Use for persistent, visual, short-loop CAD modeling with cad.open, cad.add_part, cad.edit_part, cad.place, cad.import, cad.delete, cad.look, cad.inspect, Host-owned CAD Review, and cad.export.

Use when standard mechanical parts, fasteners, bearings, V-slot rails, T-nuts, wheels, or linear-motion parts are needed in Build123d CAD, and always before modeling a screw into a 3D-printed part — printed screw joints must come from this skill's kit, never hand-modeled.

Use when a development board, SBC, MCU module, or board-level enclosure constraint must be resolved for hardware or CAD design.

Review a project's archival_memory and propose promotions, near-duplicate merges, and stale cleanup for user approval. Read-only — applies nothing.

Use when drafting evidence-backed opening lines or subject lines for an eligible contact.

Use when validating an intent classifier or ranking independently eligible account and contact records from supplied evidence.

Write or fix a prompt for a reasoning model (Gemini Pro, GPT-4o, Claude Sonnet) so it holds context across a multi-step task. Use for any request to draft, structure or debug such a prompt. Not for fast models (use engineer-prompts-for-instant).

Build AI-IDE plugin MCP elements - stdio JSON-RPC servers, tool schemas, host wiring for Claude Code/Codex, event-name mapping and validation. Use when building or adding an MCP server to a plugin. Not for plugin manifests or packaging.

Build AI-IDE plugin hook elements - shared policies plus Claude Code/Codex/OpenCode/Cursor adapters for lifecycle events, blocking, audit, and context injection. Use when adding or configuring plugin hooks.

Guide for creating effective Subagents (custom agent definitions). Use when users want to create a new subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants. Works across IDEs (Cursor, OpenCode).

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"

Integrate with Google's Gemini CLI for delegating tasks to Gemini. Use when you need an alternative AI perspective, Google Search grounding, parallel task execution, or want to leverage Gemini's 1M token context window. Enables "Claude calling Gemini" patterns for diverse AI collaboration.

Diagnose and fix MCP configuration/runtime issues across supported integrations using agents CLI checks.

Use this skill when the user wants to review code, audit a pull request, check code quality, find bugs, or get feedback on implementation.

Learn about Agent Skills - how AI agents use skills, create new skills, and understand skill discovery in real-time. Use when user asks about skills, wants to create a skill, or wants to understand how Claude uses skills.

Determine which parts of the C codebase use Rust-defined C symbols. Use this when you want to understand which C code files may be impacted by changes to a Rust FFI crate.

Guidance on implementing the Data Layer using Repository pattern, Room (Local), and Retrofit (Remote) with offline-first synchronization.

Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.

Use when creating SQLModel database models, CRUD operations, queries with joins, or relationships. NOT when non-database operations, plain SQL, or unrelated data handling. Triggers: "SQLModel", "database model", "CRUD", "create/read/update/delete", "query", "ForeignKey", "relationship".

Runs the AI Engineer loop on pi — codegraph understand, gather materials, fill prompt templates, review those prompts, then fan out tasks. Use when spawning subagents, building worker prompts from templates, or gating fan-out on prompt review.