JPeetz/agent-skills / skills/development/anti-over-engineering
anti-over-engineering
VerifiedUse when AI agents over-engineer code beyond user requests.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 477 B |
| LICENSE | other | 1.1 KB |
| SKILL.md | skill md | 12.0 KB |
| evals/evals.json | config | 2.5 KB |
| references/compatibility.md | markdown | 1.9 KB |
references/compatibility.md
View on GitHub# Compatibility Reference
## Western Agent Integration
- **Claude Code**: Install via `gh skill install JPeetz/agent-skills anti-over-engineering --agent claude-code`. Activates from natural-language triggers like "this is too much" or over-engineering patterns.
- **Hermes Agent**: Add `external_dirs` in config.yaml or `hermes skills install JPeetz/agent-skills/anti-over-engineering`. Available as `/anti-over-engineering` slash command.
- **Codex**: Copy to `~/.codex/skills/` or `~/.agents/skills/`. Activates on scope-creep signals.
- **Cursor**: Copy to `~/.cursor/skills/`. Activates via description matching.
## Complementary Skills
- **PUA (Push-Up Agent)**: When the AI is too passive or gives up easily — push it forward. Install alongside this skill for balanced behavior.
- **finding-unknowns-context-audit**: When the AI's context itself needs pruning to reduce over-engineering impulses.
- **code-review**: When you need structured review that also gates on scope.
## Pairing with PUA
Moyu and PUA solve opposite problems. They are complementary:
- **PUA**: When the AI is too passive or gives up easily — push it forward
- **Anti-Over-Engineering**: When the AI is too aggressive or over-engineers — pull it back
Install both for the best results. PUA sets the floor (don't slack), this skill sets the ceiling (don't over-do).
## Avoiding Over-Correction
Some engineering cultures value proactive architecture suggestions. If the user explicitly says "use your judgment" or "suggest the best approach," calibrate scope accordingly. This skill's default is conservative; override with user preference.
## Original Work
All techniques in this skill originate from [uucz/moyu](https://github.com/uucz/moyu). The English port maintains the full 4-level intervention system, anti-pattern tables, and detection signals from the original while adapting trigger descriptions for Western agent platforms.
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: 322k | 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: 322k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |