ravindran v retweeted
An Anthropic engineer packed his whole engineering workflow into agent skills, so anyone can copy it
Addy Osmani, ex-Google, now works on Claude Code.
His repo turns a coding agent into a senior engineer.
Each skill is a structured workflow: when to use it, the steps, the excuses agents use to skip steps with a rebuttal for each, red flags, and the evidence required before it can call the job done.
25 skills, sorted by phase:
> Define: figure out what to build
> Plan: break it into small tasks
> Build: write it test-first
> Verify: debug and prove it works
> Review: quality, security, performance
> Ship: rollout, CI, docs
Skills also switch on by themselves. Start designing an API and the API skill kicks in.
Useful if you ship with agents solo, or want every agent on your team held to the same bar.
npx skills add addyosmani/agent-skills
repo: github.com/addyosmani/agent-…
ravindran v retweeted
Sometimes, when I feel hunger, I pretend it's fat leaving my body.
Hunger is a part of losing weight.
Learn to be friends with it.
ravindran v retweeted
I don't understand why everyone isn't using this yet this will make your Claude boost productivity by 300%
Anthropic engineer Lance Martin revealed a skill for Opus 5.5
Open Claude Code and type:
/claude-api prompt-audit
> Audits your skills, CLAUDE.md and prompts
> Removes everything that slows down the model
> Rewrites using the official Opus 5.5 guide
Your prompts are written for older models
This can be fixed in 3 minutes
Bookmark this
You don't need 10 hours a week to get good at AI.
You need 60 minutes a day, used like this:
10 min: write today's goal in one sentence
5 min: prompt with goal, context, ask
5 min: get a plan and approve it
30 min: build with Sonnet 5.5
10 min: save what worked
Run that loop for 30 days.
Same hour every day. Harder task every day.
That's the whole secret.
Bookmark this. follow @cyrilXBT
ravindran v retweeted
まだみんなが
これを使ってない理由が
わからない👇
Claudeの生産性を
一気に引き上げられる。
Anthropicのエンジニア
Lance Martinが、
Opus 5.5向けのSkillを公開
Claude Codeを開いて、
これを入力するだけ。
「/claude-api prompt-audit」
すると、
・Skillを監査
・CLAUDE.mdを監査
・プロンプトを監査
・モデルを遅くする原因を削除
・公式のOpus 5.5ガイドに
沿って書き直し
までまとめてやってくれる。
今使っているプロンプト、
実は古いモデル向けの
ままかもしれない。
それをたった3分で見直せる。
Claude Codeを使ってる人は
このページ、ブックマーク推奨👇
お待たせしました！！！
本日、
無料配布スタートです。
Claude code研究ラボで
作り込んできた、
完全オリジナル
「20大特典」
ついに公開します。
初期設定だけではありません。
・CLAUDE.md
・.claude/
・Skill
・MCP
・サブエージェント
・Hooks
・自己修正ループ
・Obsidian
・X投稿自動化
・長文記事作成
・Web制作
・デバッグまで。
初期設定 → 実践 → 自動化 →
自分専用のAI環境構築
ここまで一気に進められる内容を
20個にまとめています。
しかも、
読むだけの教材ではなく、
そのまま使える
プロンプト・テンプレート・
設定ファイルまで収録。
本来は有料配布を
考えていた内容ですが、
今回は感謝を込めて
期間限定で無料配布します。
皆さんがClaude code
を使いこなせるようにと
始めたアカウントなので
もし少しでもいいな、価値があるなと
感じていただけたら引用リツイートなどで
拡散していただけると嬉しいです！
欲しい方は
今のうちに下のリンクから
受け取って下さい👇
x.gd/A0iE2
ravindran v retweeted
If you want to learn more about Mods, what they are, and how to install them, check out this article:
medium.com/@dan.avila7/claud…
Jev + Vercel Sandbox Mod in Claude Code
This Mod spins up a sandbox on Vercel, while Jev classifies which commands should run inside the sandbox and which ones should run locally
Install:
npx claude-code-templates@latest --mod security/jev-vercel-sandbox
Link:
aitmpl.com/component/mod/sec…
Mods are a great way to customize your Claude Code workflows and connect other platforms directly into the agent loop
ravindran v retweeted
With age, the priorities get simpler:
– Train your body.
