Add Docker support and documentation updates

- Add Dockerfile for containerized builds
- Add .dockerignore for cleaner builds
- Add CLAUDE.md for development guidance
- Update README and docs

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <[email protected]>

docs/DESIGN.md

@@ -317,6 +317,50 @@ Tool names must:
 - Contain only letters, numbers, underscores, and dashes
 - Not contain spaces or shell-problematic characters (`/\|&;$`"'<>(){}[]!?*#~`)
 
+## Tool Composition
+
+SmartTools are designed to chain together like any Unix command.
+
+### External Pipelines (Tool-to-Tool)
+
+```bash
+# Chain multiple SmartTools
+cat logs.txt | log-errors | summarize | translate --lang Japanese
+
+# Mix with standard Unix tools
+git log --oneline | head -20 | changelog | tee CHANGELOG.md
+
+# Build complex workflows
+cat *.py | review-code --focus security | json-extract --fields "issue, severity, file" | json2csv
+```
+
+Each tool reads stdin and writes stdout. No special integration needed.
+
+### Internal Pipelines (Multi-Step)
+
+Within a single tool, chain steps for preprocessing/validation:
+
+```yaml
+steps:
+  - type: code        # Preprocess
+    code: |
+      filtered = '\n'.join(l for l in input.split('\n') if 'ERROR' in l)
+    output_var: filtered
+  - type: prompt      # AI processes filtered input
+    prompt: "Explain these errors: {filtered}"
+    provider: claude-haiku
+    output_var: explanation
+  - type: code        # Post-process
+    code: |
+      result = f"Found {len(filtered.split(chr(10)))} errors:\n\n{explanation}"
+    output_var: result
+output: "{result}"
+```
+
+**When to use which:**
+- **External pipelines**: Reusable tools, different providers per stage, standard Unix interop
+- **Internal pipelines**: Tightly coupled steps, shared context, validation of AI output
+
 ## What This Design Doesn't Include
 
 Intentionally omitted (not needed for personal use):

docs/EXAMPLES.md

@@ -958,3 +958,101 @@ output: "{result}"
 2. **Use code steps** to validate AI output
 3. **Preprocess large inputs** to reduce tokens
 4. **Test with mock** before using real AI: `--provider mock`
+
+---
+
+## Pipeline Recipes
+
+SmartTools chain together like Unix commands. Here are practical examples:
+
+### Development Workflows
+
+```bash
+# Quick PR review: extract changes, review, summarize
+git diff main | diff-focus | review-code --focus "bugs and security" | tldr
+
+# Explain and fix an error in one pipeline
+python script.py 2>&1 | explain-error | tee error_analysis.txt
+
+# Generate tests for changed files only
+git diff --name-only | grep '\.py$' | xargs cat | gen-tests > new_tests.py
+
+# Create release notes from commits
+git log v1.0..v1.1 --oneline | changelog | translate --lang French > RELEASE_FR.md
+```
+
+### Data Processing
+
+```bash
+# Extract, transform, analyze
+curl -s api.example.com/data | json-extract --fields "users, revenue" | json2csv | csv-insights
+
+# Process multiple files
+for f in reports/*.txt; do
+    cat "$f" | json-extract --fields "total, date"
+done | json2csv > summary.csv
+
+# Clean and deduplicate contacts
+cat *.vcf | extract-contacts | sort -u -t',' -k2 > contacts.csv
+```
+
+### Text Processing Pipelines
+
+```bash
+# Translate technical docs for international team
+cat API.md | simplify --level "non-technical" | translate --lang Spanish > API_ES.md
+
+# Process customer feedback
+cat feedback.txt | summarize --length "10 points" | tone-shift --tone analytical | json-extract --fields "themes, sentiment"
+
+# Prepare content for different audiences
+cat whitepaper.txt | eli5 > simple_version.txt
+cat whitepaper.txt | summarize > executive_summary.txt
+```
+
+### Shell Functions
+
+Add these to `~/.bashrc` for common workflows:
+
+```bash
+# Review recent changes
+review-recent() {
+    git diff HEAD~"${1:-1}" | diff-focus | review-code | tldr
+}
+
+# Quick translate with summary
+translate-summary() {
+    cat "$1" | summarize | translate --lang "${2:-Spanish}"
+}
+
+# Analyze any log file
+analyze-log() {
+    cat "$1" | log-errors | summarize --length "5 key issues"
+}
+
+# Generate commit message and commit
+auto-commit() {
+    msg=$(git diff --staged | commit-msg)
+    echo "Commit message: $msg"
+    read -p "Commit? [y/N] " confirm
+    [[ $confirm == [yY] ]] && git commit -m "$msg"
+}
+```
+
+### Combining with Standard Unix Tools
+
+```bash
+# Filter before AI processing (saves tokens)
+cat huge.log | grep -i error | tail -100 | explain-error
+
+# Post-process AI output
+cat doc.txt | summarize | fmt -w 80 > formatted_summary.txt
+
+# Parallel processing
+find . -name "*.py" | parallel -j4 'cat {} | review-code > {}.review'
+
+# Watch and process
+tail -f app.log | grep --line-buffered ERROR | while read line; do
+    echo "$line" | explain-error
+done
+```