/SKILL.md` | [](best-practice/claude-skills.md) [](implementation/claude-skills-implementation.md) Reusable knowledge, workflows, and slash commands — load on-demand or invoke with `/skill-name` |
| [**Workflows**](https://code.claude.com/docs/en/common-workflows) | [`.claude/commands/weather-orchestrator.md`](.claude/commands/weather-orchestrator.md) | [](orchestration-workflow/orchestration-workflow.md) |
| [**Hooks**](https://code.claude.com/docs/en/hooks) | `.claude/hooks/` | [](https://github.com/shanraisshan/claude-code-voice-hooks) [](.claude/hooks/) Deterministic scripts that run outside the agentic loop on specific events |
| [**MCP Servers**](https://code.claude.com/docs/en/mcp) | `.claude/settings.json`, `.mcp.json` | [](best-practice/claude-mcp.md) [](.mcp.json) Model Context Protocol connections to external tools, databases, and APIs |
@@ -49,7 +49,8 @@ practice makes claude perfect
## 
-Workflow orchestration using the **Command → Agent → Skill** pattern.
+See [orchestration-workflow](orchestration-workflow/orchestration-workflow.md) for implementation details of **Command → Agent → Skill** pattern.
+
@@ -61,10 +62,8 @@ Workflow orchestration using the **Command → Agent → Skill** pattern.
| **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) |
-See [orchestration-workflow](orchestration-workflow/orchestration-workflow.md) for implementation details.
-
-## DEVELOPMENT WORKFLOW
-- [RPI](workflow/rpi/rpi-workflow.md) [](workflow/rpi/rpi-workflow.md)
+## DEVELOPMENT WORKFLOWS
+- [RPI](development-workflows/rpi/rpi-workflow.md) [](development-workflows/rpi/rpi-workflow.md)
- [Boris Feb26 workflow](https://x.com/bcherny/status/2017742741636321619)
- [Ralph plugin with sandbox](https://www.youtube.com/watch?v=eAtvoGlpeRU) [](https://github.com/shanraisshan/novel-llm-26)
- [Human Layer RPI - Research Plan Implement](https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/ace-fca.md)
@@ -107,12 +106,13 @@ See [orchestration-workflow](orchestration-workflow/orchestration-workflow.md) f
- use mcp ([Claude in Chrome](https://code.claude.com/docs/en/chrome), [Playwright](https://github.com/microsoft/playwright-mcp), [Chrome DevTools](https://developer.chrome.com/blog/chrome-devtools-mcp)) to let claude see chrome console logs on its own
- provide screenshots of the issue
-
+
- [Boris setup - 5 tips | 03/Jan/26]() ● [Tweet](https://x.com/bcherny/status/2007179832300581177)
- [10 tips for using claude code by team itself | 01/Feb/26]() ● [Tweet](https://x.com/bcherny/status/2017742741636321619)
-- [12 ways how people are customizing their claudes | 12/Feb/26](reports/claude-boris-tips-feb-26.md) ● [Tweet](https://x.com/bcherny/status/2021699851499798911)
+- [12 ways how people are customizing their claudes | 12/Feb/26](tips/claude-boris-tips-feb-26.md) ● [Tweet](https://x.com/bcherny/status/2021699851499798911)
- [Git Worktrees - 5 ways how boris is using | 21 Feb 2026]() ● [Tweet](https://x.com/bcherny/status/2025007393290272904)
+- [Seeing like an Agent - lessons from building Claude Code (Thariq) | 28 Feb 2026]() ● [Article](https://x.com/trq212/status/2027463795355095314)
## REPORTS
diff --git a/best-practice/claude-skills.md b/best-practice/claude-skills.md
new file mode 100644
index 0000000..ba775de
--- /dev/null
+++ b/best-practice/claude-skills.md
@@ -0,0 +1,162 @@
+# Skills Best Practice
+
+
+[](../implementation/claude-skills-implementation.md)
+
+Complete reference for Claude Code skills — skill definitions, frontmatter fields, and invocation patterns.
