Skip to content

Dragoon0x/taste-skills / skills/evaluation/self-assessment

self-assessment

Verified

Diagnose your taste gaps across six skill areas. Know what to practice. Use when starting a taste development program, checking progress, or identifying specific areas to improve.

FileKindSize
SKILL.mdskill md1.6 KB
---
name: self-assessment
description: "Diagnose your taste gaps across six skill areas. Know what to practice. Use when starting a taste development program, checking progress, or identifying specific areas to improve."
---

# Self-Assessment

Know your gaps. Practice the right thing.

## How to use

- `/self-assessment` Generate a taste self-assessment for the user.

## Constraints

### Six Skill Areas
Rate 1-5 on each:
- **Seeing:** Can you spot spacing inconsistencies, hierarchy issues, and craft details without being told?
- **Comparing:** Can you rank solutions and explain the ranking beyond personal preference?
- **Deconstructing:** Can you reverse-engineer the constraints and decisions behind a design?
- **Collecting:** Do you have an organized, principle-tagged reference library you can search in 60 seconds?
- **Articulating:** Can you explain design decisions without saying "it feels right"?
- **Applying:** Does your first design instinct usually turn out to be correct?

### Interpreting Results
- Lowest score = where to focus. Don't improve everything at once.
- High Seeing + Low Articulating = good instincts, can't convince anyone. Focus on vocabulary.
- High Collecting + Low Applying = great references, own work doesn't match. Focus on deconstruction.
- Even scores across the board (all 2s or 3s) = the plateau. Go deep in any one area.
- MUST retake every 3 months. Taste develops too slowly to notice daily.

### Anti-Patterns
- Overrating yourself on every dimension
- Skipping the assessment and jumping straight to exercises
- Focusing only on strengths instead of weaknesses
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: 472kUpdated 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