– Protect your sleep.
– Eat real food.
– Guard your peace.
Everything else is noise.
ravindran v retweeted
Your Claude Code install is missing a few things.
Here are 40 additions (grouped by what they do):
I've hoarded over a hundred Claude repos this year.
These cover workflows, skills, memory and tools, plus reference libraries worth keeping open.
BUILD A WORKFLOW
1. learn-claude-code → Learn how agents work.
2. karpathy-skills → Cut common coding mistakes.
3. superpowers → Plan, build and test.
4. ponytail → Keep the code simple.
5. gstack → Add planning and review workflows.
6. ECC → Add skills, memory and checks.
7. oh-my-claudecode → Coordinate agent teams.
8. Archon → Build repeatable coding workflows.
ADD SKILLS
9. taste-skill → Improve your designs.
10. anthropics skills → Browse official skills.
11. mattpocock skills → Add engineering skills.
12. wshobson agents → Find specialist agents.
13. claude-plugins → Browse official plugins.
14. addyosmani skills → Add engineering checks.
15. ui-ux-pro-max → Get interface design guidance.
16. awesome-claude-skills → Find more skills.
KEEP THE CONTEXT
17. planning-with-files → Keep plans in files.
18. claude-mem → Carry context across sessions.
19. codegraph → Map the code's connections.
20. graphify → Connect code and documents.
21. repomix → Pack a repo into one file.
22. agentmemory → Give agents persistent memory.
23. beads → Track work across sessions.
CONNECT TOOLS
24. multica → Assign issues to coding agents.
25. firecrawl → Turn websites into usable text.
26. cc-switch → Manage your coding tool setup.
27. context7 → Fetch current code documentation.
28. vibe-kanban → Manage agent tasks on a board.
29. github-mcp → Work with GitHub from Claude.
30. playwright-mcp → Let Claude use a browser.
31. serena → Find and edit relevant code.
32. claude-code-router → Route model requests.
33. awesome-mcp-servers → Find more connectors.
PROMPTS & USAGE
34. system-prompts-ai → Study AI tool prompts.
35. best-practice → Read Claude Code practices.
36. codex-plugin-cc → Add Codex reviews in Claude.
37. claude-hud → See your session usage.
38. rtk → Trim command output.
39. headroom → Compress what the model reads.
40. caveman → Get shorter replies (much shorter).
So pick one for the job you're doing.
Open its repo, follow the setup instructions and try it on a real task before adding the next one.
My Claude resource vault
→ charliehills.substack.com/p/…
Repost ♻️ to help someone in your network.
ravindran v retweeted
What if every AI agent had its own computer?
Not a chatbot window.
An actual workspace with a browser, terminal, repositories, files, memory and your team's tools.
That's useAgent.
An open-source AI coworker that gives Claude Code, Codex, OpenCode and Pi their own isolated computer for every task.
You can ask it to:
→ Research something in a real browser
→ Work directly with your repositories
→ Build a website
→ Create spreadsheets, PDFs or presentations
→ Run commands and modify code
→ Work from Slack
→ Remember team knowledge and playbooks
→ Run recurring tasks automatically
And here's the wild part:
You can watch the agent work.
The thread shows its timeline, tool activity, terminal and workspace.
You can step in, take control, or let it continue.
Every thread gets its own isolated Linux workstation, while credentials stay outside the sandbox behind a trusted gateway.
So the model isn't just answering:
“Here's how you could do it.”
It's actually getting a computer and doing the work.
Open-source. Self-hostable.
Built for agents that need to ship things, not just talk about them.
REPO👇
ravindran v retweeted
Claude Coders: Ultracode updates.
1. Toggle Ultracode On/Off with tab
2. Use Ultracode on any effort, not just xhigh
I find Low to Medium is the sweet spot.
Ultracode writes an orchestration script then generates a Claude swarm to execute it.
It is amazing.
ravindran v retweeted
I wrote an article about Claude that got 31 million views
Now, I’ve spent dozens of hours condensing the complete Anthropic Claude Agentic AI ecosystem into one clear diagram
Analyze it, implement it, and automate your workflow: build systems that work for you 24/7
I highly recommend bookmarking this one
ravindran v retweeted
Unsexy truth: if you work out only when it's “convenient” for you, you can't get
your dream physique.
