lawzava/megapowers / extras/skills/megapowers-doctor
megapowers-doctor
VerifiedUse when Megapowers seems inactive or broken: a skill did not fire, the output style is missing, or the user asks to check the Megapowers setup.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.8 KB |
| references/directory-edition.md | markdown | 1.1 KB |
| references/fixes.md | markdown | 1.2 KB |
| references/invocation.md | markdown | 488 B |
SKILL.md
View on GitHub---
name: megapowers-doctor
description: "Use when Megapowers seems inactive or broken: a skill did not fire, the output style is missing, or the user asks to check the Megapowers setup."
when_to_use: "Trigger phrases: megapowers not working, skill did not fire, output style missing, check megapowers setup, is megapowers installed, megapowers doctor."
metadata:
short-description: Diagnose a Megapowers installation and give the exact fix
---
# Megapowers Doctor
The plugin root is two directories above this skill. With Go 1.25 or newer, run:
```bash
go run "<plugin root>/skills/megapowers-doctor/scripts/doctor.go" --root "<plugin root>" --harness "<harness>"
```
Set `<harness>` using [harness invocation](references/invocation.md).
`--harness` skips unrelated style checks.
It prints the plugin version and root, harness, output-style
setting, marketplace copy, recent skill loads, and optional agent registry. Problems start with
`WARN`. Quote only those lines and give one fix per line from
[fixes by check](references/fixes.md). If the command fails, report its exit
status and raw error; that failure is the diagnosis.
Without a local shell or Go, follow [manual checks](references/directory-edition.md).
## Did a skill fire?
A skill fired only if the session loaded its body; a catalog entry or a
prose mention is not a load. Inspect the session trace, or use the session
miner in `writing-agent-instructions`, to find successful load records. Report
counts and session identifiers, not contents. The doctor's `skill loads` line
counts sessions modified in the last seven days that contain a successful load.
If a matching task never loaded the skill, the defect is trigger wording or
skill discovery; use `writing-agent-instructions`
for the trigger. If the skill loaded but the outcome did not change, say so; a
load is not evidence of behavior.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |