convez.ai
SkillProdutividadeIntermediário
uygnoey

Skills do Blog Claude

uygnoey/skills-from-claude-blog

Artefatos extraídos do blog Claude em specs prontas para uso

Ver no GitHub
InicialPluginScore · de 0 a 100

Repositório que converte automaticamente posts oficiais do blog Claude em especificações reutilizáveis (Skills, Agents, Hooks, Guides e Output Styles) seguindo os padrões do Claude Code. Atualizado a cada 4 horas, organiza artefatos por data e slug do post, com suporte multilíngue (EN, KO, ES, JA).

Instalação

$npx convez-ai uygnoey/skills-from-claude-blog

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
4
Forks
1
Acompanhando
0
Saúde
42%
Último commit
há 3 semanas
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Descobrir padrões e frameworks do Claude documentados oficialmente
  • Reutilizar Skills, Agents e Hooks testados da comunidade Anthropic
  • Acessar guias multilíngues de deployment e arquitetura

Veredito

Projeto útil de curadoria que democratiza artefatos oficiais do blog Claude em formatos imediatamente reutilizáveis. Excelente como referência e ponto de partida, mas requer familiaridade com specs do Claude Code (SKILL.md, agents, hooks) para máxima aproveitação.

README

A tradução para o português deste README ainda está na fila.

English · 한국어 · Español · 日本語

skills-from-claude-blog

Artifacts distilled from posts on claude.com/blog, organized by Claude Code's official extension specs. Not affiliated with Anthropic — this is a third-party summary project.

A repository that converts official Claude blog posts into Claude Code's official specs matching each post's character. A batch runs every 4 hours to reflect new posts and unprocessed ones.

Layout (per blog post)

One blog post = one <YYYY.MM.DD>_<blog-slug>/ folder at the repo root, where the date prefix is the post's published_date and <blog-slug> is the last URL segment. Folders sort naturally from newest to oldest on GitHub. The subfolders below appear conditionally based on the post's character.

<YYYY.MM.DD>_<blog-slug>/
├── description.en.md               # Human-readable English summary (always)
├── description.ko.md               # Korean summary (always)
├── description.es.md               # Spanish summary (always)
├── description.ja.md               # Japanese summary (always)
├── source.json                     # Source metadata (always)
│
├── skills/<name>/SKILL.md          # A. Agent Skills spec
├── agents/<name>.md                # B. Claude Code Subagent spec
├── guides/<name>.{en,ko,es,ja}.md  # C. Free-form multilingual guides
├── hooks/<name>.json +.md          # D. Claude Code Hooks JSON + notes
├── output-styles/<name>.md         # E. Output Style spec
└── plugin/                         # G. Plugin bundle (rare)
    ├── .claude-plugin/plugin.json
    └── skills|agents|hooks|output-styles/...

Official spec references

Spec selection matrix

VerdictTrigger questionArtifact
A. SkillDoes the post describe a reusable pattern / principle / framework / how-to?skills/<name>/SKILL.md
B. SubagentDoes the post explicitly define 2+ named agent roles?agents/<name>.md each
C. GuideIs the post deployment / architecture / methodology / survey in character?guides/<name>.{en,ko,es,ja}.md
D. HookDoes the post automate a lifecycle event (PreToolUse, PostToolUse, Stop, SessionStart…)?hooks/<name>.json + .md notes
E. Output StyleDoes the post define a full system-prompt tone/role/format swap (not a one-line tip)?output-styles/<name>.md
G. PluginDoes the post center on bundling multiple artifacts for distribution?whole plugin/ bundle
  • F. Slash Commands are not produced. Official docs mark .claude/commands/ as legacy and recommend .claude/skills/, so posts covering slash commands are converted into Skills.
  • Multiple verdicts applying at once is normal. Produce all.
  • When uncertain, default to including A. Skills are the most practically reusable.
  • Never invent roles, patterns, or scripts that aren't in the source. If unsure, quote the source.

Drop-in usage

Each artifact can be copied into a project as-is.

ArtifactDestination
skills/<name>/.claude/skills/<name>/ or ~/.claude/skills/<name>/
agents/<name>.md.claude/agents/<name>.md or ~/.claude/agents/<name>.md
hooks/<name>.json contentMerge into the hooks field of .claude/settings.json
output-styles/<name>.md.claude/output-styles/<name>.md
plugin/Load with --plugin-dir ./plugin

Index

Blog postPublishedArtifacts
The evolution of agentic surfaces: building with Claude Managed Agents2026-06-101 skill + 1 guide
New in Claude Managed Agents: run agents on a schedule and store environment variables in vaults2026-06-091 skill
Observability for developers building connectors2026-06-081 skill + 1 guide
Building intelligent apps for Apple platforms with Claude in the Foundation Models framework2026-06-081 skill + 1 guide + 1 plugin
The Claude Cowork product guide2026-06-051 skill + 1 guide
How one Anthropic seller rebuilt his team's workflows with Claude Code2026-06-051 skill + 1 guide + 1 style
Running an AI-native engineering org2026-06-031 skill
Lessons from building Claude Code: How we use skills2026-06-031 skill
How Anthropic enables self-service data analytics with Claude2026-06-031 skill
Best practices for getting started with Claude Cowork2026-06-031 skill + 1 guide
A harness for every task: dynamic workflows in Claude Code2026-06-021 skill + 1 guide
Introducing dynamic workflows in Claude Code2026-05-281 skill + 1 guide
How CodeRabbit Used Claude to Build an Agent Orchestration System2026-05-271 skill
Code w/ Claude London 2026: Rethinking how we build2026-05-261 skill + 1 guide
How Anthropic's finance team uses Claude to shape the narrative behind the numbers2026-05-221 skill + 1 guide
How our partners are putting Opus to work for cybersecurity2026-05-211 skill
Claude now works with more security and compliance tools2026-05-211 skill
Using Claude Code: The unreasonable effectiveness of HTML2026-05-201 skill + 1 guide
How an Anthropic sales leader uses Claude Cowork to run a 4,000-account book2026-05-201 skill + 1 guide
New in Claude Managed Agents: self-hosted sandboxes and MCP tunnels2026-05-191 skill + 1 guide
Deploying Claude across the legal industry2026-05-151 skill + 1 guide
The founder's playbook: Building an AI-native startup2026-05-141 skill + 1 guide
How Claude Code works in large codebases: Best practices and where to start2026-05-141 skill + 1 guide
Best practices for computer and browser use with Claude2026-05-131 skill + 1 guide
Code w/ Claude SF 2026: Building on the AI exponential2026-05-121 skill
Claude for the legal industry2026-05-121 skill + 1 guide + 1 style + 1 plugin
How Anthropic's cybersecurity team built a threat detection platform with Claude Code2026-05-111 skill
Agent view in Claude Code2026-05-111 skill + 1 guide
Collaborate with Claude across Excel, PowerPoint, Word and Outlook2026-05-071 skill + 1 guide
Claude Platform on AWS2026-05-071 skill + 1 guide
New in Claude Managed Agents: dreaming, outcomes, and multiagent orchestration2026-05-061 skill + 1 guide
Deploying Claude across financial services2026-05-051 skill
How a non-technical project manager built and shipped a stress management app with Claude Code in six weeks2026-05-011 skill + 4 agent + 1 guide
Lessons from building Claude Code: Prompt caching is everything2026-04-301 skill
How Kepler built verifiable AI for financial services with Claude2026-04-301 skill + 1 guide
Claude Security is now in public beta2026-04-301 skill
Building AI agents for the enterprise2026-04-301 skill + 1 guide
Product development in the agentic era2026-04-291 skill
New guide: Deploying Claude across the enterprise with Claude Cowork2026-04-291 skill
Claude API skill now in CodeRabbit, JetBrains, Resolve AI, and Warp2026-04-291 skill
Onboarding Claude Code like a new developer: Lessons from 17 years of development2026-04-281 skill
New connectors in Claude for everyday life2026-04-231 skill
Built-in memory for Claude Managed Agents2026-04-231 skill + 1 guide
Building agents that reach production systems with MCP2026-04-221 skill
Meet the winners of our Built with Opus 4.6 Claude Code hackathon2026-04-201 skill
Best practices for using Claude Opus 4.7 with Claude Code2026-04-161 skill + 1 guide
Using Claude Code: session management and 1M context2026-04-151 skill + 1 guide
Introducing routines in Claude Code2026-04-141 skill + 1 guide
Redesigning Claude Code on desktop for parallel agents2026-04-141 skill
Seeing like an agent: how we design tools in Claude Code2026-04-101 skill
Preparing your security program for AI-accelerated offense2026-04-102 skill + 3 agent + 1 guide
Multi-agent coordination patterns: Five approaches and when to use them2026-04-101 skill + 1 guide
The advisor strategy: Give agents an intelligence boost2026-04-091 skill
Making Claude Cowork ready for enterprise2026-04-091 skill
Claude Managed Agents: get to production 10x faster2026-04-081 guide
How Carta Healthcare gets AI to reason like a clinical abstractor2026-04-081 skill
How and when to use subagents in Claude Code2026-04-072 skill + 1 agent + 1 hook
Harnessing Claude's Intelligence: 3 Key Patterns for Building Apps2026-04-021 skill + 1 guide
Audit Claude Platform activity with the Compliance API2026-03-301 skill
Auto mode for Claude Code2026-03-241 skill
Put Claude to work on your computer2026-03-231 skill
Product management on the AI exponential2026-03-191 skill
Code with Claude comes to San Francisco, London, and Tokyo2026-03-181 skill + 1 guide
Claude builds interactive visuals right in your conversation2026-03-121 skill
Advancing Claude for Excel and PowerPoint2026-03-111 skill + 1 guide
Common workflow patterns for AI agents2026-03-051 skill + 1 guide
Improving skill-creator: Test, measure, and refine Agent Skills2026-03-031 skill
Cowork and plugins for finance2026-02-241 guide
