memory-leak-audit
Reviews code for memory leaks and incorrect disposal of resources. Covers DOM handlers, event listeners, lifecycle callbacks, and patterns involving DisposableStore, MutableDisposable, Event.once, and onWillDispose.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Reviews code for memory leaks and incorrect disposal of resources. Covers DOM handlers, event listeners, lifecycle callbacks, and patterns involving DisposableStore, MutableDisposable, Event.once, and onWillDispose.
Investigates high memory usage and out-of-memory errors in JavaScript and Node.js applications. Uses Chrome DevTools MCP memory tools to capture, compare, and inspect heap snapshots and resolve leaks.
Use a two-tier memory system to help Claude understand workplace language and requests. Store working memory in CLAUDE.md and the fuller knowledge base in a memory/ directory.
Persist and retrieve architectural context, user preferences, and project milestones across sessions. Use for crash-safe checkpointing, updating persistent memories, and managing context window retention.
Uses AgentDB and HNSW vector search to persist patterns and retrieve similar solutions from prior work. Supports learning across tasks, sharing knowledge between agents, and building knowledge bases.
Scans project memory files and evaluates their quality against standardized criteria. Produces scored reports and recommendations, creates missing files, and makes targeted improvements with user approval.
Transfers mature lessons from a domain memory file into its instruction file. Supports global, user, and workspace scopes through the /memory-merger command.
Use four interactive steps to remove duplicates, move rules into CLAUDE.md or rules files, compress remaining memory entries, and validate cleanup. The description reports typical token reductions of 30–50%.
Promote project-specific memories into strict, small global memory only when they are cross-project, stable, useful, safe, and worth the global context cost. Load when the user says make this global, remember across projects, save this globally, or promote this learning.
Retrieve task-relevant project and global memory without loading everything. Load when the user asks what we decided, recall prior context, find memory about a feature, explain past rationale, resume a task, or check deferred ideas.
Guides memory-safe systems programming across Rust, C++, and C. Uses RAII, ownership, smart pointers, and resource management to prevent memory bugs.
Enables and troubleshoots memory search to preserve agent context. Covers memorySearch configuration, MEMORY.md, daily logs, and vector search setup.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name