diff --git a/!/tags/anthropic-academy.svg b/!/tags/anthropic-academy.svg new file mode 100644 index 0000000..268501b --- /dev/null +++ b/!/tags/anthropic-academy.svg @@ -0,0 +1,35 @@ + + Anthropic Academy β€” Browse Courses + + + + + + + + + + + + + + + + + + + + + + + + + Level up your Claude skills β€” explore 13+ courses at Anthropic Academy including Claude Code, API, MCP & more Β· Browse Courses + + diff --git a/!/tags/developed-by.svg b/!/tags/developed-by.svg new file mode 100644 index 0000000..f0c528d --- /dev/null +++ b/!/tags/developed-by.svg @@ -0,0 +1,35 @@ + + This project is 100% autopilot and developed by Claude Code + + + + + + + + + + + + + + + + + + + + + + + + + This project is 100% autopilot and developed by Claude Code + + diff --git a/README.md b/README.md index 1af87b6..bf00a85 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ practice makes claude perfect

-## CONCEPTS +## 🧠 CONCEPTS | Feature | Location | Description | |---------|----------|-------------| @@ -72,13 +72,7 @@ claude /weather-orchestrator ``` -| Component | Role | Example | -|-----------|------|---------| -| **Command** | Entry point, user interaction | [`/weather-orchestrator`](.claude/commands/weather-orchestrator.md) | -| **Agent** | Fetches data with preloaded skill (agent skill) | [`weather-agent`](.claude/agents/weather-agent.md) with [`weather-fetcher`](.claude/skills/weather-fetcher/SKILL.md) | -| **Skill** | Creates output independently (skill) | [`weather-svg-creator`](.claude/skills/weather-svg-creator/SKILL.md) | - -## DEVELOPMENT WORKFLOWS +## βš™οΈ DEVELOPMENT WORKFLOWS ### πŸ”₯ Hot - [Cross-Model (Claude Code + Codex) Workflow](development-workflows/cross-model-workflow/cross-model-workflow.md) [![Implemented](!/tags/implemented.svg)](development-workflows/cross-model-workflow/cross-model-workflow.md) @@ -96,13 +90,15 @@ claude - [Boris Cherny (Creator of Claude Code) - Feb 2026 Workflow](https://x.com/bcherny/status/2017742741636321619) - [Peter Steinberger (Creator of OpenClaw) Workflow](https://youtu.be/8lF7HmQ_RgY?t=2582) -## TIPS AND TRICKS +## πŸ’‘ TIPS AND TRICKS ![Community](!/tags/community.svg) -β–  **Prompting (2)** +β–  **Prompting (4)** - challenge Claude β€” "grill me on these changes and don't make a PR until I pass your test." or "prove to me this works" and have Claude diff between main and your branch [![Boris](https://img.shields.io/badge/Boris-3b82f6?style=flat)](https://x.com/bcherny/status/2017742752566632544) - after a mediocre fix β€” "knowing everything you know now, scrap this and implement the elegant solution" [![Boris](https://img.shields.io/badge/Boris-3b82f6?style=flat)](https://x.com/bcherny/status/2017742752566632544) +- Claude fixes most bugs by itself β€” paste the bug, say "fix", don't micromanage how πŸ‘Ά [![Boris](https://img.shields.io/badge/Boris-3b82f6?style=flat)](https://x.com/bcherny/status/2017742750473720121) +- say "use subagents" to throw more compute at a problem β€” offload tasks to keep your main context clean and focused πŸ‘Ά [![Boris](https://img.shields.io/badge/Boris-3b82f6?style=flat)](https://x.com/bcherny/status/2017742755737555434) β–  **Planning/Specs (5)** - always start with [plan mode](https://code.claude.com/docs/en/common-workflows) [![Boris](https://img.shields.io/badge/Boris-3b82f6?style=flat)](https://x.com/bcherny/status/2007179845336527000) @@ -211,17 +207,19 @@ claude ## REPORTS -| Report | Description | -|--------|-------------| -| [Agent SDK vs CLI System Prompts](reports/claude-agent-sdk-vs-cli-system-prompts.md) | Why Claude CLI and Agent SDK outputs may differβ€”system prompt architecture and determinism | -| [Browser Automation MCP Comparison](reports/claude-in-chrome-v-chrome-devtools-mcp.md) | Comparison of Playwright, Chrome DevTools, and Claude in Chrome for automated testing | -| [Global vs Project Settings](reports/claude-global-vs-project-settings.md) | Which features are global-only (`~/.claude/`) vs dual-scope, including Tasks and Agent Teams | -| [Skills Discovery in Monorepos](reports/claude-skills-for-larger-mono-repos.md) | How skills are discovered and loaded in large monorepo projects | -| [Agent Memory Frontmatter](reports/claude-agent-memory.md) | Persistent memory scopes (`user`, `project`, `local`) for subagents β€” enabling agents to learn across sessions | -| [Advanced Tool Use Patterns](reports/claude-advanced-tool-use.md) | Programmatic Tool Calling (PTC), Tool Search, and Tool Use Examples | -| [Usage, Rate Limits & Extra Usage](reports/claude-usage-and-rate-limits.md) | Usage commands (`/usage`, `/extra-usage`, `/cost`), rate limits, and pay-as-you-go overflow billing | -| [LLM Day-to-Day Degradation](reports/llm-day-to-day-degradation.md) | Why LLM performance varies day-to-day β€” infrastructure bugs, MoE routing variance, and psychology | -| [Agents vs Commands vs Skills](reports/claude-agent-command-skill.md) | When to use each extension mechanism β€” comparison table, resolution order, and worked example | +

