matrixorigin

Use Memoria as OpenClaw's durable memory slot. Triggers: "remember this", "save to memory", "what do you remember", "continue from last time", "forget this", "correct memory", "take a snapshot", "rollback memory", "branch memory", "merge memory", "use long-term memory".

Install Memoria and configure MCP for AI tools (Kiro, Cursor, Claude Code, Codex, Gemini CLI). Decision tree for Cloud vs self-hosted mode, database, embedding provider. Use when helping users set up Memoria.

Deploy Memoria with Docker Compose or Kubernetes. Environment variables, multi-instance setup, security. Use when deploying or configuring Memoria.

Memoria REST API endpoints, request/response formats, auth, rate limits. Use when calling or implementing API endpoints.

Memoria codebase structure, workspace layout, key traits, database tables, config patterns, and testing conventions. Use when navigating or modifying Memoria code.

Use Memoria for durable user/project memory in OpenClaw. Triggers: "remember this", "save to memory", "what do you remember", "forget this", "correct memory", "update memory", "use memoria".

Recover from accidental memory loss with snapshots and rollback. Triggers: "restore memory", "rollback memory", "undo deleted memory", "recover deleted memory", "take a memory snapshot".

Run embedding on-device with ONNX Runtime. Build from source, model selection, offline mode. Use when setting up local embedding without an API key.

MatrixOne database kernel development - deterministic CGo build/test setup, complete test matrices, hung-test diagnosis, GPU builds (MO_CL_CUDA=1 / cuVS), operator lifecycle contracts (Call/Reset), pipeline protocol, and the vector/fulltext index-plugin framework. Use when modifying kernel packages, running CGo-transitive tests, diagnosing compile/link/load/vendor failures or silent hangs, changing colexec/process/compile pipelines, or adding/editing index algorithms.

Pre-push self-review gate for MatrixOne changes — systematic first-principles review of the complete diff, including functional closure, unhappy paths, state/ownership models, wait-for dependencies, restart/reuse generations, and derived test matrices. Use before push/PR updates, when concurrency or lifecycle code changes, or when repeated review rounds reveal missed closure edges.

Full-codebase MatrixOne unhappy-path audit for leak, double cleanup, hung, and OOM risks using the Q1-Q3 framework plus ownership and wait-for graphs. Use for resource lifecycle, cancellation/close/fail-fast paths, goroutines, locks/channels/RPC waits, restart/reuse generations, or unbounded growth audits.

MatrixOne database kernel development - deterministic CGo build/test setup, complete test matrices, hung-test diagnosis, GPU builds (MO_CL_CUDA=1 / cuVS), operator lifecycle contracts (Call/Reset), pipeline protocol, and the vector/fulltext index-plugin framework. Use when modifying kernel packages, running CGo-transitive tests, diagnosing compile/link/load/vendor failures or silent hangs, changing colexec/process/compile pipelines, or adding/editing index algorithms.

Systematic MatrixOne kind/bug lifecycle triage — intake normalization with `needs-triage`, conservative promotion to active severity (`severity/s-1`, `severity/s0`, `severity/s1`), immediate downgrade to `deferred` with explanatory comments, optional five-level AI effort labeling (`ai-easy`, `ai-light`, `ai-medium`, `ai-heavy`, `ai-manual`) only when explicitly requested for issues/PRs, batched GitHub metadata updates, rollback-safe processing, and drift prevention. Use when asked to triage, classify, review, downgrade, defer, label, AI-effort-assess, or bulk-update MO bugs and related PRs.

Use when editing existing matrixorigin-blog articles, preserving frontmatter, changing dates or status, updating local image paths, keeping edits scoped to one article, and validating the result.

Use when creating a new article in matrixorigin-blog, choosing matrixorigin or memoria, creating the slug directory, setting frontmatter, adding local images or videos, validating content, and preparing a scoped PR.

Use when diagnosing why a matrixorigin-blog article is missing, not published, sorted unexpectedly, has broken media, or did not update on the downstream MatrixOrigin or Memoria website.

Use for matrixorigin-blog PR preparation, PR body drafting, review output, issue association wording, scope checks, generated-file checks, and choosing verification for content, docs, schema, or workflow changes.

Run TPC-H or TPC-DS benchmarks on Super Sirius or DuckDB CPU baseline — generate data, execute queries, validate results, and compare timings. Trigger when the user mentions benchmarking, TPC-DS, TPC-H, performance testing, query runtimes, or wants to compare Sirius vs DuckDB speed.

Discover and document a dependency library or submodule — analyzes all uses within the codebase, divides the library into logical modules, identifies which modules are used, and generates LLM-consumable API documentation for each module. Use when the user wants to understand a library dependency, map its modules, or generate API reference docs for a submodule.

Use this skill when the build fails, compilation errors occur, or you see undefined references, linker errors, CUDA compilation issues, missing headers, or template instantiation failures. Analyzes errors, suggests fixes, and iteratively rebuilds until success.

生成工作周报。采集 GitHub 数据，根据岗位角色生成不同视角的周报，支持对话补充内容。说"周报"即可触发；说"团队周报"走团队模式。