+
+
+
+---
+
+## Frontmatter Fields
+
+Skills are defined in `.claude/skills//SKILL.md` with optional YAML frontmatter.
+
+| Field | Type | Required | Description |
+|-------|------|----------|-------------|
+| `name` | string | Recommended | Display name and `/slash-command` identifier. Defaults to the directory name if omitted |
+| `description` | string | Recommended | What the skill does. Shown in autocomplete and used by Claude for auto-discovery |
+| `argument-hint` | string | No | Hint shown during autocomplete (e.g., `[issue-number]`, `[filename]`) |
+| `disable-model-invocation` | boolean | No | Set `true` to prevent Claude from automatically invoking this skill |
+| `user-invocable` | boolean | No | Set `false` to hide from the `/` menu — skill becomes background knowledge only, intended for agent preloading |
+| `allowed-tools` | string | No | Tools allowed without permission prompts when this skill is active |
+| `model` | string | No | Model to use when this skill runs (e.g., `haiku`, `sonnet`, `opus`) |
+| `context` | string | No | Set to `fork` to run the skill in an isolated subagent context |
+| `agent` | string | No | Subagent type when `context: fork` is set (default: `general-purpose`) |
+| `hooks` | object | No | Lifecycle hooks scoped to this skill |
+
+---
+
+## Two Skill Patterns
+
+| Pattern | Loading | Invocation | Use Case |
+|---------|---------|-----------|----------|
+| **Skill** | On-demand | `/skill-name` or `Skill(skill: "name")` tool | Standalone reusable workflows invoked by commands or Claude |
+| **Agent Skill** | Preloaded at agent startup via `skills:` field | Automatic — full content injected into agent context | Domain knowledge or procedures baked into a specific agent |
+
+---
+
+## String Substitutions
+
+Available inside skill markdown for dynamic values:
+
+| Variable | Description |
+|----------|-------------|
+| `$ARGUMENTS` | All arguments passed when invoking the skill |
+| `$ARGUMENTS[N]` | Access a specific argument by 0-based index |
+| `$N` | Shorthand for `$ARGUMENTS[N]` (e.g., `$0`, `$1`) |
+| `${CLAUDE_SESSION_ID}` | Current session identifier |
+| `` !`command` `` | Dynamic context injection — shell command output replaces the placeholder before Claude sees it |
+
+---
+
+## Invocation
+
+| Method | Description |
+|--------|-------------|
+| `/skill-name` | Invoke directly from the slash command menu |
+| `/skill-name [args]` | Pass arguments that map to `$ARGUMENTS` |
+| `Skill(skill: "name")` | Programmatic invocation via the Skill tool (used in commands and agents) |
+| `skills: [name]` in agent frontmatter | Preload into an agent — full skill content injected at startup, not invoked on-demand |
+| Subdirectories | Skills in subdirectories use `/subdir:skill-name` |
+
+---
+
+## Example: Minimal Skill
+
+```yaml
+---
+description: Summarize staged changes into a concise changelog entry
+---
+
+Summarize the git diff in context into a one-paragraph changelog entry,
+focusing on what changed and why.
+```
+
+## Example: Minimal Agent Skill
+
+A skill preloaded into an agent as background knowledge — hidden from the `/` menu:
+
+```yaml
+---
+name: deploy-checklist
+description: Pre-flight deployment checks for production releases
+user-invocable: false
+---
+
+# Deploy Checklist
+
+Before any production deployment:
+1. Run all tests: `npm test`
+2. Check for uncommitted changes: `git status`
+3. Verify environment variables are set
+4. Confirm database migrations are ready
+```
+
+## Example: Full-Featured Skill (All Fields)
+
+```yaml
+---
+name: code-review
+description: Review code for quality, security, and performance issues
+argument-hint: [file-path]
+allowed-tools: Read, Grep, Glob
+model: sonnet
+context: fork
+agent: general-purpose
+hooks:
+ Stop:
+ - hooks:
+ - type: command
+ command: "./scripts/log-review-complete.sh"
+---
+
+Review the code at $0.