+ Agent SDK vs CLI + Browser Automation MCP + Global vs Project Settings + Skills in Monorepos +
+ Agent Memory + Advanced Tool Use + Usage & Rate Limits + Agents vs Commands vs Skills +
+ LLM Degradation +

GitHub Trending
@@ -236,6 +234,19 @@ claude 3. Go to your own project and ask Claude to suggest what best practices from this repo you should add, give it this repo as a reference so it knows what's possible. ``` +## Developed by + +![Developed by](!/tags/developed-by.svg) + +> | Workflow | Description | +> |----------|-------------| +> | /workflows:best-practice:workflow-concepts | Update the README CONCEPTS section with the latest Claude Code features and concepts | +> | /workflows:best-practice:workflow-claude-settings | Track Claude Code settings report changes and find what needs updating | +> | /workflows:best-practice:workflow-claude-subagents | Track Claude Code subagents report changes and find what needs updating | +> | /workflows:best-practice:workflow-claude-commands | Track Claude Code commands report changes and find what needs updating | +> | /workflows:best-practice:workflow-claude-skills | Track Claude Code skills report changes and find what needs updating | + [![Claude for OSS](!/tags/claude-for-oss.svg)](https://claude.com/contact-sales/claude-for-oss) [![Claude Community Ambassador](!/tags/claude-community-ambassador.svg)](https://claude.com/community/ambassadors) [![Claude Certified Architect](!/tags/claude-certified-architect.svg)](https://anthropic.skilljar.com/claude-certified-architect-foundations-access-request) +[![Anthropic Academy](!/tags/anthropic-academy.svg)](https://anthropic.skilljar.com/) diff --git a/orchestration-workflow/orchestration-workflow.md b/orchestration-workflow/orchestration-workflow.md index b7837ce..9e9c00c 100644 --- a/orchestration-workflow/orchestration-workflow.md +++ b/orchestration-workflow/orchestration-workflow.md @@ -20,6 +20,14 @@ This showcases the **Command β†’ Agent β†’ Skill** architecture pattern, where: - An agent fetches data using its preloaded skill - A skill creates the visual output independently +## Component Summary + +| Component | Role | Example | +|-----------|------|---------| +| **Command** | Entry point, user interaction | [`/weather-orchestrator`](../.claude/commands/weather-orchestrator.md) | +| **Agent** | Fetches data with preloaded skill (agent skill) | [`weather-agent`](../.claude/agents/weather-agent.md) with [`weather-fetcher`](../.claude/skills/weather-fetcher/SKILL.md) | +| **Skill** | Creates output independently (skill) | [`weather-svg-creator`](../.claude/skills/weather-svg-creator/SKILL.md) | + ## Flow Diagram ```