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.

examples/sample-merge.json

View on GitHub
{
  "skill_name": "sql-optimizer",
  "base_version": "1.0.0",
  "local_version": "1.0.0-evo.3",
  "upstream_version": "1.1.0",
  "merged_version": "1.1.0-evo.1",
  "conflicts": [
    {
      "region": "instructions",
      "local_content": "## Optimization Steps\n1. Read query using Read tool\n2. Parse SQL and validate syntax\n3. Run EXPLAIN ANALYZE via parameterized psql command\n4. Analyze query plan for sequential scans\n5. Suggest index creation if sequential scan on large table",
      "upstream_content": "## Optimization Steps\n1. Read query\n2. Run EXPLAIN ANALYZE\n3. Analyze for sequential scans, hash joins, nested loops\n4. Suggest optimizations with expected improvement percentages\n5. Generate CREATE INDEX statements",
      "resolution": "smart_merge",
      "merged_content": "## Optimization Steps\n1. Read query using Read tool\n2. Parse SQL and validate syntax\n3. Run EXPLAIN ANALYZE via parameterized psql command\n4. Analyze query plan for sequential scans, hash joins, nested loops\n5. Suggest optimizations with expected improvement percentages\n6. Generate CREATE INDEX statements if applicable"
    }
  ],
  "merge_strategy": {
    "frontmatter": "field-level merge, upstream added new command",
    "description": "semantic merge, combined local not_for with upstream scope expansion",
    "instructions": "paragraph-level merge with one conflict resolved via smart merge",
    "scripts": "no scripts in either version"
  },
  "post_merge_eval": {
    "overall_score": 73,
    "verdict": "PASS",
    "regression_detected": false,
    "regression_dimensions": []
  },
  "metadata": {
    "merged_at": "2026-02-01T11:00:00Z",
    "merge_tool_version": "1.0.0"
  }
}
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