+
+## Checklist
+- [ ] Security: injection, XSS, hardcoded secrets
+- [ ] Performance: N+1 queries, unnecessary loops
+- [ ] Quality: naming, complexity, test coverage
+- [ ] Error handling: edge cases, failure modes
+```
+
+---
+
+## Scope and Priority
+
+When multiple skills share the same name, the higher-priority location wins:
+
+| Location | Scope | Priority |
+|----------|-------|----------|
+| Project (`.claude/skills/`) | This project only | 1 (highest) |
+| Personal (`~/.claude/skills/`) | All your projects | 2 |
+| Plugin (`/skills/`) | Where plugin is enabled | 3 (lowest) |
+
+---
+
+## Skills in This Repository
+
+Skills defined in `.claude/skills/` for this project:
+
+| Skill | User-Invocable | Preloaded Into | Description |
+|-------|----------------|----------------|-------------|
+| [`weather-svg-creator`](../.claude/skills/weather-svg-creator/SKILL.md) | Yes | — | Creates SVG weather card and writes output files |
+| [`weather-fetcher`](../.claude/skills/weather-fetcher/SKILL.md) | No | `weather-agent` | Fetches current temperature from wttr.in API |
+| [`agent-browser`](../.claude/skills/agent-browser/SKILL.md) | Yes | — | Browser automation CLI for AI agents |
+| [`presentation/vibe-to-agentic-framework`](../.claude/skills/presentation/vibe-to-agentic-framework/SKILL.md) | Yes | `presentation-curator` | Conceptual framework behind the presentation |
+| [`presentation/presentation-structure`](../.claude/skills/presentation/presentation-structure/SKILL.md) | Yes | `presentation-curator` | Slide format, weight system, and section structure |
+| [`presentation/presentation-styling`](../.claude/skills/presentation/presentation-styling/SKILL.md) | Yes | `presentation-curator` | CSS classes, component patterns, and syntax highlighting |
+
+---
+
+## Sources
+
+- [Claude Code Skills — Docs](https://code.claude.com/docs/en/skills)
+- [Skills Discovery in Monorepos](../reports/claude-skills-for-larger-mono-repos.md)
+- [Claude Code CHANGELOG](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md)
diff --git a/workflow/rpi/.claude/agents/code-reviewer.md b/development-workflows/rpi/.claude/agents/code-reviewer.md
similarity index 100%
rename from workflow/rpi/.claude/agents/code-reviewer.md
rename to development-workflows/rpi/.claude/agents/code-reviewer.md
diff --git a/workflow/rpi/.claude/agents/constitutional-validator.md b/development-workflows/rpi/.claude/agents/constitutional-validator.md
similarity index 100%
rename from workflow/rpi/.claude/agents/constitutional-validator.md
rename to development-workflows/rpi/.claude/agents/constitutional-validator.md
diff --git a/workflow/rpi/.claude/agents/documentation-analyst-writer.md b/development-workflows/rpi/.claude/agents/documentation-analyst-writer.md
similarity index 100%
rename from workflow/rpi/.claude/agents/documentation-analyst-writer.md
rename to development-workflows/rpi/.claude/agents/documentation-analyst-writer.md
diff --git a/workflow/rpi/.claude/agents/product-manager.md b/development-workflows/rpi/.claude/agents/product-manager.md
similarity index 100%
rename from workflow/rpi/.claude/agents/product-manager.md
rename to development-workflows/rpi/.claude/agents/product-manager.md
diff --git a/workflow/rpi/.claude/agents/requirement-parser.md b/development-workflows/rpi/.claude/agents/requirement-parser.md
similarity index 100%
rename from workflow/rpi/.claude/agents/requirement-parser.md
rename to development-workflows/rpi/.claude/agents/requirement-parser.md
diff --git a/workflow/rpi/.claude/agents/senior-software-engineer.md b/development-workflows/rpi/.claude/agents/senior-software-engineer.md
