Cargo.toml
    ↓
Parse dependencies
    ↓
For each crate:
  ├─ Check ~/.claude/skills/{crate}/
  ├─ If missing: Check actionbook for llms.txt
  │     ├─ Found: /create-skills-via-llms
  │     └─ Not found: /create-llms-for-skills first
  └─ Load skill

/sync-crate-skills [--force]

# Read dependencies
cat Cargo.toml | grep -A 100 '\[dependencies\]' | grep -E '^[a-zA-Z]'

# List existing skills
ls ~/.claude/skills/

# 1. Fetch crate documentation
agent-browser open "https://docs.rs/{crate}/latest/{crate}/"
agent-browser get text ".docblock"
# Save content

# 2. Create skill directory
mkdir -p ~/.claude/skills/{crate}
mkdir -p ~/.claude/skills/{crate}/references

# 3. Create SKILL.md
# Use template from rust-skill-creator inline mode

# 4. Create reference files for key modules
agent-browser open "https://docs.rs/{crate}/latest/{crate}/{module}/"
agent-browser get text ".docblock"
# Save to ~/.claude/skills/{crate}/references/{module}.md

agent-browser close

WebFetch("https://docs.rs/{crate}/latest/{crate}/", "Extract API documentation overview, key types, and usage examples")

# 1. Parse root Cargo.toml for workspace members
cat Cargo.toml | grep -A 10 '\[workspace\]'

# 2. For each member, parse their Cargo.toml
for member in members; do
  cat ${member}/Cargo.toml | grep -A 100 '\[dependencies\]'
done

# 3. Aggregate and deduplicate dependencies
# 4. Generate skills for missing crates

# Clean specific crate
rm -rf ~/.claude/skills/{crate_name}

# Clean all generated skills
rm -rf ~/.claude/skills/*

# Remove old skill
rm -rf ~/.claude/skills/{crate_name}

# Re-generate (same as sync for single crate)
# Follow Step 3 above for the specific crate

~/.claude/skills/
├── tokio/
│   ├── SKILL.md
│   └── references/
├── serde/
│   ├── SKILL.md
│   └── references/
└── axum/
    ├── SKILL.md
    └── references/