npx claudepluginhub joshuarweaver/cascade-code-general-misc-3 --plugin conarylabs-miraThis skill uses the workspace's default tool permissions.
<!-- plugin/skills/help/SKILL.md -->
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
| Command | Description |
|---|---|
/mira:help | Show all available commands and tools |
/mira:status | Quick health check: index stats, storage, active goals |
/mira:recap | Get session context, preferences, and active goals |
| Command | Description |
|---|---|
/mira:search <query> | Semantic code search — find code by meaning, not just text |
/mira:goals | Track cross-session objectives with milestones |
/mira:diff | Semantic analysis of git changes with impact assessment |
/mira:insights | Surface background analysis and predictions |
| Command | Description |
|---|---|
/mira:experts | Expert consultation via Agent Teams |
/mira:full-cycle | End-to-end expert review with implementation and QA |
/mira:qa-hardening | Production readiness review and hardening backlog |
/mira:refactor | Safe code restructuring with architect and reviewer validation |
Beyond slash commands, Mira provides MCP tools that Claude uses automatically:
code, diff, project, session, insights, goal, index, launch
Note: team is available via mira tool team ... (CLI only, not exposed as an MCP tool).
These power semantic search, call graph analysis, persistent memory, and more — no slash command needed.
Some tools require indexing before they work. Here's what depends on what.
index(action="project"))| Tool | Notes |
|---|---|
code(action="search") | Semantic search over indexed code |
code(action="callers") / code(action="callees") | Call graph analysis |
code(action="bundle") | Module extraction |
diff(include_impact=true) | Impact analysis of changes |
index(action="health"))| Tool | Notes |
|---|---|
code(action="dependencies") | Auto-queues health scan if missing |
code(action="dead_code") | Auto-queues health scan if missing |
insights() | Needs health data for analysis |
| Tool | Notes |
|---|---|
project(*), session(*), goal(*) | Session and goal management |
code(action="symbols") | Single-file parsing via tree-sitter |
diff() (without impact) | Git-based analysis only |
Note: project(action="start") auto-triggers background indexing, so most users never need to manually index.
Present the command reference above. If the user seems new to Mira, highlight /mira:status and /mira:recap as good starting points.
New session? Run /mira:recap to restore context from previous work.
Quick health check? Run /mira:status to see index stats, storage, and active goals.