Cowork and plugins for teams across the enterprise2026-02-241 guide
How AI helps break the cost barrier to COBOL modernization2026-02-231 skill
Preview, review, and merge with Claude Code2026-02-201 skill
Increase web search accuracy and efficiency with dynamic filtering2026-02-171 skill
Claude Enterprise, now available self-serve2026-02-121 skill
Behind the model launch: What customers discovered testing Claude Opus 4.6 early2026-02-091 skill
Customize Cowork with plugins - Claude.ai2026-01-301 guide
Measure Claude Code's impact with contribution metrics2026-01-291 skill
A complete guide to building skills for Claude2026-01-291 skill + 1 guide
How leading retailers are turning AI pilots into enterprise-wide transformation2026-01-281 skill + 1 guide
Updates to Claude Team2026-01-281 skill
Interactive connectors and MCP Apps2026-01-261 skill + 1 guide
How Anthropic's Growth Marketing team cut ad creation time from 30 minutes to 30 seconds with Claude Code2026-01-261 skill
Building multi-agent systems: When and how to use them2026-01-231 skill
Building agents with Skills: Equipping agents for specialized work2026-01-221 skill + 1 guide
Eight trends defining how software gets built in 20262026-01-211 skill
Extending Claude's capabilities with skills and MCP servers2025-12-191 skill
Skills for organizations, partners, the ecosystem2025-12-181 skill + 1 guide
Making Claude a better electrical engineer2025-12-121 skill
Claude Code power user customization: How to configure hooks2025-12-111 skill + 9 hook
How enterprises are building AI agents in 20262025-12-091 guide
How Anthropic's legal team cut review times from days to hours with Claude2025-12-081 skill
Claude Code and Slack2025-12-081 skill
What are the key benefits of transitioning to agentic coding for software development?2025-12-011 skill + 1 guide
Using CLAUDE.MD files: Customizing Claude Code for your codebase2025-11-251 skill
What's new in Claude: Turning Claude into your thinking partner2025-11-201 skill
How to create Skills for Claude: steps and examples2025-11-191 skill
How three YC startups built their companies with Claude Code2025-11-171 skill + 1 guide
Structured outputs on the Claude Developer Platform2025-11-141 skill
Improving frontend design through Skills2025-11-121 skill + 1 guide
Best practices for prompt engineering2025-11-101 skill
Building AI agents for startups2025-11-031 skill
What is Model Context Protocol? Connect AI to your world2025-10-311 skill + 1 guide
Introduction to agentic coding2025-10-301 skill + 1 guide
How Brex improves code quality and productivity with Claude Code2025-10-301 skill
Building AI agents in healthcare and life sciences2025-10-301 skill + 1 guide
Building AI agents for financial services2025-10-301 skill + 3 agent + 1 guide
Fix software bugs faster with Claude2025-10-281 skill
How to integrate APIs seamlessly2025-10-271 skill + 1 guide
Claude Code on the web2025-10-201 skill
Introducing Agent Skills2025-10-161 skill
How to scale agentic coding across your engineering organization2025-10-151 skill
Build responsive web layouts2025-10-101 skill
Customize Claude Code with plugins2025-10-091 skill + 1 guide + 1 plugin
Beyond permission prompts: making Claude Code more secure and autonomous2025-10-081 skill
Optimize code performance quickly2025-10-061 skill
How enterprises are driving AI transformation with Claude2025-10-011 skill
Claude and Slack2025-10-011 skill + 1 guide
Managing context on the Claude Developer Platform2025-09-291 skill
Building agents with the Claude Agent SDK2025-09-291 skill
Claude is now available in Microsoft 365 Copilot2025-09-241 skill + 1 guide
Bringing memory to teams2025-09-111 skill
Claude can now create and edit files2025-09-091 skill
Piloting Claude in Chrome2025-08-251 skill + 1 guide
Claude Code and new admin controls for business plans2025-08-201 skill
Prompt caching with Claude2025-08-141 skill
Claude Sonnet 4 now supports 1M tokens of context2025-08-121 skill
Automate security reviews with Claude Code2025-08-061 skill
Build and share AI-powered apps with Claude2025-07-251 skill
How Anthropic teams use Claude Code2025-07-241 skill
Discover tools that work with Claude2025-07-141 skill
Turn ideas into interactive AI-powered apps2025-06-251 skill
Introducing Citations on the Anthropic API2025-06-231 skill + 1 guide
Remote MCP support in Claude Code2025-06-181 skill + 1 guide
Mcp Connector2025-05-221 skill
Introducing web search on the Anthropic API2025-05-071 skill + 1 guide
Claude can now connect to your world2025-05-011 skill + 1 guide
Claude takes research to new places2025-04-151 skill
Introducing the Max Plan2025-04-091 skill
Claude on Google Cloud’s Vertex AI: FedRAMP High and IL2 Authorized2025-04-021 skill
Claude can now search the web2025-03-201 skill
Token-saving updates on the Anthropic API2025-03-13(no artifacts)
Get to production faster with the upgraded Anthropic Console2025-03-061 skill
Claude 3.5 Haiku on AWS Trainium2 and model distillation in Amazon Bedrock2024-12-031 skill
Introducing the analysis tool in Claude.ai2024-10-241 skill
Improve your prompts in the developer console2024-10-141 skill
Introducing the Message Batches API2024-10-081 skill
Workspaces in the Anthropic API Console2024-09-101 skill + 1 guide
Claude for Enterprise2024-09-101 skill + 1 guide
Claude Android app2024-07-161 skill
Fine-tune Claude 3 Haiku in Amazon Bedrock2024-07-101 skill
Evaluate prompts in the developer console2024-07-091 skill
Claude can now use tools2024-05-301 skill
Generate better prompts in the developer Console2024-05-201 skill
Introducing the Claude Team plan and iOS app2024-05-01(no artifacts)
Long context prompting for Claude 2.12023-12-061 skill
Claude on Amazon Bedrock now available to every AWS customer2023-09-281 skill
Claude 2 on Amazon Bedrock2023-08-231 skill

