshore
Photo
Brady Long
RT @thisguyknowsai: I reverse-engineered the actual prompting frameworks that top AI labs use internally.
Not the fluff you see on Twitter.
The real shit that turns vague inputs into precise, structured outputs.
Spent 3 weeks reading OpenAI's model cards, Anthropic's constitutional AI papers, and leaked internal prompt libraries.
Here's what actually moves the needle:
tweet
RT @thisguyknowsai: I reverse-engineered the actual prompting frameworks that top AI labs use internally.
Not the fluff you see on Twitter.
The real shit that turns vague inputs into precise, structured outputs.
Spent 3 weeks reading OpenAI's model cards, Anthropic's constitutional AI papers, and leaked internal prompt libraries.
Here's what actually moves the needle:
tweet
Offshore
Photo
AkhenOsiris
RT @JaredSleeper: Amidst all of this, January was the biggest month for SaaS hiring in the last two years...🤦♂️ https://t.co/XG3hh6aWkK
tweet
RT @JaredSleeper: Amidst all of this, January was the biggest month for SaaS hiring in the last two years...🤦♂️ https://t.co/XG3hh6aWkK
tweet
Offshore
Photo
Javier Blas
RT @carbellorin: These companies didn’t just get access. All of them have existing contracts/projects in Venezuela. This is why GL50 was issued.
The GL49 was issued too, authorising companies to negotiate with the government/PDVSA and to enter into contingent contracts for “new” oil and gas investments.
tweet
RT @carbellorin: These companies didn’t just get access. All of them have existing contracts/projects in Venezuela. This is why GL50 was issued.
The GL49 was issued too, authorising companies to negotiate with the government/PDVSA and to enter into contingent contracts for “new” oil and gas investments.
Can't help but notice who ISN'T on this list of companies who just gained access to invest and operate in Venezuelan upstream. https://t.co/qrLcy4bd48 tweet
Offshore
Photo
Benjamin Hernandez😎
$RIVN: +27% | Q4 Earnings & R2 Outlook
Rivian losses narrowed significantly ($0.54 vs $0.68). 2026 delivery guidance of 67k units is solid. Institutional capital is rotating from Tesla into Rivian as the growth alternative. $17.50 is the key.
$SOC $ASST $OPEN $RADX $PULM https://t.co/qAHyAvsm9G
tweet
$RIVN: +27% | Q4 Earnings & R2 Outlook
Rivian losses narrowed significantly ($0.54 vs $0.68). 2026 delivery guidance of 67k units is solid. Institutional capital is rotating from Tesla into Rivian as the growth alternative. $17.50 is the key.
$SOC $ASST $OPEN $RADX $PULM https://t.co/qAHyAvsm9G
tweet
Offshore
Photo
Dimitry Nakhla | Babylon Capital®
“The biggest beneficiaries, however, would be real miners with real mines.”
One of the hardest lines in the Akre Shareholder Letter 📝
$NOW $CRM $CSU $ADBE $SNPS $CDNS $ROP $SAP $INTU $ADSK https://t.co/eDWzIgNmSG
tweet
“The biggest beneficiaries, however, would be real miners with real mines.”
One of the hardest lines in the Akre Shareholder Letter 📝
$NOW $CRM $CSU $ADBE $SNPS $CDNS $ROP $SAP $INTU $ADSK https://t.co/eDWzIgNmSG
tweet