/cf-ask

Context footprint: ⚡⚡ (medium) — what does this mean?

The /cf-ask skill answers questions about your codebase and saves the answers to persistent memory. Future sessions can reference these answers, building institutional knowledge.

Usage

/cf-ask [question]

What It Does

1. Recalls from Memory — Searches existing docs/memory/ using a 3-tier frontmatter grep (description → tags → full-text) for previously answered questions or related context
2. Analyzes Codebase — If not already answered, explores relevant files via the cf-explorer agent
3. Provides Answer — Gives clear, concise explanation with code examples
4. Saves to Memory — Delegates to cf-writer agent, stores Q&A in docs/memory/ with frontmatter (title, description, tags) for efficient future recall

Examples

/cf-ask How does the auth middleware work?

When to Use

• Onboarding to a new codebase
• Understanding design decisions
• Locating specific functionality
• Quick clarifications during development

Memory Integration

/cf-ask both reads from and writes to the Memory System:

• Recall — Before exploring code, searches existing docs/memory/ via MCP tools or a 3-tier frontmatter grep. If a direct match is found, the existing answer is presented — no redundant exploration needed.
• Save — After answering, saves the Q&A to docs/memory/ (organized by category: features/, conventions/, decisions/) with YAML frontmatter and indexes it via MCP for future recall.

See the Memory System reference for full details on tiers, search pipeline, memory types, and markdown format.

Benefits

• Reduces Ramp-Up Time — Captured knowledge speeds onboarding
• Fast Recall — Frontmatter grep finds relevant docs without reading full content
• Searchable — Find answers from previous conversations
• AI-Readable — Helps AI understand your codebase faster