Skip to content
Development
Skill

/doctor

Self-diagnostics for the harness — checks DB integrity, MCP wiring, claude binary availability, and recent run failures.

From plugin
wisp
412 skills4 agents1 command2 hooks
Install
$ npx -y skills add Samuel0101010/wisp-orchestrator --skill doctor --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/doctor

Context preview

The summary Claude sees to decide when to auto-load this skill.

Self-diagnostics for the harness — checks DB integrity, MCP wiring, claude binary availability, and recent run failures.

SKILL.md

doctor.SKILL.md
name: doctor
description: Self-diagnostics for the harness — checks DB integrity, MCP wiring, claude binary availability, and recent run failures.
model: haiku
allowed-tools: ["Bash", "Read"]
argument-hint: "(no args)"
timeout-ms: 90000

Run diagnostics in this order, output a Pass/Fail line per check: 1. `which claude` — claude CLI on PATH? 2. `claude --version` — version reported? 3. `node -e "require('better-sqlite3')"` — sqlite native binding loads? 4. Read `apps/dashboard-server/data/harness.db` exists (note: just check stat, do not open). 5. Last 5 runs from data/harness.db: how many failed?

Output: structured Pass/Fail report. Suggest one remediation per Fail.

Ships withwisp

Visual team-builder, plan-as-artifact, and live execution graph for autonomous Claude Code agent crews. Spawn a 3-role team, generate a DAG plan, run for hours, watch it ship in your browser.

Get the whole plugin

Other skills on wisp.