Skip to content

Evol-ai/SkillCompass

skill-compass

Verified

Evaluate skill quality, find the weakest dimension, and apply directed improvements. Also tracks usage to spot idle or risky skills. Use when: first session after install, or user asks about skill quality, evaluation, inbox, suggestions, or improvement.

scripts/hud-extra.js

View on GitHub
#!/usr/bin/env node
/**
 * hud-extra.js — Claude HUD extra-cmd script for SkillCompass
 *
 * Outputs JSON { "label": "🧭 N pending" } when inbox has pending suggestions.
 * Outputs { "label": "" } when nothing pending (HUD hides empty labels).
 *
 * Used by claude-hud via --extra-cmd flag.
 * Must execute in < 3 seconds, output < 10KB.
 */

const fs = require('node:fs');
const path = require('node:path');

// Try multiple possible inbox.json locations (plugin root first)
const pluginRoot = process.env.CLAUDE_PLUGIN_ROOT;
const candidates = [
  ...(pluginRoot ? [path.join(pluginRoot, '.skill-compass', 'cc', 'inbox.json')] : []),
  path.join(process.cwd(), '.skill-compass', 'cc', 'inbox.json'),
  path.join(process.env.HOME || process.env.USERPROFILE || '', '.skill-compass', 'cc', 'inbox.json')
];

let label = '';

for (const inboxPath of candidates) {
  try {
    if (!fs.existsSync(inboxPath)) continue;
    const data = JSON.parse(fs.readFileSync(inboxPath, 'utf-8'));
    const pending = (data.suggestions || []).filter(s =>
      s.status === 'pending' || s.status === 'viewed'
    ).length;

    if (pending > 0) {
      label = `🧭 ${pending} pending`;
    }
    break; // found inbox, stop searching
  } catch {
    // skip corrupt file, try next
  }
}

console.log(JSON.stringify({ label }));
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: 470kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall