memory
Memory Skill Policy
This skill is an MCP-facing facade for memory operations. Core memory policy (lifecycle/revalidation/promotion) belongs to Rust memory core, not this skill surface.
Router Logic
Scenario 1: User wants to store a transient finding
- Analyze: Determine if the item is transient operational memory (bug/workaround/incident note)
- Store: Call
save_memory(content, metadata) - Confirm: Show the saved memory ID
Scenario 2: User wants to remember/search
- Search: Call
search_memory(query, limit) - Format: Present results with relevance scores
- Respond: "I found X memories about that..."
Scenario 3: User asks for current operational memory status
- List: Call
get_memory_stats() - Recall: Call
search_memory()with relevant keywords - Present: Show structured summary with transient scope
Commands Reference
| Command | Description | Example |
|---|---|---|
save_memory |
Store short-term operational memory item | save_memory("Temporary workaround for timeout in parser", {"tag": "incident"}) |
search_memory |
Semantic search in memory | search_memory("git commit format", limit=5) |
index_memory |
Optimize vector index (IVF-FLAT) | index_memory() |
get_memory_stats |
Get memory count | get_memory_stats() |
load_skill |
Load skill manifest into memory | load_skill("git") |
Workflow: Store a Transient Workaround
User: Remember this temporary fix: increase parser timeout when MCP queue spikes.
Claude:
1. save_memory(
content="Temporary workaround: increase parser timeout under MCP queue spike",
metadata={"domain": "runtime", "kind": "workaround", "source": "user"}
)
2. → Saved memory [a1b2c3d4]: Temporary workaround: increase parser timeout...
3. → "Stored as short-term operational memory."
Workflow: Recall Recent Operational Context
User: What workaround did we use for MCP queue timeout?
Claude:
1. search_memory("MCP queue timeout workaround")
2. → Found 2 matches:
- [Score: 0.8921] Temporary workaround: increase parser timeout...
- [Score: 0.7234] Queue backpressure note...
3. → "I found recent operational memory for this issue..."
Memory vs Knowledge Skill
| Aspect | Memory (this skill) | Knowledge skill |
|---|---|---|
| Scope | Short-term operational context | Long-term reusable knowledge |
| Nature | Transient (can be purged after revalidation) | Stable (promoted/curated) |
| Purpose | "What recent issue/workaround context exists?" | "What durable rule/pattern should be reused?" |
| Policy | Managed by Rust memory core lifecycle | Managed by knowledge ingestion/curation flows |
| Exposure | MCP tool facade | MCP tool interface |
Best Practices
- Store transient operational memory, not permanent rules
- Include
kindin metadata (incident,workaround,observation) - Use clear, searchable phrasing in content
- Promote only proven durable patterns to
knowledge
More from tao3k/omni-dev-fusion
crawl4ai
Use when crawling web pages, extracting markdown content, or scraping website data with intelligent chunking and skeleton planning. Use when the user provides a URL or link to fetch or crawl.
50software_engineering
Use when analyzing project architecture, exploring codebase structure, understanding system design, reviewing code patterns, or navigating modular components.
18python_engineering
Use when linting Python code, formatting with ruff/black, running pytest tests, type checking with pyright, or modernizing Python 3.12+ standards.
18code_tools
Use when searching code by structure or meaning, analyzing code patterns, finding class or function definitions, or exploring codebase architecture.
16rust_engineering
Use when analyzing Rust project structure, managing Cargo dependencies, building and testing Rust projects, or generating Rust code.
16git
Use when committing code, managing branches, pushing to remote, creating pull requests, or performing version control operations. Conforms to docs/reference/skill-routing-value-standard.md.
15