self-correction-loop

Installation
SKILL.md

Self-Correction Loop

Core Principles

  1. Every correction is a compounding investment — A correction costs the user 30 seconds today but saves hours across all future sessions. Treat every correction as high-priority knowledge capture, not a one-time fix.

  2. Generalize before storing — "Use TimeProvider not DateTime.Now in the Orders module" becomes "Always use TimeProvider instead of DateTime.Now/UtcNow across all modules." Specific corrections become class-level rules.

  3. Categorize for retrieval — Rules organized by category (Code Style, Architecture, Naming, Testing, Data Access, API Design, Configuration, Performance) are findable. Uncategorized rules are forgotten.

  4. Deduplicate aggressively — Before adding a rule, scan existing rules for overlap. Update an existing rule rather than adding a near-duplicate. Memory bloat defeats the purpose.

  5. Review memory at session start — The first thing Claude should do in a new session is check MEMORY.md for project-specific rules. Knowledge captured but never reviewed is wasted effort.

Patterns

Correction Detection & Capture Flow

When a user corrects Claude's output, follow this exact sequence:

Installs
45
GitHub Stars
435
First Seen
Mar 17, 2026
self-correction-loop — codewithmukesh/dotnet-claude-kit