All guides and summaries are available in English, Korean, Spanish, and Japanese. Click the language switcher at the top of each file.

Batch operation

  • A Perplexity Computer cron runs every 4 hours.
  • Post list is harvested from https://www.claude.com/sitemap.xml and the /blog index.
  • Priority: new since last run (newest → oldest) → unprocessed older posts (oldest → newest) → unknown pub-date.
  • Up to 2 posts per run.

Authoring guidelines

  1. SKILL.md and agents/*.md follow the official spec (English).
  2. Hook JSON reflects the post's behavior verbatim; shell commands cite the source in comments.
  3. Output Styles copy the post's tone/role/format; if unsure, downgrade to a guide.
  4. name fields (Skill, Subagent, Output Style, Plugin): ^[a-z0-9-]+$, ≤64 chars, forbidden reserved words claude, anthropic.
  5. description is third-person and ≤1024 chars (Skill / Subagent).
  6. guides/ are authored in all four languages (.en.md, .ko.md, .es.md, .ja.md) with a language switcher at the top.
  7. Human summaries (description.*.md) cover the same four languages with a language switcher.
  8. Never invent content not in the source. If unsure, fall back to "see source".
  9. Artifacts are self-contained. SKILL.md, agents/*.md, hooks/*.md, and output-styles/*.md must not reference anything outside their own folder — no ../ paths, no cross-artifact links, no links back to description.*.md or guides/. If outside material is needed, copy it into a local companion file (references/, examples/, templates/, scripts/, prompts/, assets/, or a sibling .md).

Files

.
├── <YYYY.MM.DD>_<blog-slug>/           # One folder per blog post, date-prefixed
├── scripts/
│   ├── list_pending.py          # List pending URLs
│   ├── mark_processed.py        # Mark a URL processed
│   ├── update_last_run.py       # Stamp batch timestamp
│   ├── validate.py              # Pre-commit validator for all specs
│   └── strip_parent_refs.py     # Rewrite artifacts to drop ../ escapes
└── state/
    └── processed.json           # Processed URLs + last_run_at

License

  • Source posts (Claude blog) are © Anthropic. This repo contains summaries and quotations for study and reference only.
  • Repository code: MIT License.
Ver o original no GitHub

Bom para

Relacionados