memory-audit

SkillDocs & knowledge

Keep your AI's MEMORY.md notes file free of stale entries. Memory Audit reviews the file and removes entries that are outdated or no longer accurate, so its notes stay current and reliable.

Use memory-audit in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add memory-audit and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the memory-audit skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Memory Audit, then ask your AI to audit its MEMORY.md file. It will go through the entries and clear out the ones that are outdated.

memory-auditStart free

What your AI can do with it

  • Review the entries in its MEMORY.md notes file
  • Identify entries that are stale or outdated
  • Remove entries that no longer apply
  • Keep its notes accurate and up to date

What this skill tells your AI

The instructions your AI receives, as published by fastled/fastled in .claude/skills/memory-audit/SKILL.md and read by Ahel’s review.

Audit code for memory safety issues specific to resource-constrained embedded systems.

$ARGUMENTS

What This Skill Analyzes

Stack Usage

  • Functions with large local arrays or structs (risk of stack overflow)
  • Deep call chains and recursion (stack depth estimation)
  • Task/thread stack size adequacy (FreeRTOS xTaskCreate stack parameter)
  • Alloca/VLA usage (variable-length arrays on stack)

Heap Fragmentation

  • Frequent small allocations and deallocations in hot paths
  • Mixed allocation sizes causing fragmentation over time
  • Missing deallocation (memory leaks)
  • Allocation in ISRs or time-critical code (heap locks can cause priority inversion)

Static Allocation Patterns

  • Global/static buffer sizing (too large wastes RAM, too small causes overflow)
  • Compile-time vs runtime allocation trade-offs
  • .bss and .data section usage
  • PSRAM vs internal SRAM placement decisions

Platform-Specific Concerns

  • ESP32: DRAM/IRAM split, PSRAM cache line alignment, DMA-capable memory
  • ARM Cortex-M: Stack/heap collision, MPU configuration, scatter file layout
  • AVR: 2KB SRAM constraint, PROGMEM usage for constants

How To Use

/memory-audit src/platforms/esp/32/drivers/
/memory-audit src/fl/channels/
/memory-audit Check if LED buffer allocation is safe for 1000+ LEDs on ESP32

What You'll Get

  • Memory usage breakdown by category (stack, heap, static)
  • Risk assessment for each finding (Critical/High/Medium/Low)
  • Specific recommendations with code examples
  • Platform-aware advice (e.g., "move to PSRAM" vs "reduce buffer size")

Signals

GitHub stars
8k
Forks
2k
Last commit
Sep 2026
Advanced
Item type
skill
Key
memory-audit
Source
github.com/fastled/fastled