The physique that you want demands sacrifices and discomfort
Jev is the Bitcoin moment for AI: 10,000 decisions cost 42 cents instead of $300
what it is, how to use it, and how to find the calls in your own agent that shouldn't cost what they cost:
step 1 → sort your agent's calls first. can you list every valid answer? would a human settle it at a glance? does it fire often enough for milliseconds to matter? three yeses and the call leaves the LLM
step 2 → send state plus typed questions, get typed probabilities back, no text generated at all. nothing to parse, and no fifth option nobody defined
step 3 → every fork becomes one of three primitives: Choice picks from up to 255 options, Score places state on a scale you define, Noul returns the probability of yes
step 4 → install in five minutes: pip install typesafe-sdk in a fresh venv, your key in an environment variable, the official skill via npx if a coding agent writes your calls
step 5 → test one decision in the Playground before writing app code: paste a ticket as state, add one Noul and one Choice, change one field and watch how far the distribution moves
step 6 → wire it end to end: three questions, one call, all evaluated in parallel. your code owns every branch after the answer
step 7 → build the gate that ships: code counts files, lines and test status, Jev answers ship, return or escalate, and blast radius gets checked before the verdict
step 8 → ask eight questions in one call, since a sixth or seventh barely moves the latency. anything that needs a fresh result goes in a second request
step 9 → rebuild the menu every turn: the workers online right now, the sources you hold right now, filtered in code before Jev chooses
step 10 → add the harness: a middleware that checks every tool call before it runs, and a router that picks the cheapest model able to finish the task
Browser Use ran a live flight search on it in 7 seconds for $0.0039. one developer classified 1,018 research papers for $0.08 total. another sorted 500 emails for 3.5 cents
the rule above all ten: if code already solves it, keep the code
now open your last agent run and count the forks that never needed a sentence
the full build with the code is in the article below
ravindran v retweeted
各部門の AWS アカウント上のデータを使い、部門横断で回答する Agent 構築 (マルチアカウント構成) のベスプラ記事です。
platform account の Agent と各 LOB account の MCP Server を AgentCore Gateway で繋ぐ方法が、セキュリティ・NW・評価の観点でまとまっています。 aws.amazon.com/jp/blogs/mach…
ravindran v retweeted
Lambda ランタイムのサポート終了日・Aurora MySQL の標準サポート終了日など，今までサービスごとのドキュメントを見てた EOL 情報が eol.json として公開されてるんだ❗️
AWS Service End-of-Life Data
github.com/awslabs/aws-servi…
ravindran v retweeted
YOU DON’T NEED 10 AI MODELS.
YOU NEED TO UNDERSTAND THE AI STACK.
ChatGPT, Claude, Gemini, Llama...
They’re just the models.
The real power comes from everything connected around them:
Model
→ Context
→ Memory
→ Tools
→ APIs
→ Agents
→ Actions
Give an AI model access to your database.
Add web search.
Add memory.
Add tools.
Now it can do more than generate text.
It can research.
It can decide.
It can call APIs.
It can execute tasks.
That’s the shift happening in AI.
We’re moving from:
“Ask AI a question”
to:
“Give AI a system to work inside.”
Linux Kernel Developers Consider Adding AGENTS.md To Help Guide AI/LLM Agents
phoronix.com/news/Linux-Cons…
ravindran v retweeted
Argo CD Architecture Explained 🚀
By the end of this blog,
You will understand how Argo CD actually works under the hood.
It covers,
- Core components and what they really do
- How they communicate and sync changes
- How Argo CD stores data and how to back it up properly
- How to run Argo CD in high availability mode
- Security and monitoring (Prometheus + Grafana)
and more..
𝗗𝗲𝘁𝗮𝗶𝗹𝗲𝗱 𝗚𝘂𝗶𝗱𝗲: devopscube.com/argo-cd-archi…
Over to you 👇
How are you using Argo CD today?
What is the key issue you faced in mnaging ArgoCD
Share it in the comments below.
#devops #gitops