similarity index 100%
rename from workflow/rpi/.claude/agents/senior-software-engineer.md
rename to development-workflows/rpi/.claude/agents/senior-software-engineer.md
diff --git a/workflow/rpi/.claude/agents/technical-cto-advisor.md b/development-workflows/rpi/.claude/agents/technical-cto-advisor.md
similarity index 100%
rename from workflow/rpi/.claude/agents/technical-cto-advisor.md
rename to development-workflows/rpi/.claude/agents/technical-cto-advisor.md
diff --git a/workflow/rpi/.claude/agents/ux-designer.md b/development-workflows/rpi/.claude/agents/ux-designer.md
similarity index 100%
rename from workflow/rpi/.claude/agents/ux-designer.md
rename to development-workflows/rpi/.claude/agents/ux-designer.md
diff --git a/workflow/rpi/.claude/commands/rpi/implement.md b/development-workflows/rpi/.claude/commands/rpi/implement.md
similarity index 100%
rename from workflow/rpi/.claude/commands/rpi/implement.md
rename to development-workflows/rpi/.claude/commands/rpi/implement.md
diff --git a/workflow/rpi/.claude/commands/rpi/plan.md b/development-workflows/rpi/.claude/commands/rpi/plan.md
similarity index 100%
rename from workflow/rpi/.claude/commands/rpi/plan.md
rename to development-workflows/rpi/.claude/commands/rpi/plan.md
diff --git a/workflow/rpi/.claude/commands/rpi/research.md b/development-workflows/rpi/.claude/commands/rpi/research.md
similarity index 100%
rename from workflow/rpi/.claude/commands/rpi/research.md
rename to development-workflows/rpi/.claude/commands/rpi/research.md
diff --git a/workflow/rpi/rpi-workflow.md b/development-workflows/rpi/rpi-workflow.md
similarity index 100%
rename from workflow/rpi/rpi-workflow.md
rename to development-workflows/rpi/rpi-workflow.md
diff --git a/workflow/rpi/rpi-workflow.svg b/development-workflows/rpi/rpi-workflow.svg
similarity index 100%
rename from workflow/rpi/rpi-workflow.svg
rename to development-workflows/rpi/rpi-workflow.svg
diff --git a/orchestration-workflow/orchestration-workflow.md b/orchestration-workflow/orchestration-workflow.md
index 74ac8c4..c602a5d 100644
--- a/orchestration-workflow/orchestration-workflow.md
+++ b/orchestration-workflow/orchestration-workflow.md
@@ -23,63 +23,49 @@ This showcases the **Command → Agent → Skill** architecture pattern, where:
## Flow Diagram
```
- ┌─────────────────────────────────────────────────┐
- │ User Interaction │
- └─────────────────────────────────────────────────┘
- │
- ▼
- ┌───────────────────────────┐
- │ /weather-orchestrator │
- │ Command │
- │ (Entry point) │
- └───────────────────────────┘
- │
- ┌─────────────┤
- │ │
- ▼ │
- ┌──────────────┐ │
- │ AskUser │ │
- │ C° or F°? │ │
- └──────────────┘ │
- │ │
- ▼ │
- Step 2: Task tool │
- │ │
- ▼ │
- ┌───────────────────────────┐
- │ weather-agent │
- │ Agent │
- │ │
- │ preloaded skill: │
- │ - weather-fetcher │
- └───────────────────────────┘
- │
- │ Returns: temperature + unit
- │
- ▼
- Step 3: Skill tool
- │
- ▼
- ┌───────────────────────────┐
- │ weather-svg-creator │
- │ Skill │
- │ │
- │ Creates SVG card │
- │ Writes output files │
- └───────────────────────────┘
- │
- ┌────────┴────────┐
- │ │
- ▼ ▼
-┌──────────────────┐ ┌──────────────────┐
-│ weather.svg │ │ output.md │
-└──────────────────┘ └──────────────────┘
- │
- ▼
- ┌───────────────────────────┐
- │ Display Summary │
- │ to User │
- └───────────────────────────┘
+╔══════════════════════════════════════════════════════════════════╗
+║ ORCHESTRATION WORKFLOW ║
+║ Command → Agent → Skill ║
+╚══════════════════════════════════════════════════════════════════╝
+
+ ┌───────────────────┐
+ │ User Interaction │
+ └─────────┬─────────┘
+ │
+ ▼
+ ┌─────────────────────────────────────────────────────┐
+ │ /weather-orchestrator — Command (Entry Point) │
+ └─────────────────────────┬───────────────────────────┘
+ │
+ Step 1
+ │
+ ▼
+ ┌────────────────────────┐
+ │ AskUser — C° or F°? │
+ └────────────┬───────────┘
+ │
+ Step 2 — Task tool
+ │
+ ▼
+ ┌─────────────────────────────────────────────────────┐
+ │ weather-agent — Agent ● skill: weather-fetcher │
+ └─────────────────────────┬───────────────────────────┘
+ │
+ Returns: temp + unit
+ │
+ Step 3 — Skill tool
+ │
+ ▼
+ ┌─────────────────────────────────────────────────────┐
+ │ weather-svg-creator — Skill ● SVG card + output │
+ └─────────────────────────┬───────────────────────────┘
+ │
+ ┌────────┴────────┐
+ │ │
+ ▼ ▼
+ ┌────────────┐ ┌────────────┐
+ │weather.svg │ │ output.md │
+ └────────────┘ └────────────┘
```
## Component Details
diff --git a/presentation/index.html b/presentation/index.html
index 09db98c..b370508 100644
--- a/presentation/index.html
+++ b/presentation/index.html
@@ -1644,7 +1644,7 @@ managed-settings.json 
+
---
@@ -28,7 +28,7 @@ Set up your terminal for the best Claude Code experience:
- **Newlines**: If using Claude Code in an IDE terminal, Apple Terminal, Warp, or Alacritty, run `/terminal-setup` to enable shift+enter for newlines (so you don't need to type `\`)
- **Vim mode**: Run `/vim`
-
+
---
@@ -42,7 +42,7 @@ Run `/model` to pick your preferred effort level:
Boris's preference: High for everything.
-
+
---
@@ -54,7 +54,7 @@ Install from the official Anthropic plugin marketplace, or create your own marke
Run `/plugin` to get started.
-
+
---
@@ -66,7 +66,7 @@ You can also set the default agent for the main conversation using the `"agent"`
Run `/agents` to get started.
-
+
---
@@ -78,7 +78,7 @@ Out of the box, a small set of safe commands are pre-approved. To pre-approve mo
Full wildcard syntax is supported — e.g., `Bash(bun run *)` or `Edit(/docs/**)`.
-
+
---
@@ -88,7 +88,7 @@ Opt into Claude Code's open source sandbox runtime to improve safety while reduc
Run `/sandbox` to enable it. Sandboxing runs on your machine and supports both file and network isolation.
-
+
---
@@ -98,7 +98,7 @@ Custom status lines show up right below the composer, displaying model, director
Every team member can have a different statusline. Use `/statusline` to have Claude generate one based on your `.bashrc`/`.zshrc`.
-
+
---
@@ -106,7 +106,7 @@ Every team member can have a different statusline. Use `/statusline` to have Cla
Every key binding in Claude Code is customizable. Run `/keybindings` to re-map any key. Settings live reload so you can see how it feels immediately.
-
+
---
@@ -120,7 +120,7 @@ Hooks let you deterministically hook into Claude's lifecycle:
Ask Claude to add a hook to get started.
-
+
---
@@ -128,7 +128,7 @@ Ask Claude to add a hook to get started.
Customize your spinner verbs to add or replace the default list with your own verbs. Check the `settings.json` into source control to share verbs with your team.
-
+
---
@@ -140,7 +140,7 @@ Run `/config` and set an output style to have Claude respond using a different t
- **Learning** — to have Claude coach you through making code changes
- **Custom** — create custom output styles to adjust Claude's voice
-
+
---
@@ -155,7 +155,7 @@ Claude Code works great out of the box, but when you do customize, check your `s
With 37 settings and 84 environment variables (use the `"env"` field in your `settings.json` to avoid wrapper scripts), there's a good chance any behavior you want is configurable.
-
+
---