L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Productivité · SKILL.md

confidence-check

confidence-check

Pre-implementation validation requiring ≥90% confidence before coding. Prevents wrong-direction work by assessing duplicates, architecture alignment, and root cause understanding.

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: confidence-check description: Pre-implementation validation requiring ≥90% confidence before coding. Prevents wrong-direction work by assessing duplicates, architecture alignment, and root cause understanding. metadata: {"clawdbot":{"requires":{"env":[]}}} user-invocable: true

Confidence Check

Pre-implementation validation framework. Never code at < 90% confidence.

Why This Matters

Wrong-direction work costs 5K-50K tokens to undo. A 2-minute confidence check saves hours of rework.

The 90% Rule

Before implementing ANY significant change:

Confidence < 70%  → STOP. Research more.
Confidence 70-89% → PAUSE. Fill gaps first.
Confidence ≥ 90%  → PROCEED with implementation.

Confidence Checklist

1. Duplicate Check (20 points)

  • Searched codebase for existing solution
  • Checked if similar pattern exists elsewhere
  • Verified not reinventing existing functionality

2. Architecture Alignment (20 points)

  • Understand where this fits in the system
  • Know which files/modules are affected
  • Approach matches existing patterns

3. Requirements Clarity (20 points)

  • Clear on what success looks like
  • Understand edge cases
  • Know acceptance criteria

4. Root Cause Understanding (20 points)

  • If fixing bug: know WHY it happens
  • If adding feature: know WHY it's needed
  • Understand the problem, not just symptoms

5. Implementation Path (20 points)

  • Know the steps to implement
  • Identified potential blockers
  • Have fallback approach

Scoring

Score each category 0-20:
- 0-5:   No understanding
- 6-10:  Partial understanding
- 11-15: Good understanding, some gaps
- 16-20: Full understanding

Total = sum of all categories (0-100)

Output Template

## Confidence Check: [Task]

### Assessment

| Category | Score | Notes |
|----------|-------|-------|
| Duplicate Check | /20 | |
| Architecture | /20 | |
| Requirements | /20 | |
| Root Cause | /20 | |
| Implementation | /20 | |
| **TOTAL** | **/100** | |

### Gaps Identified
- [ ] [gap 1 - how to fill]
- [ ] [gap 2 - how to fill]

### Verdict
**[PROCEED / RESEARCH MORE / STOP]**

### If RESEARCH MORE:
1. [specific question to answer]
2. [file to read]
3. [person to ask]

Quick Check (30 seconds)

For small changes, ask yourself:

  1. Have I read the code I'm changing? (Y/N)
  2. Do I know why this change is needed? (Y/N)
  3. Do I know how to test it works? (Y/N)

All Y → Proceed Any N → Pause and fill the gap

When to Skip

  • Typo fixes
  • Comment updates
  • Obvious one-liners
  • Explicitly requested by user with full context

Anti-Patterns

❌ "I'll figure it out as I go" ❌ "This looks similar to something I did before" ❌ "The user asked for it so it must be right" ❌ "I'll just try this and see"

✅ "I understand the problem and solution" ✅ "I've verified no existing solution" ✅ "I know exactly what files to change"

Skills enregistrées