Menu
Open the erinra memory dashboard in the browser
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | memory-dashboard |
| description | Open the erinra memory dashboard in the browser |
Open the erinra memory visualization dashboard.
The erinra MCP server must be running with --web so the dashboard daemon is available. The recommended MCP setup:
claude mcp add erinra -- erinra serve --web -s user
Ensure the MCP server is alive. If you have NOT called any mcp__erinra__* tool earlier in this session, call mcp__erinra__context first to wake the server and start the web daemon:
mcp__erinra__context({
queries: ["user preferences"],
include_taxonomy: true,
content_budget: 500,
limit: 5
})
If you have already interacted with erinra MCP tools in this session, skip this step.
Open the dashboard. Run erinra dash --open-only to open it in the default browser:
erinra dash --open-only
This reads the daemon state, constructs an authenticated URL, opens the browser, and exits immediately.
If the command fails, tell the user their MCP server may not be configured with --web. Suggest updating their MCP configuration:
claude mcp remove erinra
claude mcp add erinra -- erinra serve --web -s user
~/.erinra/config.toml under [web], or via --port / --bind flags on erinra serveRun parallel code review agents and consolidate findings into a unified report
Capture a follow-up idea or task as a work-item draft without interrupting current work. Use to quickly jot down something you think of mid-task so it gets tracked. Works with nibs, GitHub, Azure DevOps, or a Markdown fallback.
Take an under-specified work item and make it actionable — resolve its open questions through a short interview grounded in the code, and give it acceptance criteria. Use on a captured draft, or any item too vague to start on.
Reconcile what was built against what was planned, record decisions and deviations, close the item (a single phase or a whole plan), and file follow-ups for deferred work. Use after finishing a phase or plan to keep planned and actual from drifting apart.
Orchestrate execution of MULTIPLE nibs in one run. Selects a queue, understands the nibs collectively (including how they fit together), then chooses the best execution mechanism per cluster — single series agent, parallel fan-out, scripted workflow, or agent team — and dispatches with ONE approval gate. Use when the user wants to work several nibs together (in parallel or series) rather than one at a time. Complements /decaf-build:auto-dev and /decaf-build:auto-tdd (which handle a single nib).
Direct development with automated review. Plans implementation, executes via subagent, then auto-reviews. Use for work that isn't test-driven (UI, config, styling, infrastructure, scaffolding).