memory-audit
SkillDocs & knowledgeKeep 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 Memory Audit reviews the file and removes entries that are outdated or no longer accurate, so its notes stay current and reliable.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.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
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 It will go through the entries and clear out the ones that are outdated.
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- Identify entries that are stale or outdated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
xTaskCreatestack 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
.bssand.datasection 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
More in Docs & knowledge
Skill · mattpocock
More in Docs & knowledgecanvas-design
Skill · anthropics
More in Docs & knowledgedoc-coauthoring
Skill · anthropics
More in Docs & knowledgepopups
Skill · coreyhaines31
More in Docs & knowledgewriting-for-agents
Skill · mattpocock
More in Docs & knowledgespec-driven-development
Skill · addyosmani
More in Docs & knowledge